Merge branch 'dev' into nf-core-template-merge-2.4

.github/workflows/ci.yml

@@ -28,6 +28,21 @@ jobs:
           # Test latest edge release of Nextflow
           - NXF_VER: ""
             NXF_EDGE: "1"
+        parameters:
+          - "--perform_longread_clip false"
+          - "--perform_shortread_clipmerge false"
+          - "--shortread_clipmerge_tool fastp"
+          - "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
+          - "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs"
+          - "--shortread_clipmerge_tool adapterremoval"
+          - "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
+          - "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
+          - "--shortread_complexityfilter_tool bbduk"
+          - "--shortread_complexityfilter_tool prinseqplusplus"
+          - "--perform_runmerging"
+          - "--perform_runmerging --shortread_clipmerge_mergepairs"
+          - "--shortread_complexityfilter false --perform_shortread_hostremoval"
+
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
@@ -42,9 +57,17 @@ jobs:
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
 
+      - name: Show current locale
+        run: locale
+
+      - name: Set UTF-8 enabled locale
+        run: |
+          sudo locale-gen en_US.UTF-8
+          sudo update-locale LANG=en_US.UTF-8
+
       - name: Run pipeline with test data
         # TODO nf-core: You can customise CI pipeline run tests as required
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results ${{ matrix.parameters }}

.prettierignore

@@ -6,4 +6,5 @@ results/
 .DS_Store
 testing/
 testing*
+tests/
 *.pyc

CITATIONS.md

@@ -13,8 +13,49 @@
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [fastp](https://doi.org/10.1093/bioinformatics/bty560)
+
+  > Chen, Shifu, Yanqing Zhou, Yaru Chen, and Jia Gu. 2018. Fastp: An Ultra-Fast All-in-One FASTQ Preprocessor. Bioinformatics 34 (17): i884-90. 10.1093/bioinformatics/bty560.
+
+- [AdapterRemoval2](https://doi.org/10.1186/s13104-016-1900-2)
+
+  > Schubert, Mikkel, Stinus Lindgreen, and Ludovic Orlando. 2016. AdapterRemoval v2: Rapid Adapter Trimming, Identification, and Read Merging. BMC Research Notes 9 (February): 88. doi:10.1186/s13104-016-1900-2.
+
+- [Porechop](https://github.com/rrwick/Porechop)
+
+- [BBTools](http://sourceforge.net/projects/bbmap/)
+
+- [PRINSEQ++](https://doi.org/10.7287/peerj.preprints.27553v1)
+
+  > Cantu, Vito Adrian, Jeffrey Sadural, and Robert Edwards. 2019. PRINSEQ++, a Multi-Threaded Tool for Fast and Efficient Quality Control and Preprocessing of Sequencing Datasets. e27553v1. PeerJ Preprints. doi: 10.7287/peerj.preprints.27553v1.
+
+- [Kraken2](https://doi.org/10.1186/s13059-019-1891-0)
+
+  > Wood, Derrick E., Jennifer Lu, and Ben Langmead. 2019. Improved Metagenomic Analysis with Kraken 2. Genome Biology 20 (1): 257. doi: 10.1186/s13059-019-1891-0.
+
+- [MALT](https://doi.org/10.1038/s41559-017-0446-6)
+
+  > Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico. Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.
+
+- [MEGAN](https://doi.org/10.1371/journal.pcbi.1004957)
+
+  > Huson, Daniel H., Sina Beier, Isabell Flade, Anna Górska, Mohamed El-Hadidi, Suparna Mitra, Hans-Joachim Ruscheweyh, and Rewati Tappu. 2016. “MEGAN Community Edition - Interactive Exploration and Analysis of Large-Scale Microbiome Sequencing Data.” PLoS Computational Biology 12 (6): e1004957. doi: 10.1371/journal.pcbi.1004957.
+
+- [MetaPhlAn3](https://doi.org/10.7554/eLife.65088)
+
+  > Beghini, Francesco, Lauren J McIver, Aitor Blanco-Míguez, Leonard Dubois, Francesco Asnicar, Sagun Maharjan, Ana Mailyan, et al. 2021. “Integrating Taxonomic, Functional, and Strain-Level Profiling of Diverse Microbial Communities with BioBakery 3.” Edited by Peter Turnbaugh, Eduardo Franco, and C Titus Brown. ELife 10 (May): e65088. doi: 10.7554/eLife.65088
+
+- [Centrifuge](https://doi.org/10.1101/gr.210641.116)
+
+  > Kim, Daehwan, Li Song, Florian P. Breitwieser, and Steven L. Salzberg. 2016. “Centrifuge: Rapid and Sensitive Classification of Metagenomic Sequences.” Genome Research 26 (12): 1721-29. doi: 10.1101/gr.210641.116.
+
+- [DIAMOND](https://doi.org/10.1038/nmeth.3176)
+
+> Buchfink, Benjamin, Chao Xie, and Daniel H. Huson. 2015. “Fast and Sensitive Protein Alignment Using DIAMOND.” Nature Methods 12 (1): 59-60. doi: 10.1038/nmeth.3176.
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -19,7 +19,7 @@
 
 <!-- TODO nf-core: Write a 1-2 sentence summary of what data the pipeline is for and what it does -->
 
-**nf-core/taxprofiler** is a bioinformatics best-practice analysis pipeline for Taxonomic profiling of shotgun metagenomic data.
+**nf-core/taxprofiler** is a bioinformatics best-practice analysis pipeline for taxonomic profiling of shotgun metagenomic data. It allows for in-parallel profiling with multiple profiling tools against multiple databases, produces standardised output tables.
 
 The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!
 
@@ -32,7 +32,24 @@ On release, automated continuous integration tests run the pipeline on a full-si
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+2. Performs optional read pre-processing
+   - Adapter clipping and merging (short read: [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval2](https://github.com/MikkelSchubert/adapterremoval); long read: [porechop](https://github.com/rrwick/Porechop))
+   - Low complexity filtering ([bbduk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/), [PRINSEQ++](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus))
+   - Host read removal ([BowTie2](http://bowtie-bio.sourceforge.net/bowtie2/))
+   - Run merging
+3. Performs taxonomic profiling using one or more of:
+   - [Kraken2](https://ccb.jhu.edu/software/kraken2/)
+   - [MetaPhlAn3](https://huttenhower.sph.harvard.edu/metaphlan/)
+   - [MALT](https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/algorithms-in-bioinformatics/software/malt/)
+   - [DIAMOND](https://github.com/bbuchfink/diamond)
+   - [Centrifuge](https://ccb.jhu.edu/software/centrifuge/)
+   - [Kaiju](https://kaiju.binf.ku.dk/)
+   - [mOTUs](https://motu-tool.org/)
+   - [MetaMaps](https://github.com/DiltheyLab/MetaMaps)
+4. Perform optional post-processing with:
+   - [bracken](https://ccb.jhu.edu/software/bracken/)
+5. Standardises output tables
+6. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## Quick Start
 
@@ -55,10 +72,8 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 4. Start running your own analysis!
 
-   <!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
-
    ```console
-   nextflow run nf-core/taxprofiler --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
+   nextflow run nf-core/taxprofiler --input samplesheet.csv --databases database.csv --outdir <OUTDIR> --run_<TOOL1> --run_<TOOL1> -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
    ```
 
 ## Documentation
@@ -71,7 +86,7 @@ nf-core/taxprofiler was originally written by nf-core community.
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+[James A. Fellows Yates](https://github.com/jfy133), [Moritz Beber](https://github.com/Midnighter), [Lauri Mesilaakso](https://github.com/ljmesi), [Sofia Stamouli](https://github.com/sofsam), [Maxime Borry](https://github.com/maxibor).
 
 ## Contributions and Support
 

assets/samplesheet.csv

@@ -1,3 +1,6 @@
-sample,fastq_1,fastq_2
+sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
+2611,ERR5766174,ILLUMINA,,,/<path>/<to>/fasta/ERX5474930_ERR5766174_1.fa.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+2612,ERR5766176,ILLUMINA,/<path>/<to>/fastq/ERX5474932_ERR5766176_1.fastq.gz,/<path>/<to>/fastq/ERX5474932_ERR5766176_2.fastq.gz,
+2612,ERR5766180,ILLUMINA,/<path>/<to>/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
+2613,ERR5766181,ILLUMINA,/<path>/<to>/fastq/ERX5474937_ERR5766181_1.fastq.gz,/<path>/<to>/fastq/ERX5474937_ERR5766181_2.fastq.gz,
+ERR3201952,ERR3201952,OXFORD_NANOPORE,/<path>/<to>/fastq/ERR3201952.fastq.gz,,

bin/check_samplesheet.py

@@ -1,259 +1,227 @@
 #!/usr/bin/env python
 
-
+from distutils import extension
-"""Provide a command line tool to validate and transform tabular samplesheets."""
+import os
-
-
-import argparse
-import csv
-import logging
 import sys
-from collections import Counter
+import errno
-from pathlib import Path
+import argparse
 
 
-logger = logging.getLogger()
+def parse_args(args=None):
-
+    Description = (
-
+        "Reformat nf-core/taxprofiler samplesheet file and check its contents."
-class RowChecker:
-    """
-    Define a service that can validate and transform each given row.
-
-    Attributes:
-        modified (list): A list of dicts, where each dict corresponds to a previously
-            validated and transformed row. The order of rows is maintained.
-
-    """
-
-    VALID_FORMATS = (
-        ".fq.gz",
-        ".fastq.gz",
     )
+    Epilog = "Example usage: python check_samplesheet.py <FILE_IN> <FILE_OUT>"
 
-    def __init__(
+    parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
-        self,
+    parser.add_argument("FILE_IN", help="Input samplesheet file.")
-        sample_col="sample",
+    parser.add_argument("FILE_OUT", help="Output file.")
-        first_col="fastq_1",
+    return parser.parse_args(args)
-        second_col="fastq_2",
-        single_col="single_end",
-        **kwargs,
-    ):
-        """
-        Initialize the row checker with the expected column names.
 
-        Args:
-            sample_col (str): The name of the column that contains the sample name
-                (default "sample").
-            first_col (str): The name of the column that contains the first (or only)
-                FASTQ file path (default "fastq_1").
-            second_col (str): The name of the column that contains the second (if any)
-                FASTQ file path (default "fastq_2").
-            single_col (str): The name of the new column that will be inserted and
-                records whether the sample contains single- or paired-end sequencing
-                reads (default "single_end").
 
-        """
+def make_dir(path):
-        super().__init__(**kwargs)
+    if len(path) > 0:
-        self._sample_col = sample_col
+        try:
-        self._first_col = first_col
+            os.makedirs(path)
-        self._second_col = second_col
+        except OSError as exception:
-        self._single_col = single_col
+            if exception.errno != errno.EEXIST:
-        self._seen = set()
+                raise exception
-        self.modified = []
 
-    def validate_and_transform(self, row):
-        """
-        Perform all validations on the given row and insert the read pairing status.
 
-        Args:
+def print_error(error, context="Line", context_str=""):
-            row (dict): A mapping from column headers (keys) to elements of that row
+    error_str = "ERROR: Please check samplesheet -> {}".format(error)
-                (values).
+    if context != "" and context_str != "":
-
+        error_str = "ERROR: Please check samplesheet -> {}\n{}: '{}'".format(
-        """
+            error, context.strip(), context_str.strip()
-        self._validate_sample(row)
-        self._validate_first(row)
-        self._validate_second(row)
-        self._validate_pair(row)
-        self._seen.add((row[self._sample_col], row[self._first_col]))
-        self.modified.append(row)
-
-    def _validate_sample(self, row):
-        """Assert that the sample name exists and convert spaces to underscores."""
-        assert len(row[self._sample_col]) > 0, "Sample input is required."
-        # Sanitize samples slightly.
-        row[self._sample_col] = row[self._sample_col].replace(" ", "_")
-
-    def _validate_first(self, row):
-        """Assert that the first FASTQ entry is non-empty and has the right format."""
-        assert len(row[self._first_col]) > 0, "At least the first FASTQ file is required."
-        self._validate_fastq_format(row[self._first_col])
-
-    def _validate_second(self, row):
-        """Assert that the second FASTQ entry has the right format if it exists."""
-        if len(row[self._second_col]) > 0:
-            self._validate_fastq_format(row[self._second_col])
-
-    def _validate_pair(self, row):
-        """Assert that read pairs have the same file extension. Report pair status."""
-        if row[self._first_col] and row[self._second_col]:
-            row[self._single_col] = False
-            assert (
-                Path(row[self._first_col]).suffixes[-2:] == Path(row[self._second_col]).suffixes[-2:]
-            ), "FASTQ pairs must have the same file extensions."
-        else:
-            row[self._single_col] = True
-
-    def _validate_fastq_format(self, filename):
-        """Assert that a given filename has one of the expected FASTQ extensions."""
-        assert any(filename.endswith(extension) for extension in self.VALID_FORMATS), (
-            f"The FASTQ file has an unrecognized extension: {filename}\n"
-            f"It should be one of: {', '.join(self.VALID_FORMATS)}"
         )
-
+    print(error_str)
-    def validate_unique_samples(self):
+    sys.exit(1)
-        """
-        Assert that the combination of sample name and FASTQ filename is unique.
-
-        In addition to the validation, also rename the sample if more than one sample,
-        FASTQ file combination exists.
-
-        """
-        assert len(self._seen) == len(self.modified), "The pair of sample name and FASTQ must be unique."
-        if len({pair[0] for pair in self._seen}) < len(self._seen):
-            counts = Counter(pair[0] for pair in self._seen)
-            seen = Counter()
-            for row in self.modified:
-                sample = row[self._sample_col]
-                seen[sample] += 1
-                if counts[sample] > 1:
-                    row[self._sample_col] = f"{sample}_T{seen[sample]}"
-
-
-def read_head(handle, num_lines=10):
-    """Read the specified number of lines from the current position in the file."""
-    lines = []
-    for idx, line in enumerate(handle):
-        if idx == num_lines:
-            break
-        lines.append(line)
-    return "".join(lines)
-
-
-def sniff_format(handle):
-    """
-    Detect the tabular format.
-
-    Args:
-        handle (text file): A handle to a `text file`_ object. The read position is
-        expected to be at the beginning (index 0).
-
-    Returns:
-        csv.Dialect: The detected tabular format.
-
-    .. _text file:
-        https://docs.python.org/3/glossary.html#term-text-file
-
-    """
-    peek = read_head(handle)
-    handle.seek(0)
-    sniffer = csv.Sniffer()
-    if not sniffer.has_header(peek):
-        logger.critical(f"The given sample sheet does not appear to contain a header.")
-        sys.exit(1)
-    dialect = sniffer.sniff(peek)
-    return dialect
-
 
 def check_samplesheet(file_in, file_out):
     """
-    Check that the tabular samplesheet has the structure expected by nf-core pipelines.
+    This function checks that the samplesheet follows the following structure:
-
-    Validate the general shape of the table, expected columns, and each row. Also add
-    an additional column which records whether one or two FASTQ reads were found.
-
-    Args:
-        file_in (pathlib.Path): The given tabular samplesheet. The format can be either
-            CSV, TSV, or any other format automatically recognized by ``csv.Sniffer``.
-        file_out (pathlib.Path): Where the validated and transformed samplesheet should
-            be created; always in CSV format.
-
-    Example:
-        This function checks that the samplesheet follows the following structure,
-        see also the `viral recon samplesheet`_::
-
-            sample,fastq_1,fastq_2
-            SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz
-            SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz
-            SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz,
-
-    .. _viral recon samplesheet:
-        https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv
 
+    sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
+    2611,ERR5766174,ILLUMINA,,,ERX5474930_ERR5766174_1.fa.gz
+    2612,ERR5766176,ILLUMINA,ERX5474932_ERR5766176_1.fastq.gz,ERX5474932_ERR5766176_2.fastq.gz,
+    2612,ERR5766174,ILLUMINA,ERX5474936_ERR5766180_1.fastq.gz,,
+    2613,ERR5766181,ILLUMINA,ERX5474937_ERR5766181_1.fastq.gz,ERX5474937_ERR5766181_2.fastq.gz,
     """
-    required_columns = {"sample", "fastq_1", "fastq_2"}
+
-    # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`.
+    FQ_EXTENSIONS = (".fq", ".fq.gz", ".fastq", ".fastq.gz")
-    with file_in.open(newline="") as in_handle:
+    FA_EXTENSIONS = (
-        reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle))
+        ".fa",
-        # Validate the existence of the expected header columns.
+        ".fa.gz",
-        if not required_columns.issubset(reader.fieldnames):
+        ".fasta",
-            logger.critical(f"The sample sheet **must** contain the column headers: {', '.join(required_columns)}.")
+        ".fasta.gz",
+        ".fna",
+        ".fna.gz",
+        ".fas",
+        ".fas.gz",
+    )
+    INSTRUMENT_PLATFORMS = [
+        "ABI_SOLID",
+        "BGISEQ",
+        "CAPILLARY",
+        "COMPLETE_GENOMICS",
+        "DNBSEQ",
+        "HELICOS",
+        "ILLUMINA",
+        "ION_TORRENT",
+        "LS454",
+        "OXFORD_NANOPORE",
+        "PACBIO_SMRT",
+    ]
+
+    sample_mapping_dict = {}
+    with open(file_in, "r") as fin:
+
+        ## Check header
+        MIN_COLS = 4
+        HEADER = [
+            "sample",
+            "run_accession",
+            "instrument_platform",
+            "fastq_1",
+            "fastq_2",
+            "fasta",
+        ]
+        header = [x.strip('"') for x in fin.readline().strip().split(",")]
+        if header[: len(HEADER)] != HEADER:
+            print(
+                "ERROR: Please check samplesheet header -> {} != {}".format(
+                    ",".join(header), ",".join(HEADER)
+                )
+            )
             sys.exit(1)
-        # Validate each row.
+
-        checker = RowChecker()
+        ## Check sample entries
-        for i, row in enumerate(reader):
+        for line in fin:
-            try:
+            lspl = [x.strip().strip('"') for x in line.strip().split(",")]
-                checker.validate_and_transform(row)
+
-            except AssertionError as error:
+            # Check valid number of columns per row
-                logger.critical(f"{str(error)} On line {i + 2}.")
+            if len(lspl) < len(HEADER):
-                sys.exit(1)
+                print_error(
-        checker.validate_unique_samples()
+                    "Invalid number of columns (minimum = {})!".format(len(HEADER)),
-    header = list(reader.fieldnames)
+                    "Line",
-    header.insert(1, "single_end")
+                    line,
-    # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`.
+                )
-    with file_out.open(mode="w", newline="") as out_handle:
+            num_cols = len([x for x in lspl if x])
-        writer = csv.DictWriter(out_handle, header, delimiter=",")
+            if num_cols < MIN_COLS:
-        writer.writeheader()
+                print_error(
-        for row in checker.modified:
+                    "Invalid number of populated columns (minimum = {})!".format(
-            writer.writerow(row)
+                        MIN_COLS
+                    ),
+                    "Line",
+                    line,
+                )
+
+            ## Check sample name entries
+            (
+                sample,
+                run_accession,
+                instrument_platform,
+                fastq_1,
+                fastq_2,
+                fasta,
+            ) = lspl[: len(HEADER)]
+            sample = sample.replace(" ", "_")
+            if not sample:
+                print_error("Sample entry has not been specified!", "Line", line)
+
+            ## Check FastQ file extension
+            for fastq in [fastq_1, fastq_2]:
+                if fastq:
+                    if fastq.find(" ") != -1:
+                        print_error("FastQ file contains spaces!", "Line", line)
+                    if not fastq.endswith(FQ_EXTENSIONS):
+                        print_error(
+                            f"FastQ file does not have extension {' or '.join(list(FQ_EXTENSIONS))} !",
+                            "Line",
+                            line,
+                        )
+            if fasta:
+                if fasta.find(" ") != -1:
+                    print_error("FastA file contains spaces!", "Line", line)
+                if not fasta.endswith(FA_EXTENSIONS):
+                    print_error(
+                        f"FastA file does not have extension {' or '.join(list(FA_EXTENSIONS))}!",
+                        "Line",
+                        line,
+                    )
+            sample_info = []
+
+            # Check run_accession
+            if not run_accession:
+                print_error("Run accession has not been specified!", "Line", line)
+            else:
+                sample_info.append(run_accession)
+
+            # Check instrument_platform
+            if not instrument_platform:
+                print_error("Instrument platform has not been specified!", "Line", line)
+            else:
+                if instrument_platform not in INSTRUMENT_PLATFORMS:
+                    print_error(
+                        f"Instrument platform {instrument_platform} is not supported!",
+                        f"List of supported platforms {', '.join(INSTRUMENT_PLATFORMS)}",
+                        "Line",
+                        line,
+                    )
+                sample_info.append(instrument_platform)
+
+            ## Auto-detect paired-end/single-end
+            if sample and fastq_1 and fastq_2:  ## Paired-end short reads
+                sample_info.extend(["0", fastq_1, fastq_2, fasta])
+            elif sample and fastq_1 and not fastq_2:  ## Single-end short/long fastq reads
+                sample_info.extend(["1", fastq_1, fastq_2, fasta])
+            elif (
+                sample and fasta and not fastq_1 and not fastq_2
+            ):  ## Single-end long reads
+                sample_info.extend(["1", fastq_1, fastq_2, fasta])
+            elif fasta and (fastq_1 or fastq_2):
+                print_error(
+                    "FastQ and FastA files cannot be specified together in the same library!",
+                    "Line",
+                    line,
+                )
+            else:
+                print_error("Invalid combination of columns provided!", "Line", line)
+
+            ## Create sample mapping dictionary = { sample: [ run_accession, instrument_platform, single_end, fastq_1, fastq_2 , fasta ] }
+            if sample not in sample_mapping_dict:
+                sample_mapping_dict[sample] = [sample_info]
+            else:
+                if sample_info in sample_mapping_dict[sample]:
+                    print_error("Samplesheet contains duplicate rows!", "Line", line)
+                else:
+                    sample_mapping_dict[sample].append(sample_info)
+
+    ## Write validated samplesheet with appropriate columns
+    HEADER_OUT = [
+        "sample",
+        "run_accession",
+        "instrument_platform",
+        "single_end",
+        "fastq_1",
+        "fastq_2",
+        "fasta",
+    ]
+    if len(sample_mapping_dict) > 0:
+        out_dir = os.path.dirname(file_out)
+        make_dir(out_dir)
+        with open(file_out, "w") as fout:
+            fout.write(",".join(HEADER_OUT) + "\n")
+            for sample in sorted(sample_mapping_dict.keys()):
+                for idx, val in enumerate(sample_mapping_dict[sample]):
+                    fout.write(f"{sample},{','.join(val)}\n")
+    else:
+        print_error("No entries to process!", "Samplesheet: {}".format(file_in))
 
 
-def parse_args(argv=None):
+def main(args=None):
-    """Define and immediately parse command line arguments."""
+    args = parse_args(args)
-    parser = argparse.ArgumentParser(
+    check_samplesheet(args.FILE_IN, args.FILE_OUT)
-        description="Validate and transform a tabular samplesheet.",
-        epilog="Example: python check_samplesheet.py samplesheet.csv samplesheet.valid.csv",
-    )
-    parser.add_argument(
-        "file_in",
-        metavar="FILE_IN",
-        type=Path,
-        help="Tabular input samplesheet in CSV or TSV format.",
-    )
-    parser.add_argument(
-        "file_out",
-        metavar="FILE_OUT",
-        type=Path,
-        help="Transformed output samplesheet in CSV format.",
-    )
-    parser.add_argument(
-        "-l",
-        "--log-level",
-        help="The desired log level (default WARNING).",
-        choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"),
-        default="WARNING",
-    )
-    return parser.parse_args(argv)
-
-
-def main(argv=None):
-    """Coordinate argument parsing and program execution."""
-    args = parse_args(argv)
-    logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s")
-    if not args.file_in.is_file():
-        logger.error(f"The given input file {args.file_in} was not found!")
-        sys.exit(2)
-    args.file_out.parent.mkdir(parents=True, exist_ok=True)
-    check_samplesheet(args.file_in, args.file_out)
 
 
 if __name__ == "__main__":

conf/modules.config

@@ -12,12 +12,6 @@
 
 process {
 
-    publishDir = [
-        path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
-        mode: params.publish_dir_mode,
-        saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-    ]
-
     withName: SAMPLESHEET_CHECK {
         publishDir = [
             path: { "${params.outdir}/pipeline_info" },
@@ -26,8 +20,321 @@ process {
         ]
     }
 
+    withName: DATABASE_CHECK {
+        publishDir = [
+            path: { "${params.outdir}/pipeline_info" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: FASTQC {
         ext.args = '--quiet'
+        ext.prefix = { "${meta.id}_${meta.run_accession}_raw" }
+        publishDir = [
+            path: { "${params.outdir}/fastqc/raw" },
+            mode: params.publish_dir_mode,
+            pattern: '*.html'
+        ]
+    }
+
+    withName: FASTQC_PROCESSED {
+        ext.args = '--quiet'
+        ext.prefix = { "${meta.id}_${meta.run_accession}_processed" }
+        publishDir = [
+            path: { "${params.outdir}/fastqc/processed" },
+            mode: params.publish_dir_mode,
+            pattern: '*.html'
+        ]
+    }
+
+    withName: FASTP_SINGLE {
+        ext.args   = [
+            // trimming options
+            params.shortread_clipmerge_skipadaptertrim ? "--disable_adapter_trimming" : "",
+            params.shortread_clipmerge_adapter1 ? "--adapter_sequence ${params.shortread_clipmerge_adapter1}" : "",
+            // filtering options
+            "--length_required ${params.shortread_clipmerge_minlength}",
+            (params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp') ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : ''
+        ].join(' ').trim()
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/fastp" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_preprocessed_reads
+        ]
+    }
+
+    withName: FASTP_PAIRED {
+        ext.args   = [
+            // collapsing options - option to retain singletons
+            params.shortread_clipmerge_excludeunmerged ? '' : "--include_unmerged",
+            // trimming options
+            params.shortread_clipmerge_skipadaptertrim ? "--disable_adapter_trimming" : "",
+            params.shortread_clipmerge_adapter1 ? "--adapter_sequence ${params.shortread_clipmerge_adapter1}" : "",
+            params.shortread_clipmerge_adapter2 ? "--adapter_sequence_r2 ${params.shortread_clipmerge_adapter2}" : "--detect_adapter_for_pe",
+            // filtering options
+            "--length_required ${params.shortread_clipmerge_minlength}",
+            params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == 'fastp' ? "--low_complexity_filter --complexity_threshold ${params.shortread_complexityfilter_fastp_threshold}" : ''
+        ].join(' ').trim()
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/fastp" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_preprocessed_reads
+        ]
+    }
+
+    withName: ADAPTERREMOVAL_SINGLE {
+        ext.args   = [
+            // trimming options
+            params.shortread_clipmerge_skipadaptertrim ? "--adapter1 '' --adapter2 ''" : "",
+            params.shortread_clipmerge_adapter1 ? "--adapter1 ${params.shortread_clipmerge_adapter1}" : "",
+            // filtering options
+            "--minlength ${params.shortread_clipmerge_minlength}"
+        ].join(' ').trim()
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/adapterremoval" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_preprocessed_reads
+        ]
+    }
+
+    withName: ADAPTERREMOVAL_PAIRED {
+        ext.args   = [
+            // collapsing options
+            params.shortread_clipmerge_mergepairs ? "--collapse" : "",
+            // trimming options
+            params.shortread_clipmerge_skipadaptertrim ? "--adapter1 '' --adapter2 ''" : "",
+            params.shortread_clipmerge_adapter1 ? "--adapter1 ${params.shortread_clipmerge_adapter1}" : "",
+            params.shortread_clipmerge_adapter2 ? "--adapter2 ${params.shortread_clipmerge_adapter2}" : "",
+            // filtering options
+            "--minlength ${params.shortread_clipmerge_minlength}"
+        ].join(' ').trim()
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/adapterremoval" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_preprocessed_reads
+        ]
+    }
+
+    withName: PORECHOP {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/porechop" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_preprocessed_reads
+        ]
+    }
+
+    withName: BOWTIE2_BUILD {
+        publishDir = [
+            path: { "${params.outdir}/bowtie2/build" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_index,
+            pattern: 'bowtie2'
+        ]
+    }
+
+    withName: BOWTIE2_ALIGN {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            [
+            path: { "${params.outdir}/bowtie2/align" },
+            mode: params.publish_dir_mode,
+            pattern: '*.log'
+            ],
+            [
+            path: { "${params.outdir}/bowtie2/align" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_mapped,
+            pattern: '*.bam'
+            ],
+            [
+            path: { "${params.outdir}/bowtie2/align" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*.fastq.gz'
+            ]
+        ]
+    }
+
+    withName: MINIMAP2_INDEX {
+        ext.args = '-x map-ont'
+        publishDir = [
+            path: { "${params.outdir}/minimap2/index" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_index,
+            pattern: 'minimap2'
+        ]
+    }
+
+    withName: MINIMAP2_ALIGN {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/minimap2/align" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_mapped,
+            pattern: '*.bam'
+        ]
+    }
+
+    withName: SAMTOOLS_VIEW {
+        ext.args = '-f 4'
+        ext.prefix = { "${meta.id}.mapped.sorted" }
+        publishDir = [
+            path: { "${params.outdir}/samtools/view" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*.bam'
+        ]
+    }
+
+    withName: SAMTOOLS_BAM2FQ {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/samtools/bam2fq" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*.fq.gz'
+        ]
+    }
+
+    withName: BBMAP_BBDUK {
+        ext.args =  [
+                "entropy=${params.shortread_complexityfilter_entropy}",
+                "entropywindow=${params.shortread_complexityfilter_bbduk_windowsize}",
+                params.shortread_complexityfilter_bbduk_mask ?  "entropymask=t" : "entropymask=f"
+            ].join(' ').trim()
+        ext.prefix = { "${meta.id}-${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/bbduk/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{fastq.gz,log}',
+            enabled: params.save_complexityfiltered_reads
+        ]
+    }
+
+    withName: PRINSEQPLUSPLUS {
+        ext.args =  [
+                params.shortread_complexityfilter_prinseqplusplus_mode == 'dust' ? "-lc_dust=${params.shortread_complexityfilter_prinseqplusplus_dustscore}" : "-lc_entropy=${params.shortread_complexityfilter_entropy}",
+                "-trim_qual_left=0 -trim_qual_left=0 -trim_qual_window=0 -trim_qual_step=0"
+            ].join(' ').trim()
+        ext.prefix = { "${meta.id}-${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/prinseqplusplus/" },
+            mode: params.publish_dir_mode,
+            pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz,log}',
+            enabled: params.save_complexityfiltered_reads
+        ]
+    }
+
+    withName: CAT_FASTQ {
+        ext.prefix = { "${meta.id}" }
+        publishDir = [
+            path: { "${params.outdir}/run_merging/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.fastq.gz',
+            enabled: params.save_runmerged_reads
+        ]
+    }
+
+    withName: MALT_RUN {
+        ext.args = { "${meta.db_params}" }
+        // one run with multiple samples, so fix ID to just db name to ensure clean log name
+        ext.prefix = { "${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/malt/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{rma6,log,sam}'
+        ]
+    }
+
+    withName: MEGAN_RMA2INFO {
+        ext.args = "-c2c Taxonomy"
+        ext.prefix = { "${meta.id}" }
+        publishDir = [
+            path: { "${params.outdir}/malt/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt.gz,megan}'
+        ]
+    }
+
+    withName: KRAKEN2_KRAKEN2 {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/kraken2/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt}'
+        ]
+    }
+
+    withName: METAPHLAN3 {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{biom,txt}'
+        ]
+    }
+
+    withName: CENTRIFUGE_CENTRIFUGE {
+        publishDir = [
+            path: { "${params.outdir}/centrifuge/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.txt'
+        ]
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+    }
+
+    withName: CENTRIFUGE_KREPORT {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/centrifuge/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt}'
+        ]
+    }
+
+    withName: KAIJU_KAIJU {
+        publishDir = [
+            path: { "${params.outdir}/kaiju/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.tsv'
+        ]
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+    }
+
+    withName: KAIJU_KAIJU2TABLE {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/kaiju/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{txt}'
+        ]
+    }
+
+    withName: DIAMOND_BLASTX {
+        ext.args = { "${meta.db_params}" }
+        ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
+        publishDir = [
+            path: { "${params.outdir}/diamond/${meta.db_name}" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{blast,xml,txt,daa,sam,tsv,paf}'
+        ]
     }
 
     withName: CUSTOM_DUMPSOFTWAREVERSIONS {
@@ -38,4 +345,11 @@ process {
         ]
     }
 
+    withName: MULTIQC {
+        publishDir = [
+            path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
 }

conf/test.config

@@ -22,8 +22,25 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+    input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
-
+    databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
-    // Genome references
+    perform_shortread_clipmerge           = true
-    genome = 'R64-1-1'
+    perform_longread_clip                 = false
+    perform_shortread_complexityfilter    = true
+    perform_shortread_hostremoval         = true
+    perform_longread_hostremoval          = true
+    perform_runmerging                    = true
+    hostremoval_reference                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                             = true
+    run_kraken2                           = true
+    run_malt                              = true
+    run_metaphlan3                        = true
+    run_centrifuge                        = true
+    run_diamond                           = true
+}
+
+process {
+    withName: MALT_RUN {
+        maxForks = 1
+    }
 }

conf/test_nopreprocessing.config

@@ -0,0 +1,46 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/taxprofiler -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset skipping all preprocessing to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
+    // TODO nf-core: Give any required params for the test so that command line flags are not needed
+    input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
+    databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
+    perform_shortread_clipmerge           = false
+    perform_longread_clip                 = false
+    perform_shortread_complexityfilter    = false
+    perform_shortread_hostremoval         = false
+    perform_longread_hostremoval          = false
+    perform_runmerging                    = false
+    hostremoval_reference                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                             = true
+    run_kraken2                           = true
+    run_malt                              = true
+    run_metaphlan3                        = true
+    run_centrifuge                        = true
+    run_diamond                           = true
+}
+
+process {
+    withName: MALT_RUN {
+        maxForks = 1
+    }
+}

conf/test_noprofiling.config

@@ -0,0 +1,46 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/taxprofiler -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset without performing any profiling to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
+    // TODO nf-core: Give any required params for the test so that command line flags are not needed
+    input                                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
+    databases                             = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
+    perform_shortread_clipmerge           = true
+    perform_longread_clip                 = true
+    perform_shortread_complexityfilter    = true
+    perform_shortread_hostremoval         = true
+    perform_longread_hostremoval          = true
+    perform_runmerging                    = true
+    hostremoval_reference                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    run_kaiju                             = false
+    run_kraken2                           = false
+    run_malt                              = false
+    run_metaphlan3                        = false
+    run_centrifuge                        = false
+    run_diamond                           = false
+}
+
+process {
+    withName: MALT_RUN {
+        maxForks = 1
+    }
+}

docs/usage.md

@@ -8,56 +8,136 @@
 
 <!-- TODO nf-core: Add documentation about anything specific to running your pipeline. For general topics, please point to (and add to) the main nf-core website. -->
 
-## Samplesheet input
+## Samplesheet inputs
 
-You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below.
+nf-core/taxprofiler can accept as input raw or preprocessed single- or paired-end short-read (e.g. Illumina) FASTQ files, long-read FASTQ files (e.g. Oxford Nanopore), or FASTA sequences (available for a subset of profilers).
+
+You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 6 columns, and a header row as shown in the examples below. Furthermother, nf-core/taxprofiler also requires a second comma-separated file of 3 columns with a header row as in the examples below.
+
+This samplesheet is then specified on the command line as follows:
 
 ```console
---input '[path to samplesheet file]'
+--input '[path to samplesheet file]' --databases '[path to database sheet file]'
 ```
 
 ### Multiple runs of the same sample
 
-The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes:
+The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate different runs FASTQ files of the same sample before performing profiling, when `--perform_runmerging` is supplied. Below is an example for the same sample sequenced across 3 lanes:
 
 ```console
-sample,fastq_1,fastq_2
+sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+2612,run1,ILLUMINA,2612_run1_R1.fq.gz,,
-CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz
+2612,run2,ILLUMINA,2612_run2_R1.fq.gz,,
-CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz
+2612,run3,ILLUMINA,2612_run3_R1.fq.gz,2612_run3_R2.fq.gz,
+
 ```
 
+> ⚠️ Runs of the same sample sequenced on Illumina platforms with a combination of single and paired-end data will **not** be run-wise concatenated, unless pair-merging is specified. In the example above, `run3` will be profiled independently of `run1` and `run2` if pairs are not merged.
+
 ### Full samplesheet
 
-The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below.
+The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 6 columns to match those defined in the table below.
 
-A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice.
+A final samplesheet file consisting of both single- and paired-end data, as well as long-read FASTA files may look something like the one below. This is for 6 samples, where `2612` has been sequenced twice.
 
 ```console
-sample,fastq_1,fastq_2
+2611,ERR5766174,ILLUMINA,,,/<path>/<to>/fasta/ERX5474930_ERR5766174_1.fa.gz
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+2612,ERR5766176,ILLUMINA,/<path>/<to>/fastq/ERX5474932_ERR5766176_1.fastq.gz,/<path>/<to>/fastq/ERX5474932_ERR5766176_2.fastq.gz,
-CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz
+2612,ERR5766180,ILLUMINA,/<path>/<to>/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
-CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz
+2613,ERR5766181,ILLUMINA,/<path>/<to>/fastq/ERX5474937_ERR5766181_1.fastq.gz,/<path>/<to>/fastq/ERX5474937_ERR5766181_2.fastq.gz,
-TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz,
+ERR3201952,ERR3201952,OXFORD_NANOPORE,/<path>/<to>/fastq/ERR3201952.fastq.gz,,
-TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz,
-TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz,
-TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz,
 ```
 
-| Column    | Description                                                                                                                                                                            |
+| Column                | Description                                                                                                                                                                                              |
-| --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
+| `sample`              | Unique sample name [required].                                                                                                                                                                           |
-| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+| `run_accession`       | Run ID or name unique for each (pairs of) file(s) .Can also supply sample name again here, if only a single run was generated [required].                                                                |
-| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
+| `instrument_platform` | Sequencing platform reads generated on, selected from the EBI ENA [controlled vocabulary](https://www.ebi.ac.uk/ena/portal/api/controlledVocab?field=instrument_platform) [required].                    |
+| `fastq_1`             | Path or URL to sequencing reads or for Illumina R1 sequencing reads in FASTQ format. GZipped compressed files accepted. Can be left empty if data in FASTA is specifed. Cannot be combined with `fasta`. |
+| `fastq_2`             | Path or URL to Illumina R2 sequencing reads in FASTQ format. GZipped compressed files accepted. Can be left empty if single end data. Cannot be combined with `fasta`.                                   |
+| `fasta`               | Path or URL to long-reads or contigs in FASTA format. GZipped compressed files accepted. Can be left empty if data in FASTA is specifed. Cannot be combined with `fastq_1` or `fastq_2`.                 |
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 
+### Full database sheet
+
+nf-core/taxprofiler supports multiple databases being profiled in parallel for each tool.
+Databases can be supplied either in the form of a compressed `.tar.gz` archive of a directory containing all relevant database files or the path to a directory on the filesystem.
+The pipeline takes the locations and specific parameters of these databases as input via a four column comma-separated sheet.
+
+> ⚠️ nf-core/taxprofiler does not provide any databases by default, nor does it currently generate them for you. This must be performed manually by the user. See below for more information of the expected database files.
+
+An example database sheet can look as follows, where 4 tools are being used, and `malt` and `kraken2` will be used against two databases each.
+
+```console
+tool,db_name,db_params,db_path
+malt,malt85,-id 85,/<path>/<to>/malt/testdb-malt/
+malt,malt95,-id 90,/<path>/<to>/malt/testdb-malt.tar.gz
+kraken2,db1,,/<path>/<to>/kraken2/testdb-kraken2.tar.gz
+kraken2,db2,--quick,/<path>/<to>/kraken2/testdb-kraken2.tar.gz
+centrifuge,db1,,/<path>/<to>/centrifuge/minigut_cf.tar.gz
+metaphlan3,db1,,/<path>/<to>/metaphlan3/metaphlan_database/
+```
+
+Column specifications are as follows:
+
+| Column      | Description                                                                                                                                                                                                                                             |
+| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `tool`      | Taxonomic profiling tool (supported by nf-core/taxprofiler) that the database has been indexed for [required].                                                                                                                                          |
+| `db_name`   | A unique name of the particular database [required].                                                                                                                                                                                                    |
+| `db_params` | Any parameters of the given taxonomic profiler that you wish to specify that the taxonomic profiling tool should use when profiling against this specific. Can be empty to use taxonomic profiler defaults Must not be surrounded by quotes [required]. |
+| `db_path`   | Path to the database. Can either be a path to a directory containing the database index files or a `.tar.gz` file which contains the compressed database directory with the same name as the tar archive, minus `.tar.gz` [required].                   |
+
+> 💡 You can also specify the same database directory/file twice (ensuring unique `db_name`s) and specify different parameters for each database to compare the effect of different parameters during profiling.
+
+nf-core/taxprofiler will automatically decompress and extract any compressed archives for you.
+
+Expected (uncompressed) database files for each tool are as follows:
+
+- **MALT** output of `malt-build`. A directory containing:
+  - `ref.idx`
+  - `taxonomy.idx`
+  - `taxonomy.map`
+  - `index0.idx`
+  - `table0.idx`
+  - `table0.db`
+  - `ref.inf`
+  - `ref.db`
+  - `taxonomy.tre`
+- **Kraken2** output of `kraken2-build` command(s) A directory containing:
+  - `opts.k2d`
+  - `hash.k2d`
+  - `taxo.k2d`
+- **Centrifuge** output of `centrifuge-build`. A directory containing:
+  - `<database_name>.<number>.cf`
+  - `<database_name>.<number>.cf`
+  - `<database_name>.<number>.cf`
+  - `<database_name>.<number>.cf`
+- **MetaPhlAn3** generated with `metaphlan --install` or downloaded from links on the [MetaPhlAn3 wiki](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-3.0#customizing-the-database). A directory containing:
+  - `mpa_v30_CHOCOPhlAn_201901.pkl`
+  - `mpa_v30_CHOCOPhlAn_201901.pkl`
+  - `mpa_v30_CHOCOPhlAn_201901.fasta`
+  - `mpa_v30_CHOCOPhlAn_201901.3.bt2`
+  - `mpa_v30_CHOCOPhlAn_201901.4.bt2`
+  - `mpa_v30_CHOCOPhlAn_201901.1.bt2`
+  - `mpa_v30_CHOCOPhlAn_201901.2.bt2`
+  - `mpa_v30_CHOCOPhlAn_201901.rev.1.bt2`
+  - `mpa_v30_CHOCOPhlAn_201901.rev.2.bt2`
+  - `mpa_latest`
+- **Kaiju** output of `kaiju-makedb`. A directory containing:
+  - `kaiju_db_*.fmi`
+  - `nodes.dmp`
+  - `names.dmp`
+- **DIAMOND** output of `diamond makedb`. Note: requires building with taxonomy files
+  to generate taxonomic profile. See [DIAMOND documentation](https://github.com/bbuchfink/diamond/wiki/3.-Command-line-options#makedb-options). A file named:
+  - `<database_name>.dmnd`
+
 ## Running the pipeline
 
 The typical command for running the pipeline is as follows:
 
 ```console
-nextflow run nf-core/taxprofiler --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile docker
+nextflow run nf-core/taxprofiler --input samplesheet.csv --databases databases.csv --outdir <OUTDIR> -profile docker --run_<TOOL1> --run_<TOOL2>
 ```
 
 This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles.
@@ -66,11 +146,71 @@ Note that the pipeline will create the following files in your working directory
 
 ```console
 work                # Directory containing the nextflow working files
-<OUTIDR>            # Finished results in specified location (defined with --outdir)
+<OUTDIR>            # Finished results in specified location (defined with --outdir)
 .nextflow_log       # Log file from Nextflow
 # Other nextflow hidden files, eg. history of pipeline runs and old logs.
 ```
 
+### Preprocessing Steps
+
+nf-core/taxprofiler offers four main preprocessing steps
+
+- Read processing: adapter clipping and pair-merging.
+- Complexity filtering: removal of low-sequence complexity reads.
+- Host read-removal: removal of reads aligning to reference genome(s) of a host.
+- Run merging: concatenation of multiple FASTQ chunks/sequencing runs/libraries of a sample.
+
+#### Read Processing
+
+Raw sequencing read processing in the form of adapter clipping and paired-end read merging can be activated via the `--perform_shortread_clipmerge` or `--perform_longread_clip` flags.
+
+It is highly recommended to run this on raw reads to remove artefacts from sequencing that can cause false positive identification of taxa (e.g. contaminated reference genomes) and/or skews in taxonomic abundance profiles.
+
+There are currently two options for short-read preprocessing: `fastp` or `adapterremoval`.
+
+For adapter clipping, you can either rely on tool default adapter sequences, or supply your own adapters (`--shortread_clipmerge_adapter1` and `--shortread_clipmerge_adapter2`)
+By default, paired-end merging is not activated and paired-end profiling is performed where supported otherwise pairs will be independently profiled. If paired-end merging is activated you can also specify whether to exclude unmerged reads in the reads sent for profiling (`--shortread_clipmerge_mergepairs` and `--shortread_clipmerge_excludeunmerged`).
+You can also turn off clipping and only perform paired-end merging, if requested. This can be useful when processing data downloaded from the ENA, SRA, or DDBJ (`--shortread_clipmerge_skipadaptertrim`).
+Both tools support length filtering of reads and can be tuned with `--shortread_clipmerge_minlength`. Performing length filtering can be useful to remove short (often low sequencing complexity) sequences that result in unspecific classification and therefore slow down runtime during profiling, with minimal gain.
+
+There is currently one option for long-read Oxford Nanopore processing: `porechop`.
+
+For both short-read and long-read preprocessing, you can optionally save the resulting processed reads with `--save_preprocessed_reads`.
+
+#### Complexity Filtering
+
+Complexity filtering can be activated via the `--perform_shortread_complexityfilter` flag.
+
+Complexity filtering is primarily a run-time optimisation step. It is not necessary for accurate taxonomic profiling, however it can speed up run-time of each tool by removing reads with low-diversity of nucleotides (e.g. with mono-nucleotide - `AAAAAAAA`, or di-nucleotide repeats `GAGAGAGAGAGAGAG`) that have a low-chance of giving an informative taxonomic ID as they can be associated with many different taxa. Removing these reads therefore saves computational time and resources.
+
+There are currently three options for short-read complexity filtering: [`bbduk`](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/bbduk-guide/), [`prinseq++`](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus), and [`fastp`](https://github.com/OpenGene/fastp#low-complexity-filter).
+
+The tools offer different algorithms and parameters for removing low complexity reads. We therefore recommend reviewing the pipeline's [parameter documentation](https://nf-co.re/taxprofiler/parameters) and the documentation of the tools (see links above) to decide on optimal methods and parameters for your dataset.
+
+You can optionally save the FASTQ output of the run merging with the `--save_complexityfiltered_reads`. If running with `fastp`, complexity filtering happens inclusively within the earlier shortread preprocessing step. Therefore there will not be an independent pipeline step for complexity filtering, and no independent FASTQ file (i.e. `--save_complexityfiltered_reads` will be ignored) - your complexity filtered reads will also be in the `fastp/` folder in the same file(s) as the preprocessed read.
+
+#### Host Removal
+
+Removal of possible-host reads from FASTQ files prior profiling can be activated with `--perform_shortread_hostremoval` or `--perform_longread_hostremoval`.
+
+Similarly to complexity filtering, host-removal can be useful for runtime optimisation and reduction in misclassified reads. It is not always necessary to report classification of reads from a host when you already know the host of the sample, therefore you can gain a run-time and computational advantage by removing these prior typically resource-heavy profiling with more efficient methods. Furthermore, particularly with human samples, you can reduce the number of false positives during profiling that occur due to host-sequence contamination in reference genomes on public databases.
+
+nf-core/taxprofiler currently offers host-removal via alignment against a reference genome with Bowtie2, and the use of the unaligned reads for downstream profiling.
+
+You can supply your reference genome in FASTA format with `--hostremoval_reference`. You can also optionally supply a directory containing pre-indexed Bowtie2 index files with `--shortread_hostremoval_index` or `--longread_hostremoval_index`, however nf-core/taxprofiler will generate this for you if necessary. Pre-supplying the directory of index files can greatly speed up the process, and these can be re-used.
+
+> 💡 If you have multiple taxa or sequences you wish to remove (e.g., the host genome and then also PhiX - common quality-control reagent during sequencing) you can simply concatenate the FASTAs of each taxa or sequences into a single reference file.
+
+#### Run Merging
+
+For samples that may have been sequenced over multiple runs, or for FASTQ files split into multiple chunks, you can activate the ability to merge across all runs or chunks with `--perform_runmerging`.
+
+For more information how to set up your input samplesheet, see [Multiple runs of the same sample](#multiple-runs-of-the-same-sample).
+
+Activating this functionality will concatenate the FASTQ files with the same sample name _after_ the optional preprocessing steps and _before_ profiling. Note that libraries with runs of different pairing types will **not** be merged and this will be indicated on output files with a `_se` or `_pe` suffix to the sample name accordingly.
+
+You can optionally save the FASTQ output of the run merging with the `--save_runmerged_reads`.
+
 ### Updating the pipeline
 
 When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:

lib/WorkflowTaxprofiler.groovy

@@ -10,10 +10,11 @@ class WorkflowTaxprofiler {
     public static void initialise(params, log) {
         genomeExistsError(params, log)
 
-        if (!params.fasta) {
+        // TODO update as necessary
-            log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
+        //if (!params.fasta) {
-            System.exit(1)
+        //    log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
-        }
+        //    System.exit(1)
+        //}
     }
 
     //

modules.json

@@ -3,14 +3,80 @@
     "homePage": "https://github.com/nf-core/taxprofiler",
     "repos": {
         "nf-core/modules": {
+            "adapterremoval": {
+                "git_sha": "879d42c5e28661fe0a5e744c9e2c515868f9e08a"
+            },
+            "bbmap/bbduk": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "bowtie2/align": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "bowtie2/build": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "cat/fastq": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "centrifuge/centrifuge": {
+                "git_sha": "d2726fcf75063960f06b36d2229a4c0966614108"
+            },
+            "centrifuge/kreport": {
+                "git_sha": "be4ae28c3c95b3c4047a7d9fb4cb0ed749631cea"
+            },
             "custom/dumpsoftwareversions": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
+            "diamond/blastx": {
+                "git_sha": "42564565b934eeb2449e35ec97ed13ff2a67f1de"
+            },
+            "fastp": {
+                "git_sha": "d0a1cbb703a130c19f6796c3fce24fbe7dfce789"
+            },
             "fastqc": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
+            "kaiju/kaiju": {
+                "git_sha": "8856f127c58f6af479128be8b8df4d42e442ddbe"
+            },
+            "kaiju/kaiju2table": {
+                "git_sha": "538dbac98ba9c8f799536cd5a617195501439457"
+            },
+            "kraken2/kraken2": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "malt/run": {
+                "git_sha": "72b96f4e504eef673f2b5c13560a9d90b669129b"
+            },
+            "megan/rma2info": {
+                "git_sha": "2d38566eca4cc15142b2ffa7c11837569b39aece"
+            },
+            "metaphlan3": {
+                "git_sha": "ed4dd1a928ebf4308efb720de878045f7773f8e2"
+            },
+            "minimap2/align": {
+                "git_sha": "1a5a9e7b4009dcf34e6867dd1a5a1d9a718b027b"
+            },
+            "minimap2/index": {
+                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
             "multiqc": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+            },
+            "porechop": {
+                "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
+            },
+            "prinseqplusplus": {
+                "git_sha": "f1c5384c31e985591716afdd732cf8c2ae29d05b"
+            },
+            "samtools/bam2fq": {
+                "git_sha": "5510ea39fe638594bc26ac34cadf4a84bf27d159"
+            },
+            "samtools/view": {
+                "git_sha": "6b64f9cb6c3dd3577931cc3cd032d6fb730000ce"
+            },
+            "untar": {
+                "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918"
             }
         }
     }

modules/local/database_check.nf

@@ -0,0 +1,25 @@
+process DATABASE_CHECK {
+    tag "$databasesheet"
+
+    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/python:3.8.3' :
+        'quay.io/biocontainers/python:3.8.3' }"
+
+    input:
+    path databasesheet
+
+    output:
+    path '*.csv'       , emit: csv
+    path "versions.yml", emit: versions
+
+    script: // This script is bundled with the pipeline, in nf-core/taxprofiler/bin/
+    """
+    cat $databasesheet >> database_sheet.valid.csv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python --version | sed 's/Python //g')
+    END_VERSIONS
+    """
+}

modules/local/ensure_fastq_extension.nf

@@ -0,0 +1,31 @@
+process ENSURE_FASTQ_EXTENSION {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::bash=5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv2/biocontainers_v1.2.0_cv2.img' :
+        'biocontainers/biocontainers:v1.2.0_cv2' }"
+
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path('*.fastq.gz'), emit: reads
+
+    script:
+    if (meta.single_end) {
+        fastq = "${reads.baseName}.fastq.gz"
+        """
+        ln -s '${reads}' '${fastq}'
+        """
+    } else {
+        first = "${reads[0].baseName}.fastq.gz"
+        second = "${reads[1].baseName}.fastq.gz"
+        """
+        ln -s '${reads[0]}' '${first}'
+        ln -s '${reads[1]}' '${second}'
+        """
+    }
+}

modules/nf-core/modules/adapterremoval/main.nf

@@ -0,0 +1,92 @@
+process ADAPTERREMOVAL {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::adapterremoval=2.3.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/adapterremoval:2.3.2--hb7ba0dd_0' :
+        'quay.io/biocontainers/adapterremoval:2.3.2--hb7ba0dd_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path(adapterlist)
+
+    output:
+    tuple val(meta), path("${prefix}.truncated.fastq.gz")            , optional: true, emit: singles_truncated
+    tuple val(meta), path("${prefix}.discarded.fastq.gz")            , optional: true, emit: discarded
+    tuple val(meta), path("${prefix}.pair{1,2}.truncated.fastq.gz")  , optional: true, emit: paired_truncated
+    tuple val(meta), path("${prefix}.collapsed.fastq.gz")            , optional: true, emit: collapsed
+    tuple val(meta), path("${prefix}.collapsed.truncated.fastq.gz")  , optional: true, emit: collapsed_truncated
+    tuple val(meta), path("${prefix}.paired.fastq.gz")               , optional: true, emit: paired_interleaved
+    tuple val(meta), path('*.settings')                              , emit: settings
+    path "versions.yml"                                              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def list = adapterlist ? "--adapter-list ${adapterlist}" : ""
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    if (meta.single_end) {
+        """
+        AdapterRemoval  \\
+            --file1 $reads \\
+            $args \\
+            $adapterlist \\
+            --basename ${prefix} \\
+            --threads ${task.cpus} \\
+            --seed 42 \\
+            --gzip
+
+        ensure_fastq() {
+            if [ -f "\${1}" ]; then
+                mv "\${1}" "\${1::-3}.fastq.gz"
+            fi
+
+        }
+
+        ensure_fastq '${prefix}.truncated.gz'
+        ensure_fastq '${prefix}.discarded.gz'
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            adapterremoval: \$(AdapterRemoval --version 2>&1 | sed -e "s/AdapterRemoval ver. //g")
+        END_VERSIONS
+        """
+    } else {
+        """
+        AdapterRemoval  \\
+            --file1 ${reads[0]} \\
+            --file2 ${reads[1]} \\
+            $args \\
+            $adapterlist \\
+            --basename ${prefix} \\
+            --threads $task.cpus \\
+            --seed 42 \\
+            --gzip
+
+        ensure_fastq() {
+            if [ -f "\${1}" ]; then
+                mv "\${1}" "\${1::-3}.fastq.gz"
+            fi
+
+        }
+
+        ensure_fastq '${prefix}.truncated.gz'
+        ensure_fastq '${prefix}.discarded.gz'
+        ensure_fastq '${prefix}.pair1.truncated.gz'
+        ensure_fastq '${prefix}.pair2.truncated.gz'
+        ensure_fastq '${prefix}.collapsed.gz'
+        ensure_fastq '${prefix}.collapsed.truncated.gz'
+        ensure_fastq '${prefix}.paired.gz'
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            adapterremoval: \$(AdapterRemoval --version 2>&1 | sed -e "s/AdapterRemoval ver. //g")
+        END_VERSIONS
+        """
+    }
+
+}

modules/nf-core/modules/adapterremoval/meta.yml

@@ -0,0 +1,90 @@
+name: adapterremoval
+description: Trim sequencing adapters and collapse overlapping reads
+keywords:
+  - trimming
+  - adapters
+  - merging
+  - fastq
+tools:
+  - adapterremoval:
+      description: The AdapterRemoval v2 tool for merging and clipping reads.
+      homepage: https://github.com/MikkelSchubert/adapterremoval
+      documentation: https://adapterremoval.readthedocs.io
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+      pattern: "*.{fq,fastq,fq.gz,fastq.gz}"
+  - adapterlist:
+      type: file
+      description: Optional text file containing list of adapters to look for for removal
+        with one adapter per line. Otherwise will look for default adapters (see
+        AdapterRemoval man page), or can be modified to remove user-specified
+        adapters via ext.args.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - singles_truncated:
+      type: file
+      description: |
+        Adapter trimmed FastQ files of either single-end reads, or singleton
+        'orphaned' reads from merging of paired-end data (i.e., one of the pair
+        was lost due to filtering thresholds).
+      pattern: "*.truncated.fastq.gz"
+  - discarded:
+      type: file
+      description: |
+        Adapter trimmed FastQ files of reads that did not pass filtering
+        thresholds.
+      pattern: "*.discarded.fastq.gz"
+  - pair1_truncated:
+      type: file
+      description: |
+        Adapter trimmed R1 FastQ files of paired-end reads that did not merge
+        with their respective R2 pair due to long templates. The respective pair
+        is stored in 'pair2_truncated'.
+      pattern: "*.pair1.truncated.fastq.gz"
+  - pair2_truncated:
+      type: file
+      description: |
+        Adapter trimmed R2 FastQ files of paired-end reads that did not merge
+        with their respective R1 pair due to long templates. The respective pair
+        is stored in 'pair1_truncated'.
+      pattern: "*.pair2.truncated.fastq.gz"
+  - collapsed:
+      type: file
+      description: |
+        Collapsed FastQ of paired-end reads that successfully merged with their
+        respective R1 pair but were not trimmed.
+      pattern: "*.collapsed.fastq.gz"
+  - collapsed_truncated:
+      type: file
+      description: |
+        Collapsed FastQ of paired-end reads that successfully merged with their
+        respective R1 pair and were trimmed of adapter due to sufficient overlap.
+      pattern: "*.collapsed.truncated.fastq.gz"
+  - log:
+      type: file
+      description: AdapterRemoval log file
+      pattern: "*.settings"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@maxibor"
+  - "@jfy133"

modules/nf-core/modules/bbmap/bbduk/main.nf

@@ -0,0 +1,43 @@
+process BBMAP_BBDUK {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::bbmap=38.90" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bbmap:38.90--he522d1c_1' :
+        'quay.io/biocontainers/bbmap:38.90--he522d1c_1' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path contaminants
+
+    output:
+    tuple val(meta), path('*.fastq.gz'), emit: reads
+    tuple val(meta), path('*.log')     , emit: log
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def raw      = meta.single_end ? "in=${reads[0]}" : "in1=${reads[0]} in2=${reads[1]}"
+    def trimmed  = meta.single_end ? "out=${prefix}.fastq.gz" : "out1=${prefix}_1.fastq.gz out2=${prefix}_2.fastq.gz"
+    def contaminants_fa = contaminants ? "ref=$contaminants" : ''
+    """
+    maxmem=\$(echo \"$task.memory\"| sed 's/ GB/g/g')
+    bbduk.sh \\
+        -Xmx\$maxmem \\
+        $raw \\
+        $trimmed \\
+        threads=$task.cpus \\
+        $args \\
+        $contaminants_fa \\
+        &> ${prefix}.bbduk.log
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bbmap: \$(bbversion.sh)
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/bbmap/bbduk/meta.yml

@@ -0,0 +1,52 @@
+name: bbmap_bbduk
+description: Adapter and quality trimming of sequencing reads
+keywords:
+  - trimming
+  - adapter trimming
+  - quality trimming
+tools:
+  - bbmap:
+      description: BBMap is a short read aligner, as well as various other bioinformatic tools.
+      homepage: https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/
+      documentation: https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/
+      tool_dev_url: None
+      doi: ""
+      licence: ["UC-LBL license (see package)"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - contaminants:
+      type: file
+      description: |
+        Reference files containing adapter and/or contaminant sequences for sequence kmer matching
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: The trimmed/modified fastq reads
+      pattern: "*fastq.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - log:
+      type: file
+      description: Bbduk log file
+      pattern: "*bbduk.log"
+
+authors:
+  - "@MGordon09"

modules/nf-core/modules/bowtie2/align/main.nf

@@ -0,0 +1,77 @@
+process BOWTIE2_ALIGN {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4 bioconda::samtools=1.14 conda-forge::pigz=2.6' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:4d235f41348a00533f18e47c9669f1ecb327f629-0' :
+        'quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:4d235f41348a00533f18e47c9669f1ecb327f629-0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path  index
+    val   save_unaligned
+
+    output:
+    tuple val(meta), path('*.bam')    , emit: bam
+    tuple val(meta), path('*.log')    , emit: log
+    tuple val(meta), path('*fastq.gz'), emit: fastq, optional:true
+    path  "versions.yml"              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (meta.single_end) {
+        def unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
+        """
+        INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
+        bowtie2 \\
+            -x \$INDEX \\
+            -U $reads \\
+            --threads $task.cpus \\
+            $unaligned \\
+            $args \\
+            2> ${prefix}.bowtie2.log \\
+            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+        END_VERSIONS
+        """
+    } else {
+        def unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
+        """
+        INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
+        bowtie2 \\
+            -x \$INDEX \\
+            -1 ${reads[0]} \\
+            -2 ${reads[1]} \\
+            --threads $task.cpus \\
+            $unaligned \\
+            $args \\
+            2> ${prefix}.bowtie2.log \\
+            | samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
+
+        if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
+            mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
+        fi
+        if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
+            mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
+        fi
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+        END_VERSIONS
+        """
+    }
+}

modules/nf-core/modules/bowtie2/align/meta.yml

@@ -0,0 +1,51 @@
+name: bowtie2_align
+description: Align reads to a reference genome using bowtie2
+keywords:
+  - align
+  - fasta
+  - genome
+  - reference
+tools:
+  - bowtie2:
+      description: |
+        Bowtie 2 is an ultrafast and memory-efficient tool for aligning
+        sequencing reads to long reference sequences.
+      homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
+      documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
+      doi: 10.1038/nmeth.1923
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - index:
+      type: file
+      description: Bowtie2 genome index files
+      pattern: "*.ebwt"
+output:
+  - bam:
+      type: file
+      description: Output BAM file containing read alignments
+      pattern: "*.{bam}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - fastq:
+      type: file
+      description: Unaligned FastQ files
+      pattern: "*.fastq.gz"
+  - log:
+      type: file
+      description: Aligment log
+      pattern: "*.log"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

modules/nf-core/modules/bowtie2/build/main.nf

@@ -0,0 +1,30 @@
+process BOWTIE2_BUILD {
+    tag "$fasta"
+    label 'process_high'
+
+    conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bowtie2:2.4.4--py39hbb4e92a_0' :
+        'quay.io/biocontainers/bowtie2:2.4.4--py39hbb4e92a_0' }"
+
+    input:
+    path fasta
+
+    output:
+    path 'bowtie2'      , emit: index
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    mkdir bowtie2
+    bowtie2-build $args --threads $task.cpus $fasta bowtie2/${fasta.baseName}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/bowtie2/build/meta.yml

@@ -0,0 +1,33 @@
+name: bowtie2_build
+description: Builds bowtie index for reference genome
+keywords:
+  - build
+  - index
+  - fasta
+  - genome
+  - reference
+tools:
+  - bowtie2:
+      description: |
+        Bowtie 2 is an ultrafast and memory-efficient tool for aligning
+        sequencing reads to long reference sequences.
+      homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
+      documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
+      doi: 10.1038/nmeth.1923
+      licence: ["GPL-3.0-or-later"]
+input:
+  - fasta:
+      type: file
+      description: Input genome fasta file
+output:
+  - index:
+      type: file
+      description: Bowtie2 genome index files
+      pattern: "*.bt2"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

modules/nf-core/modules/cat/fastq/main.nf

@@ -0,0 +1,51 @@
+process CAT_FASTQ {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
+        'biocontainers/biocontainers:v1.2.0_cv1' }"
+
+    input:
+    tuple val(meta), path(reads, stageAs: "input*/*")
+
+    output:
+    tuple val(meta), path("*.merged.fastq.gz"), emit: reads
+    path "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def readList = reads.collect{ it.toString() }
+    if (meta.single_end) {
+        if (readList.size > 1) {
+            """
+            cat ${readList.join(' ')} > ${prefix}.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    } else {
+        if (readList.size > 2) {
+            def read1 = []
+            def read2 = []
+            readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v }
+            """
+            cat ${read1.join(' ')} > ${prefix}_1.merged.fastq.gz
+            cat ${read2.join(' ')} > ${prefix}_2.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    }
+}

modules/nf-core/modules/cat/fastq/meta.yml

@@ -0,0 +1,39 @@
+name: cat_fastq
+description: Concatenates fastq files
+keywords:
+  - fastq
+  - concatenate
+tools:
+  - cat:
+      description: |
+        The cat utility reads files sequentially, writing them to the standard output.
+      documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: list
+      description: |
+        List of input FastQ files to be concatenated.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: Merged fastq file
+      pattern: "*.{merged.fastq.gz}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

modules/nf-core/modules/centrifuge/centrifuge/main.nf

@@ -0,0 +1,61 @@
+process CENTRIFUGE_CENTRIFUGE {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::centrifuge=1.0.4_beta" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/centrifuge:1.0.4_beta--h9a82719_6' :
+        'quay.io/biocontainers/centrifuge:1.0.4_beta--h9a82719_6' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path db
+    val save_unaligned
+    val save_aligned
+    val sam_format
+
+    output:
+    tuple val(meta), path('*report.txt')                 , emit: report
+    tuple val(meta), path('*results.txt')                , emit: results
+    tuple val(meta), path('*.sam')                       , optional: true, emit: sam
+    tuple val(meta), path('*.mapped.fastq{,.1,.2}.gz')   , optional: true, emit: fastq_mapped
+    tuple val(meta), path('*.unmapped.fastq{,.1,.2}.gz') , optional: true, emit: fastq_unmapped
+    path "versions.yml"                                  , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def paired = meta.single_end ? "-U ${reads}" :  "-1 ${reads[0]} -2 ${reads[1]}"
+    def unaligned = ''
+    def aligned = ''
+    if (meta.single_end) {
+        unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
+        aligned = save_aligned ? "--al-gz ${prefix}.mapped.fastq.gz" : ''
+    } else {
+        unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
+        aligned = save_aligned ? "--al-conc-gz ${prefix}.mapped.fastq.gz" : ''
+    }
+    def sam_output = sam_format ? "--out-fmt 'sam'" : ''
+    """
+    ## we add "-no-name ._" to ensure silly Mac OSX metafiles files aren't included
+    db_name=`find -L ${db} -name "*.1.cf" -not -name "._*"  | sed 's/.1.cf//'`
+    centrifuge \\
+        -x \$db_name \\
+        -p $task.cpus \\
+        $paired \\
+        --report-file ${prefix}.report.txt \\
+        -S ${prefix}.results.txt \\
+        $unaligned \\
+        $aligned \\
+        $sam_output \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        centrifuge: \$( centrifuge --version  | sed -n 1p | sed 's/^.*centrifuge-class version //')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/centrifuge/centrifuge/meta.yml

@@ -0,0 +1,66 @@
+name: centrifuge_centrifuge
+description: Classifies metagenomic sequence data
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - db
+tools:
+  - centrifuge:
+      description: Centrifuge is a classifier for metagenomic sequences.
+      homepage: https://ccb.jhu.edu/software/centrifuge/
+      documentation: https://ccb.jhu.edu/software/centrifuge/manual.shtml
+      doi: 10.1101/gr.210641.116
+      licence: ["GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - db:
+      type: directory
+      description: Path to directory containing centrifuge database files
+  - save_unaligned:
+      type: value
+      description: If true unmapped fastq files are saved
+  - save_aligned:
+      type: value
+      description: If true mapped fastq files are saved
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - report:
+      type: file
+      description: |
+        File containing a classification summary
+      pattern: "*.{report.txt}"
+  - results:
+      type: file
+      description: |
+        File containing classification results
+      pattern: "*.{results.txt}"
+  - fastq_unmapped:
+      type: file
+      description: Unmapped fastq files
+      pattern: "*.unmapped.fastq.gz"
+  - fastq_mapped:
+      type: file
+      description: Mapped fastq files
+      pattern: "*.mapped.fastq.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@sofstam"
+  - "@jfy133"
+  - "@sateeshperi"

modules/nf-core/modules/centrifuge/kreport/main.nf

@@ -0,0 +1,33 @@
+process CENTRIFUGE_KREPORT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::centrifuge=1.0.4_beta" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/centrifuge:1.0.4_beta--h9a82719_6':
+        'quay.io/biocontainers/centrifuge:1.0.4_beta--h9a82719_6' }"
+
+    input:
+    tuple val(meta), path(results)
+    path db
+
+    output:
+    tuple val(meta), path('*.txt')                , emit: kreport
+    path "versions.yml"                                  , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    db_name=`find -L ${db} -name "*.1.cf" -not -name "._*"  | sed 's/.1.cf//'`
+    centrifuge-kreport -x \$db_name ${results} > ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        centrifuge: \$( centrifuge --version  | sed -n 1p | sed 's/^.*centrifuge-class version //')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/centrifuge/kreport/meta.yml

@@ -0,0 +1,41 @@
+name: "centrifuge_kreport"
+description: Creates Kraken-style reports from centrifuge out files
+keywords:
+  - metagenomics
+tools:
+  - centrifuge:
+      description: Centrifuge is a classifier for metagenomic sequences.
+      homepage: https://ccb.jhu.edu/software/centrifuge/
+      documentation: https://ccb.jhu.edu/software/centrifuge/manual.shtml
+      doi: 10.1101/gr.210641.116
+      licence: ["GPL v3"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - results:
+      type: file
+      description: File containing the centrifuge classification results
+      pattern: "*.{txt}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - kreport:
+      type: file
+      description: |
+        File containing kraken-style report from centrifuge
+        out files.
+      pattern: "*.{txt}"
+authors:
+  - "@sofstam"
+  - "@jfy133"

modules/nf-core/modules/diamond/blastx/main.nf

@@ -0,0 +1,53 @@
+process DIAMOND_BLASTX {
+    tag "$meta.id"
+    label 'process_medium'
+
+    // Dimaond is limited to v2.0.9 because there is not a
+    // singularity version higher than this at the current time.
+    conda (params.enable_conda ? "bioconda::diamond=2.0.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/diamond:2.0.9--hdcc8f71_0' :
+        'quay.io/biocontainers/diamond:2.0.9--hdcc8f71_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    path db
+    val outext
+
+    output:
+    tuple val(meta), path('*.{blast,xml,txt,daa,sam,tsv,paf}'), emit: output
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    switch ( outext ) {
+        case "blast": outfmt = 0; break
+        case "xml": outfmt = 5; break
+        case "txt": outfmt = 6; break
+        case "daa": outfmt = 100; break
+        case "sam": outfmt = 101; break
+        case "tsv": outfmt = 102; break
+        case "paf": outfmt = 103; break
+    }
+    """
+    DB=`find -L ./ -name "*.dmnd" | sed 's/.dmnd//'`
+
+    diamond \\
+        blastx \\
+        --threads $task.cpus \\
+        --db \$DB \\
+        --query $fasta \\
+        --outfmt ${outfmt} \\
+        $args \\
+        --out ${prefix}.${outext}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        diamond: \$(diamond --version 2>&1 | tail -n 1 | sed 's/^diamond version //')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/diamond/blastx/meta.yml

@@ -0,0 +1,52 @@
+name: diamond_blastx
+description: Queries a DIAMOND database using blastx mode
+keywords:
+  - fasta
+  - diamond
+  - blastx
+  - DNA sequence
+tools:
+  - diamond:
+      description: Accelerated BLAST compatible local sequence aligner
+      homepage: https://github.com/bbuchfink/diamond
+      documentation: https://github.com/bbuchfink/diamond/wiki
+      tool_dev_url: https://github.com/bbuchfink/diamond
+      doi: "doi:10.1038/s41592-021-01101-x"
+      licence: ["GPL v3.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
+      type: file
+      description: Input fasta file containing query sequences
+      pattern: "*.{fa,fasta}"
+  - db:
+      type: directory
+      description: Directory containing the nucelotide blast database
+      pattern: "*"
+  - outext:
+      type: string
+      description: |
+        Specify the type of output file to be generated. `blast` corresponds to
+        BLAST pairwise format. `xml` corresponds to BLAST xml format.
+        `txt` corresponds to to BLAST tabular format. `tsv` corresponds to
+        taxonomic classification format.
+      pattern: "blast|xml|txt|daa|sam|tsv|paf"
+
+output:
+  - txt:
+      type: file
+      description: File containing blastx hits
+      pattern: "*.{blastx.txt}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@spficklin"
+  - "@jfy133"

modules/nf-core/modules/fastp/main.nf

@@ -0,0 +1,75 @@
+process FASTP {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::fastp=0.23.2' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastp:0.23.2--h79da9fb_0' :
+        'quay.io/biocontainers/fastp:0.23.2--h79da9fb_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    val   save_trimmed_fail
+    val   save_merged
+
+    output:
+    tuple val(meta), path('*.trim.fastq.gz')  , optional:true, emit: reads
+    tuple val(meta), path('*.json')           , emit: json
+    tuple val(meta), path('*.html')           , emit: html
+    tuple val(meta), path('*.log')            , emit: log
+    path "versions.yml"                       , emit: versions
+    tuple val(meta), path('*.fail.fastq.gz')  , optional:true, emit: reads_fail
+    tuple val(meta), path('*.merged.fastq.gz'), optional:true, emit: reads_merged
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    // Added soft-links to original fastqs for consistent naming in MultiQC
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (meta.single_end) {
+        def fail_fastq = save_trimmed_fail ? "--failed_out ${prefix}.fail.fastq.gz" : ''
+        """
+        [ ! -f  ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz
+        fastp \\
+            --in1 ${prefix}.fastq.gz \\
+            --out1 ${prefix}.trim.fastq.gz \\
+            --thread $task.cpus \\
+            --json ${prefix}.fastp.json \\
+            --html ${prefix}.fastp.html \\
+            $fail_fastq \\
+            $args \\
+            2> ${prefix}.fastp.log
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            fastp: \$(fastp --version 2>&1 | sed -e "s/fastp //g")
+        END_VERSIONS
+        """
+    } else {
+        def fail_fastq  = save_trimmed_fail ? "--unpaired1 ${prefix}_1.fail.fastq.gz --unpaired2 ${prefix}_2.fail.fastq.gz" : ''
+        def merge_fastq = save_merged ? "-m --merged_out ${prefix}.merged.fastq.gz" : ''
+        """
+        [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
+        [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
+        fastp \\
+            --in1 ${prefix}_1.fastq.gz \\
+            --in2 ${prefix}_2.fastq.gz \\
+            --out1 ${prefix}_1.trim.fastq.gz \\
+            --out2 ${prefix}_2.trim.fastq.gz \\
+            --json ${prefix}.fastp.json \\
+            --html ${prefix}.fastp.html \\
+            $fail_fastq \\
+            $merge_fastq \\
+            --thread $task.cpus \\
+            --detect_adapter_for_pe \\
+            $args \\
+            2> ${prefix}.fastp.log
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            fastp: \$(fastp --version 2>&1 | sed -e "s/fastp //g")
+        END_VERSIONS
+        """
+    }
+}

modules/nf-core/modules/fastp/meta.yml

@@ -0,0 +1,68 @@
+name: fastp
+description: Perform adapter/quality trimming on sequencing reads
+keywords:
+  - trimming
+  - quality control
+  - fastq
+tools:
+  - fastp:
+      description: |
+        A tool designed to provide fast all-in-one preprocessing for FastQ files. This tool is developed in C++ with multithreading supported to afford high performance.
+      documentation: https://github.com/OpenGene/fastp
+      doi: https://doi.org/10.1093/bioinformatics/bty560
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - save_trimmed_fail:
+      type: boolean
+      description: Specify true to save files that failed to pass trimming thresholds ending in `*.fail.fastq.gz`
+  - save_merged:
+      type: boolean
+      description: Specify true to save all merged reads to the a file ending in `*.merged.fastq.gz`
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: The trimmed/modified/unmerged fastq reads
+      pattern: "*trim.fastq.gz"
+  - json:
+      type: file
+      description: Results in JSON format
+      pattern: "*.json"
+  - html:
+      type: file
+      description: Results in HTML format
+      pattern: "*.html"
+  - log:
+      type: file
+      description: fastq log file
+      pattern: "*.log"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads_fail:
+      type: file
+      description: Reads the failed the preprocessing
+      pattern: "*fail.fastq.gz"
+  - reads_merged:
+      type: file
+      description: Reads that were successfully merged
+      pattern: "*.{merged.fastq.gz}"
+authors:
+  - "@drpatelh"
+  - "@kevinmenden"

modules/nf-core/modules/kaiju/kaiju/main.nf

@@ -0,0 +1,41 @@
+process KAIJU_KAIJU {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::kaiju=1.8.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kaiju:1.8.2--h5b5514e_1':
+        'quay.io/biocontainers/kaiju:1.8.2--h5b5514e_1' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path(db)
+
+    output:
+    tuple val(meta), path('*.tsv'), emit: results
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input = meta.single_end ? "-i ${reads}" : "-i ${reads[0]} -j ${reads[1]}"
+    """
+    dbnodes=`find -L ${db} -name "*nodes.dmp"`
+    dbname=`find -L ${db} -name "*.fmi" -not -name "._*"`
+    kaiju \\
+        $args \\
+        -z $task.cpus \\
+        -t \$dbnodes \\
+        -f \$dbname \\
+        -o ${prefix}.tsv \\
+        $input
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/kaiju/kaiju/meta.yml

@@ -0,0 +1,53 @@
+name: kaiju_kaiju
+description: Taxonomic classification of metagenomic sequence data using a protein reference database
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - taxonomic profiling
+tools:
+  - kaiju:
+      description: Fast and sensitive taxonomic classification for metagenomics
+      homepage: https://kaiju.binf.ku.dk/
+      documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md
+      tool_dev_url: https://github.com/bioinformatics-centre/kaiju
+      doi: "10.1038/ncomms11257"
+      licence: ["GNU GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input fastq/fasta files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+      pattern: "*.{fastq,fq,fasta,fa,fsa,fas,fna,fastq.gz,fq.gz,fasta.gz,fa.gz,fsa.gz,fas.gz,fna.gz}"
+  - db:
+      type: files
+      description: |
+        List containing the database and nodes files for Kaiju
+        e.g. [ 'database.fmi', 'nodes.dmp' ]
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - results:
+      type: file
+      description: Results with taxonomic classification of each read
+      pattern: "*.tsv"
+
+authors:
+  - "@talnor"
+  - "@sofstam"
+  - "@jfy133"

modules/nf-core/modules/kaiju/kaiju2table/main.nf

@@ -0,0 +1,40 @@
+process KAIJU_KAIJU2TABLE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::kaiju=1.8.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kaiju:1.8.2--h5b5514e_1':
+        'quay.io/biocontainers/kaiju:1.8.2--h2e03b76_0' }"
+
+    input:
+    tuple val(meta), path(results)
+    path db
+    val taxon_rank
+
+    output:
+    tuple val(meta), path('*.txt'), emit: summary
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    dbnodes=`find -L ${db} -name "*nodes.dmp"`
+    dbname=`find -L ${db} -name "*.fmi" -not -name "._*"`
+    kaiju2table   $args \\
+        -t \$dbnodes \\
+        -n \$dbname \\
+        -r ${taxon_rank} \\
+        -o ${prefix}.txt \\
+        ${results}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/kaiju/kaiju2table/meta.yml

@@ -0,0 +1,50 @@
+name: "kaiju_kaiju2table"
+description: write your description here
+keywords:
+  - classify
+  - metagenomics
+tools:
+  - kaiju:
+      description: Fast and sensitive taxonomic classification for metagenomics
+      homepage: https://kaiju.binf.ku.dk/
+      documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md
+      tool_dev_url: https://github.com/bioinformatics-centre/kaiju
+      doi: "10.1038/ncomms11257"
+      licence: ["GNU GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - results:
+      type: file
+      description: File containing the kaiju classification results
+      pattern: "*.{txt}"
+  - taxon_rank:
+      type: string
+      description: |
+        Taxonomic rank to display in report
+        pattern: "phylum|class|order|family|genus|species"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - results:
+      type: file
+      description: |
+        Summary table for a given taxonomic rank
+      pattern: "*.{tsv}"
+
+authors:
+  - "@sofstam"
+  - "@talnor"
+  - "@jfy133"

modules/nf-core/modules/kraken2/kraken2/main.nf

@@ -0,0 +1,49 @@
+process KRAKEN2_KRAKEN2 {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? 'bioconda::kraken2=2.1.2 conda-forge::pigz=2.6' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0' :
+        'quay.io/biocontainers/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path  db
+
+    output:
+    tuple val(meta), path('*classified*')  , emit: classified
+    tuple val(meta), path('*unclassified*'), emit: unclassified
+    tuple val(meta), path('*report.txt')   , emit: txt
+    path "versions.yml"                    , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def paired       = meta.single_end ? "" : "--paired"
+    def classified   = meta.single_end ? "${prefix}.classified.fastq"   : "${prefix}.classified#.fastq"
+    def unclassified = meta.single_end ? "${prefix}.unclassified.fastq" : "${prefix}.unclassified#.fastq"
+    """
+    kraken2 \\
+        --db $db \\
+        --threads $task.cpus \\
+        --unclassified-out $unclassified \\
+        --classified-out $classified \\
+        --report ${prefix}.kraken2.report.txt \\
+        --gzip-compressed \\
+        $paired \\
+        $args \\
+        $reads
+
+    pigz -p $task.cpus *.fastq
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kraken2: \$(echo \$(kraken2 --version 2>&1) | sed 's/^.*Kraken version //; s/ .*\$//')
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/kraken2/kraken2/meta.yml

@@ -0,0 +1,60 @@
+name: kraken2_kraken2
+description: Classifies metagenomic sequence data
+keywords:
+  - classify
+  - metagenomics
+  - fastq
+  - db
+tools:
+  - kraken2:
+      description: |
+        Kraken2 is a taxonomic sequence classifier that assigns taxonomic labels to sequence reads
+      homepage: https://ccb.jhu.edu/software/kraken2/
+      documentation: https://github.com/DerrickWood/kraken2/wiki/Manual
+      doi: 10.1186/s13059-019-1891-0
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+  - db:
+      type: directory
+      description: Kraken2 database
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - classified:
+      type: file
+      description: |
+        Reads classified to belong to any of the taxa
+        on the Kraken2 database.
+      pattern: "*{fastq.gz}"
+  - unclassified:
+      type: file
+      description: |
+        Reads not classified to belong to any of the taxa
+        on the Kraken2 database.
+      pattern: "*{fastq.gz}"
+  - txt:
+      type: file
+      description: |
+        Kraken2 report containing stats about classified
+        and not classifed reads.
+      pattern: "*.{report.txt}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

modules/nf-core/modules/malt/run/main.nf

@@ -0,0 +1,50 @@
+process MALT_RUN {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::malt=0.53" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/malt:0.53--hdfd78af_0' :
+        'quay.io/biocontainers/malt:0.53--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fastqs)
+    val mode
+    path index
+
+    output:
+    tuple val(meta), path("*.rma6")                          , emit: rma6
+    tuple val(meta), path("*.{tab,text,sam}"),  optional:true, emit: alignments
+    tuple val(meta), path("*.log")                           , emit: log
+    path "versions.yml"                                      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def avail_mem = 6
+    if (!task.memory) {
+        log.info '[MALT_RUN] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    malt-run \\
+        -J-Xmx${avail_mem}g \\
+        -t $task.cpus \\
+        -v \\
+        -o . \\
+        $args \\
+        --inFile ${fastqs.join(' ')} \\
+        -m $mode \\
+        --index $index/ |&tee ${prefix}-malt-run.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        malt: \$(malt-run --help  2>&1 | grep -o 'version.* ' | cut -f 1 -d ',' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/malt/run/meta.yml

@@ -0,0 +1,58 @@
+name: malt_run
+description: MALT, an acronym for MEGAN alignment tool, is a sequence alignment and analysis tool designed for processing high-throughput sequencing data, especially in the context of metagenomics.
+keywords:
+  - malt
+  - alignment
+  - metagenomics
+  - ancient DNA
+  - aDNA
+  - palaeogenomics
+  - archaeogenomics
+  - microbiome
+tools:
+  - malt:
+      description: A tool for mapping metagenomic data
+      homepage: https://www.wsi.uni-tuebingen.de/lehrstuehle/algorithms-in-bioinformatics/software/malt/
+      documentation: https://software-ab.informatik.uni-tuebingen.de/download/malt/manual.pdf
+      tool_dev_url: None
+      doi: "10.1038/s41559-017-0446-6"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastqs:
+      type: file
+      description: Input FASTQ files
+      pattern: "*.{fastq.gz,fq.gz}"
+  - mode:
+      type: string
+      description: Program mode
+      pattern: "Unknown|BlastN|BlastP|BlastX|Classifier"
+  - index:
+      type: directory
+      description: Index/database directory from malt-build
+      pattern: "*/"
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - rma6:
+      type: file
+      description: MEGAN6 RMA6 file
+      pattern: "*.rma6"
+  - sam:
+      type: file
+      description: Alignment files in Tab, Text or MEGAN-compatible SAM format
+      pattern: "*.{tab,txt,sam}"
+  - log:
+      type: file
+      description: Log of verbose MALT stdout
+      pattern: "*-malt-run.log"
+
+authors:
+  - "@jfy133"

modules/nf-core/modules/megan/rma2info/main.nf

@@ -0,0 +1,38 @@
+process MEGAN_RMA2INFO {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::megan=6.21.7" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/megan:6.21.7--h9ee0642_0':
+        'quay.io/biocontainers/megan:6.21.7--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(rma6)
+    val(megan_summary)
+
+    output:
+    tuple val(meta), path("*.txt.gz")               , emit: txt
+    tuple val(meta), path("*.megan"), optional: true, emit: megan_summary
+    path "versions.yml"                             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def summary = megan_summary ? "-es ${prefix}.megan" : ""
+    """
+    rma2info \\
+        -i ${rma6} \\
+        -o ${prefix}.txt.gz \\
+        ${summary} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        megan: \$(echo \$(rma2info 2>&1) | grep version | sed 's/.*version //g;s/, built.*//g')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/megan/rma2info/meta.yml

@@ -0,0 +1,51 @@
+name: "megan_rma2info"
+description: Analyses an RMA file and exports information in text format
+keywords:
+  - megan
+  - rma6
+  - classification
+  - conversion
+tools:
+  - "megan":
+      description: "A tool for studying the taxonomic content of a set of DNA reads"
+      homepage: "https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/algorithms-in-bioinformatics/software/megan6/"
+      documentation: "https://software-ab.informatik.uni-tuebingen.de/download/megan6/welcome.html"
+      tool_dev_url: "https://github.com/husonlab/megan-ce"
+      doi: "10.1371/journal.pcbi.1004957"
+      licence: "['GPL >=3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - rma6:
+      type: file
+      description: RMA6 file from MEGAN or MALT
+      pattern: "*.rma6"
+  - megan_summary:
+      type: boolean
+      description: Specify whether to generate an MEGAN summary file
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - txt:
+      type: file
+      description: Compressed text file
+      pattern: "*.txt.gz"
+  - megan_summary:
+      type: file
+      description: Optionally generated MEGAN summary file
+      pattern: "*.megan"
+
+authors:
+  - "@jfy133"

modules/nf-core/modules/metaphlan3/main.nf

@@ -0,0 +1,45 @@
+process METAPHLAN3 {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? 'bioconda::metaphlan=3.0.12' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/metaphlan:3.0.12--pyhb7b1952_0' :
+        'quay.io/biocontainers/metaphlan:3.0.12--pyhb7b1952_0' }"
+
+    input:
+    tuple val(meta), path(input)
+    path metaphlan_db
+
+    output:
+    tuple val(meta), path("*_profile.txt")   ,                emit: profile
+    tuple val(meta), path("*.biom")          ,                emit: biom
+    tuple val(meta), path('*.bowtie2out.txt'), optional:true, emit: bt2out
+    path "versions.yml"                      ,                emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_type  = ("$input".endsWith(".fastq.gz") || "$input".endsWith(".fq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
+    def input_data  = ("$input_type".contains("fastq")) && !meta.single_end ? "${input[0]},${input[1]}" : "$input"
+    def bowtie2_out = "$input_type" == "--input_type bowtie2out" || "$input_type" == "--input_type sam" ? '' : "--bowtie2out ${prefix}.bowtie2out.txt"
+
+    """
+    metaphlan \\
+        --nproc $task.cpus \\
+        $input_type \\
+        $input_data \\
+        $args \\
+        $bowtie2_out \\
+        --bowtie2db ${metaphlan_db} \\
+        --biom ${prefix}.biom \\
+        --output_file ${prefix}_profile.txt
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metaphlan3: \$(metaphlan --version 2>&1 | awk '{print \$3}')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/metaphlan3/meta.yml

@@ -0,0 +1,52 @@
+name: metaphlan3
+description: MetaPhlAn is a tool for profiling the composition of microbial communities from metagenomic shotgun sequencing data.
+keywords:
+  - metagenomics
+  - classification
+  - fastq
+  - bam
+  - fasta
+tools:
+  - metaphlan3:
+      description: Identify clades (phyla to species) present in the metagenome obtained from a microbiome sample and their relative abundance
+      homepage: https://huttenhower.sph.harvard.edu/metaphlan/
+      documentation: https://github.com/biobakery/MetaPhlAn
+      doi: "10.7554/eLife.65088"
+      licence: ["MIT License"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: Metaphlan 3.0 can classify the metagenome from a variety of input data types, including FASTQ files (single-end and paired-end), FASTA, bowtie2-produced SAM files (produced from alignments to the MetaPHlAn marker database) and intermediate bowtie2 alignment files (bowtie2out)
+      pattern: "*.{fastq.gz, fasta, fasta.gz, sam, bowtie2out.txt}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - profile:
+      type: file
+      description: Tab-separated output file of the predicted taxon relative abundances
+      pattern: "*.{txt}"
+  - biom:
+      type: file
+      description: General-use format for representing biological sample by observation contingency tables
+      pattern: "*.{biom}"
+  - bowtie2out:
+      type: file
+      description: Intermediate Bowtie2 output produced from mapping the metagenome against the MetaPHlAn marker database ( not compatible with `bowtie2out` files generated with MetaPhlAn versions below 3 )
+      pattern: "*.{bowtie2out.txt}"
+
+authors:
+  - "@MGordon09"

modules/nf-core/modules/minimap2/align/main.nf

@@ -0,0 +1,48 @@
+process MINIMAP2_ALIGN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::minimap2=2.21 bioconda::samtools=1.12' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' :
+        'quay.io/biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path reference
+    val bam_format
+    val cigar_paf_format
+    val cigar_bam
+
+    output:
+    tuple val(meta), path("*.paf"), optional: true, emit: paf
+    tuple val(meta), path("*.bam"), optional: true, emit: bam
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_reads = meta.single_end ? "$reads" : "${reads[0]} ${reads[1]}"
+    def bam_output = bam_format ? "-a | samtools sort | samtools view -@ ${task.cpus} -b -h -o ${prefix}.bam" : "-o ${prefix}.paf"
+    def cigar_paf = cigar_paf_format && !bam_format ? "-c" : ''
+    def set_cigar_bam = cigar_bam && bam_format ? "-L" : ''
+    """
+    minimap2 \\
+        $args \\
+        -t $task.cpus \\
+        $reference \\
+        $input_reads \\
+        $cigar_paf \\
+        $set_cigar_bam \\
+        $bam_output
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        minimap2: \$(minimap2 --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/minimap2/align/meta.yml

@@ -0,0 +1,65 @@
+name: minimap2_align
+description: A versatile pairwise aligner for genomic and spliced nucleotide sequences
+keywords:
+  - align
+  - fasta
+  - fastq
+  - genome
+  - paf
+  - reference
+tools:
+  - minimap2:
+      description: |
+        A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+      homepage: https://github.com/lh3/minimap2
+      documentation: https://github.com/lh3/minimap2#uguide
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FASTA or FASTQ files of size 1 and 2 for single-end
+        and paired-end data, respectively.
+  - reference:
+      type: file
+      description: |
+        Reference database in FASTA format.
+  - bam_format:
+      type: boolean
+      description: Specify that output should be in BAM format
+  - cigar_paf_format:
+      type: boolean
+      description: Specify that output CIGAR should be in PAF format
+  - cigar_bam:
+      type: boolean
+      description: |
+        Write CIGAR with >65535 ops at the CG tag. This is recommended when
+        doing XYZ (https://github.com/lh3/minimap2#working-with-65535-cigar-operations)
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - paf:
+      type: file
+      description: Alignment in PAF format
+      pattern: "*.paf"
+  - bam:
+      type: file
+      description: Alignment in BAM format
+      pattern: "*.bam"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@heuermh"
+  - "@sofstam"
+  - "@sateeshperi"
+  - "@jfy133"

modules/nf-core/modules/minimap2/index/main.nf

@@ -0,0 +1,33 @@
+process MINIMAP2_INDEX {
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::minimap2=2.21' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/minimap2:2.21--h5bf99c6_0' :
+        'quay.io/biocontainers/minimap2:2.21--h5bf99c6_0' }"
+
+    input:
+    path fasta
+
+    output:
+    path "*.mmi"        , emit: index
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    minimap2 \\
+        -t $task.cpus \\
+        -d ${fasta.baseName}.mmi \\
+        $args \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        minimap2: \$(minimap2 --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/minimap2/index/meta.yml

@@ -0,0 +1,30 @@
+name: minimap2_index
+description: Provides fasta index required by minimap2 alignment.
+keywords:
+  - index
+  - fasta
+  - reference
+tools:
+  - minimap2:
+      description: |
+        A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+      homepage: https://github.com/lh3/minimap2
+      documentation: https://github.com/lh3/minimap2#uguide
+      licence: ["MIT"]
+input:
+  - fasta:
+      type: file
+      description: |
+        Reference database in FASTA format.
+output:
+  - mmi:
+      type: file
+      description: Minimap2 fasta index.
+      pattern: "*.mmi"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@yuukiiwa"
+  - "@drpatelh"

modules/nf-core/modules/porechop/main.nf

@@ -0,0 +1,35 @@
+process PORECHOP {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::porechop=0.2.4" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/porechop:0.2.4--py39h7cff6ad_2' :
+        'quay.io/biocontainers/porechop:0.2.4--py39h7cff6ad_2' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.fastq.gz"), emit: reads
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    porechop \\
+        -i $reads \\
+        -t $task.cpus \\
+        $args \\
+        -o ${prefix}.fastq.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        porechop: \$( porechop --version )
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/porechop/meta.yml

@@ -0,0 +1,50 @@
+name: porechop
+description: Adapter removal and demultiplexing of Oxford Nanopore reads
+keywords:
+  - adapter
+  - nanopore
+  - demultiplexing
+tools:
+  - porechop:
+      description: Adapter removal and demultiplexing of Oxford Nanopore reads
+      homepage: "https://github.com/rrwick/Porechop"
+      documentation: "https://github.com/rrwick/Porechop"
+      tool_dev_url: "https://github.com/rrwick/Porechop"
+      doi: "10.1099/mgen.0.000132"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: fastq/fastq.gz file
+      pattern: "*.{fastq,fastq.gz,fq,fq.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: Demultiplexed and/or adapter-trimmed fastq.gz file
+      pattern: "*.{fastq.gz}"
+
+authors:
+  - "@ggabernet"
+  - "@jasmezz"
+  - "@d4straub"
+  - "@LaurenceKuhl"
+  - "@SusiJo"
+  - "@jonasscheid"
+  - "@jonoave"
+  - "@GokceOGUZ"

modules/nf-core/modules/prinseqplusplus/main.nf

@@ -0,0 +1,61 @@
+process PRINSEQPLUSPLUS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::prinseq-plus-plus=1.2.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/prinseq-plus-plus:1.2.3--hc90279e_1':
+        'quay.io/biocontainers/prinseq-plus-plus:1.2.3--hc90279e_1' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*_good_out*.fastq.gz")                  , emit: good_reads
+    tuple val(meta), path("*_single_out*.fastq.gz"), optional: true, emit: single_reads
+    tuple val(meta), path("*_bad_out*.fastq.gz")   , optional: true, emit: bad_reads
+    tuple val(meta), path("*.log")                                 , emit: log
+    path "versions.yml"                                            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    if (meta.single_end) {
+        """
+        prinseq++ \\
+            -threads $task.cpus \\
+            -fastq ${reads} \\
+            -out_name ${prefix} \\
+            -out_gz \\
+            -VERBOSE 1 \\
+            $args \\
+            | tee ${prefix}.log
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
+        END_VERSIONS
+        """
+    } else {
+        """
+        prinseq++ \\
+            -threads $task.cpus \\
+            -fastq ${reads[0]} \\
+            -fastq2 ${reads[1]} \\
+            -out_name ${prefix} \\
+            -out_gz \\
+            -VERBOSE 1 \\
+            $args \\
+            | tee ${prefix}.log
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
+        END_VERSIONS
+        """
+    }
+}

modules/nf-core/modules/prinseqplusplus/meta.yml

@@ -0,0 +1,60 @@
+name: "prinseqplusplus"
+description: PRINSEQ++ is a C++ implementation of the prinseq-lite.pl program. It can be used to filter, reformat or trim genomic and metagenomic sequence data
+keywords:
+  - fastq
+  - fasta
+  - filter
+  - trim
+tools:
+  - "prinseqplusplus":
+      description: "PRINSEQ++ - Multi-threaded C++ sequence cleaning"
+      homepage: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      documentation: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      tool_dev_url: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
+      doi: "10.7287/peerj.preprints.27553v1"
+      licence: "['GPL v2']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end
+        data, respectively.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - good_reads:
+      type: file
+      description: Reads passing filter(s) in gzipped FASTQ format
+      pattern: "*_good_out_{R1,R2}.fastq.gz"
+  - single_reads:
+      type: file
+      description: |
+        Single reads without the pair passing filter(s) in gzipped FASTQ format
+      pattern: "*_single_out_{R1,R2}.fastq.gz"
+  - bad_reads:
+      type: file
+      description: |
+        Reads without not passing filter(s) in gzipped FASTQ format
+      pattern: "*_bad_out_{R1,R2}.fastq.gz"
+  - log:
+      type: file
+      description: |
+        Verbose level 2 STDOUT information in a log file
+      pattern: "*.log"
+
+authors:
+  - "@jfy133"

modules/nf-core/modules/samtools/bam2fq/main.nf

@@ -0,0 +1,56 @@
+process SAMTOOLS_BAM2FQ {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(inputbam)
+    val split
+
+    output:
+    tuple val(meta), path("*.fq.gz"), emit: reads
+    path "versions.yml"             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    if (split){
+        """
+        samtools \\
+            bam2fq \\
+            $args \\
+            -@ $task.cpus \\
+            -1 ${prefix}_1.fq.gz \\
+            -2 ${prefix}_2.fq.gz \\
+            -0 ${prefix}_other.fq.gz \\
+            -s ${prefix}_singleton.fq.gz \\
+            $inputbam
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        samtools \\
+            bam2fq \\
+            $args \\
+            -@ $task.cpus \\
+            $inputbam | gzip --no-name > ${prefix}_interleaved.fq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    }
+}

modules/nf-core/modules/samtools/bam2fq/meta.yml

@@ -0,0 +1,55 @@
+name: samtools_bam2fq
+description: |
+  The module uses bam2fq method from samtools to
+  convert a SAM, BAM or CRAM file to FASTQ format
+keywords:
+  - bam2fq
+  - samtools
+  - fastq
+tools:
+  - samtools:
+      description: Tools for dealing with SAM, BAM and CRAM files
+      homepage: None
+      documentation: http://www.htslib.org/doc/1.1/samtools.html
+      tool_dev_url: None
+      doi: ""
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - inputbam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - split:
+      type: boolean
+      description: |
+        TRUE/FALSE value to indicate if reads should be separated into
+        /1, /2 and if present other, or singleton.
+        Note: choosing TRUE will generate 4 different files.
+        Choosing FALSE will produce a single file, which will be interleaved in case
+        the input contains paired reads.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: |
+        FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton)
+        or a single interleaved .fq.gz file if the user chooses not to split the reads.
+      pattern: "*.fq.gz"
+
+authors:
+  - "@lescai"

modules/nf-core/modules/samtools/view/main.nf

@@ -0,0 +1,56 @@
+process SAMTOOLS_VIEW {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(input), path(index)
+    path fasta
+
+    output:
+    tuple val(meta), path("*.bam") , emit: bam , optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    path  "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--reference ${fasta} -C" : ""
+    def file_type = input.getExtension()
+    if ("$input" == "${prefix}.${file_type}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    samtools \\
+        view \\
+        --threads ${task.cpus-1} \\
+        ${reference} \\
+        $args \\
+        $input \\
+        $args2 \\
+        > ${prefix}.${file_type}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+    touch ${prefix}.cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/samtools/view/meta.yml

@@ -0,0 +1,57 @@
+name: samtools_view
+description: filter/convert SAM/BAM/CRAM file
+keywords:
+  - view
+  - bam
+  - sam
+  - cram
+tools:
+  - samtools:
+      description: |
+        SAMtools is a set of utilities for interacting with and post-processing
+        short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+        These files are generated as output by short read aligners like BWA.
+      homepage: http://www.htslib.org/
+      documentation: hhttp://www.htslib.org/doc/samtools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - index:
+      type: optional file
+      description: BAM.BAI/CRAM.CRAI file
+      pattern: "*.{.bai,.crai}"
+  - fasta:
+      type: optional file
+      description: Reference file the CRAM was created with
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: filtered/converted BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - cram:
+      type: file
+      description: filtered/converted CRAM file
+      pattern: "*.cram"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"
+  - "@joseespinosa"
+  - "@FriederikeHanssen"

modules/nf-core/modules/untar/main.nf

@@ -0,0 +1,36 @@
+process UNTAR {
+    tag "$archive"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::tar=1.32" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
+        'biocontainers/biocontainers:v1.2.0_cv1' }"
+
+    input:
+    tuple val(meta), path(archive)
+
+    output:
+    tuple val(meta), path("$untar"), emit: untar
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args  = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    untar     = archive.toString() - '.tar.gz'
+    """
+    tar \\
+        -xzvf \\
+        $args \\
+        $archive \\
+        $args2 \\
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/untar/meta.yml

@@ -0,0 +1,38 @@
+name: untar
+description: Extract files.
+keywords:
+  - untar
+  - uncompress
+tools:
+  - untar:
+      description: |
+        Extract tar.gz files.
+      documentation: https://www.gnu.org/software/tar/manual/
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - archive:
+      type: file
+      description: File to be untar
+      pattern: "*.{tar}.{gz}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - untar:
+      type: file
+      description:
+      pattern: "*.*"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

nextflow.config

@@ -34,7 +34,7 @@ params {
     help                       = false
     validate_params            = true
     show_hidden_params         = false
-    schema_ignore_params       = 'genomes'
+    schema_ignore_params       = 'genomes,fasta'
     enable_conda               = false
 
     // Config options
@@ -51,6 +51,71 @@ params {
     max_cpus                   = 16
     max_time                   = '240.h'
 
+    // Databases
+    databases = null
+
+    // FASTQ preprocessing
+    perform_shortread_clipmerge             = false
+    shortread_clipmerge_tool                = 'fastp'
+    shortread_clipmerge_skipadaptertrim     = false
+    shortread_clipmerge_mergepairs          = false
+    shortread_clipmerge_excludeunmerged     = false
+    shortread_clipmerge_adapter1            = null
+    shortread_clipmerge_adapter2            = null
+    shortread_clipmerge_minlength           = 15
+    perform_longread_clip                   = false
+    save_preprocessed_reads                 = false
+
+    // Complexity filtering
+    perform_shortread_complexityfilter                   = false
+    shortread_complexityfilter_tool                      = 'bbduk'
+    shortread_complexityfilter_entropy                   = 0.3
+    shortread_complexityfilter_bbduk_windowsize          = 50
+    shortread_complexityfilter_bbduk_mask                = false
+    shortread_complexityfilter_prinseqplusplus_mode      = 'entropy'
+    shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
+    shortread_complexityfilter_fastp_threshold           = 30
+    save_complexityfiltered_reads                        = false
+
+    // run merging
+    perform_runmerging          = false
+    save_runmerged_reads        = false
+
+    // Host Removal
+    perform_shortread_hostremoval          = false
+    perform_longread_hostremoval           = false
+    hostremoval_reference                  = null
+    shortread_hostremoval_index            = null
+    longread_hostremoval_index             = null
+    save_hostremoval_index                 = false
+    save_hostremoval_mapped                = false
+    save_hostremoval_unmapped              = false
+
+
+    // MALT
+    run_malt                   = false
+    malt_mode                  = 'BlastN'
+    malt_generatemegansummary = false
+
+    // kraken2
+    run_kraken2                = false
+
+    // centrifuge
+    run_centrifuge             = false
+    centrifuge_save_unaligned  = false
+    centrifuge_save_aligned    = false
+    centrifuge_sam_format      = false
+
+    // metaphlan3
+    run_metaphlan3             = false
+
+    // kaiju
+    run_kaiju                  = false
+    kaiju_taxon_name           = 'species'
+
+    // diamond
+    run_diamond                = false
+    diamond_output_format      = 'txt'
 }
 
 // Load base.config by default for all pipelines
@@ -65,11 +130,11 @@ try {
 
 // Load nf-core/taxprofiler custom profiles from different institutions.
 // Warning: Uncomment only if a pipeline-specific instititutional config already exists on nf-core/configs!
-// try {
+try {
-//   includeConfig "${params.custom_config_base}/pipeline/taxprofiler.config"
+    includeConfig "${params.custom_config_base}/pipeline/taxprofiler.config"
-// } catch (Exception e) {
+} catch (Exception e) {
-//   System.err.println("WARNING: Could not load nf-core/config/taxprofiler profiles: ${params.custom_config_base}/pipeline/taxprofiler.config")
+    System.err.println("WARNING: Could not load nf-core/config/taxprofiler profiles: ${params.custom_config_base}/pipeline/taxprofiler.config")
-// }
+}
 
 
 profiles {
@@ -121,6 +186,8 @@ profiles {
     }
     test      { includeConfig 'conf/test.config'      }
     test_full { includeConfig 'conf/test_full.config' }
+    test_noprofiling { includeConfig 'conf/test_noprofiling.config' }
+    test_nopreprocessing { includeConfig 'conf/test_preprocessing.config' }
 }
 
 // Load igenomes.config if required
@@ -135,7 +202,7 @@ if (!params.igenomes_ignore) {
 // See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.
 
 env {
-    PYTHONNOUSERSITE = 1
+    PYTHONNOUSERSITE = '1'
     R_PROFILE_USER   = "/.Rprofile"
     R_ENVIRON_USER   = "/.Renviron"
     JULIA_DEPOT_PATH = "/usr/local/share/julia"

nextflow_schema.json

@@ -54,15 +54,6 @@
                     "fa_icon": "fas fa-book",
                     "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
                 },
-                "fasta": {
-                    "type": "string",
-                    "format": "file-path",
-                    "mimetype": "text/plain",
-                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
-                    "description": "Path to FASTA genome file.",
-                    "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.",
-                    "fa_icon": "far fa-file-code"
-                },
                 "igenomes_base": {
                     "type": "string",
                     "format": "directory-path",
@@ -265,5 +256,159 @@
         {
             "$ref": "#/definitions/generic_options"
         }
-    ]
+    ],
+    "properties": {
+        "databases": {
+            "type": "string",
+            "default": "None"
+        },
+        "shortread_clipmerge_excludeunmerged": {
+            "type": "boolean"
+        },
+        "run_malt": {
+            "type": "boolean"
+        },
+        "malt_mode": {
+            "type": "string",
+            "default": "BlastN"
+        },
+        "run_kraken2": {
+            "type": "boolean"
+        },
+        "run_centrifuge": {
+            "type": "boolean"
+        },
+        "centrifuge_save_unaligned": {
+            "type": "boolean"
+        },
+        "centrifuge_save_aligned": {
+            "type": "boolean"
+        },
+        "centrifuge_sam_format": {
+            "type": "boolean"
+        },
+        "run_metaphlan3": {
+            "type": "boolean",
+            "description": "Enable MetaPhlAn for taxonomic profiling"
+        },
+        "shortread_clipmerge_tool": {
+            "type": "string",
+            "default": "fastp",
+            "enum": ["fastp", "adapterremoval"]
+        },
+        "shortread_clipmerge_skipadaptertrim": {
+            "type": "boolean"
+        },
+        "shortread_clipmerge_mergepairs": {
+            "type": "boolean"
+        },
+        "shortread_clipmerge_adapter1": {
+            "type": "string",
+            "default": "None"
+        },
+        "shortread_clipmerge_adapter2": {
+            "type": "string",
+            "default": "None"
+        },
+        "shortread_clipmerge_minlength": {
+            "type": "integer",
+            "default": 15
+        },
+        "save_preprocessed_reads": {
+            "type": "boolean"
+        },
+        "shortread_complexityfilter_tool": {
+            "type": "string",
+            "default": "bbduk",
+            "enum": ["bbduk", "prinseqplusplus", "fastp"]
+        },
+        "shortread_complexityfilter_bbduk_windowsize": {
+            "type": "integer",
+            "default": 50
+        },
+        "shortread_complexityfilter_bbduk_mask": {
+            "type": "boolean"
+        },
+        "shortread_complexityfilter_entropy": {
+            "type": "number",
+            "default": 0.3
+        },
+        "shortread_complexityfilter_prinseqplusplus_mode": {
+            "type": "string",
+            "default": "entropy",
+            "enum": ["entropy", "dust"]
+        },
+        "shortread_complexityfilter_prinseqplusplus_dustscore": {
+            "type": "number",
+            "default": 0.5
+        },
+        "save_complexityfiltered_reads": {
+            "type": "boolean"
+        },
+        "save_runmerged_reads": {
+            "type": "boolean"
+        },
+        "perform_shortread_clipmerge": {
+            "type": "boolean"
+        },
+        "perform_longread_clip": {
+            "type": "boolean"
+        },
+        "perform_shortread_complexityfilter": {
+            "type": "boolean"
+        },
+        "perform_runmerging": {
+            "type": "boolean"
+        },
+        "perform_shortread_hostremoval": {
+            "type": "boolean"
+        },
+        "perform_longread_hostremoval": {
+            "type": "boolean"
+        },
+        "hostremoval_reference": {
+            "type": "string",
+            "default": "None"
+        },
+        "shortread_hostremoval_index": {
+            "type": "string",
+            "default": "None"
+        },
+        "save_hostremoval_index": {
+            "type": "boolean"
+        },
+        "save_hostremoval_mapped": {
+            "type": "boolean"
+        },
+        "save_hostremoval_unmapped": {
+            "type": "boolean"
+        },
+        "run_kaiju": {
+            "type": "boolean"
+        },
+        "malt_generatemegansummary": {
+            "type": "boolean"
+        },
+        "kaiju_taxon_name": {
+            "type": "string",
+            "default": "species",
+            "enum": ["phylum", "class", "order", "family", "genus", "species"]
+        },
+        "run_diamond": {
+            "type": "boolean"
+        },
+        "diamond_output_format": {
+            "type": "string",
+            "default": "tsv",
+            "enum": ["blast", "xml", "txt", "daa", "sam", "tsv", "paf"]
+        },
+        "longread_hostremoval_index": {
+            "type": "string",
+            "default": "None"
+        },
+        "shortread_complexityfilter_fastp_threshold": {
+            "type": "integer",
+            "default": 30
+        }
+    }
 }

subworkflows/local/db_check.nf

@@ -0,0 +1,53 @@
+//
+// Check input samplesheet and get read channels
+//
+
+include { DATABASE_CHECK } from '../../modules/local/database_check'
+include { UNTAR          } from '../../modules/nf-core/modules/untar/main'
+
+workflow DB_CHECK {
+    take:
+    dbsheet // file: /path/to/dbsheet.csv
+
+    main:
+
+    // TODO: make database sheet check
+    // Checks:
+    // 1) no duplicates,
+    // 2) args do not have quotes, e.g. just `,,` and NOT `,"",`
+    parsed_samplesheet = DATABASE_CHECK ( dbsheet )
+        .csv
+        .splitCsv ( header:true, sep:',' )
+        .map { create_db_channels(it) }
+
+    ch_dbs_for_untar = parsed_samplesheet
+        .branch {
+            untar: it[1].toString().endsWith(".tar.gz")
+            skip: true
+        }
+
+    // TODO Filter to only run UNTAR on DBs of tools actually using?
+    // TODO make optional whether to save
+    UNTAR ( ch_dbs_for_untar.untar )
+
+    ch_final_dbs = ch_dbs_for_untar.skip.mix( UNTAR.out.untar )
+
+    emit:
+    dbs = ch_final_dbs                        // channel: [ val(meta), [ db ] ]
+    versions = DATABASE_CHECK.out.versions.mix(UNTAR.out.versions.first()) // channel: [ versions.yml ]
+}
+
+def create_db_channels(LinkedHashMap row) {
+    def meta = [:]
+    meta.tool             = row.tool
+    meta.db_name          = row.db_name
+    meta.db_params        = row.db_params
+
+    def array = []
+    if (!file(row.db_path, type: 'dir').exists()) {
+        exit 1, "ERROR: Please check input samplesheet -> database could not be found!\n${row.db_path}"
+    }
+    array = [ meta, file(row.db_path) ]
+
+    return array
+}

subworkflows/local/input_check.nf

@@ -9,14 +9,31 @@ workflow INPUT_CHECK {
     samplesheet // file: /path/to/samplesheet.csv
 
     main:
-    SAMPLESHEET_CHECK ( samplesheet )
+    parsed_samplesheet = SAMPLESHEET_CHECK ( samplesheet )
         .csv
         .splitCsv ( header:true, sep:',' )
+        .branch {
+            fasta: it['fasta'] != ''
+            nanopore: it['instrument_platform'] == 'OXFORD_NANOPORE'
+            fastq: true
+        }
+
+    parsed_samplesheet.fastq
         .map { create_fastq_channel(it) }
-        .set { reads }
+        .set { fastq }
+
+    parsed_samplesheet.nanopore
+        .map { create_fastq_channel(it) }
+        .set { nanopore }
+
+    parsed_samplesheet.fasta
+        .map { create_fasta_channel(it) }
+        .set { fasta }
 
     emit:
-    reads                                     // channel: [ val(meta), [ reads ] ]
+    fastq = fastq ?: []                       // channel: [ val(meta), [ reads ] ]
+    nanopore = nanopore ?: []                 // channel: [ val(meta), [ reads ] ]
+    fasta = fasta ?: []                       // channel: [ val(meta), fasta ]
     versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ]
 }
 
@@ -24,8 +41,11 @@ workflow INPUT_CHECK {
 def create_fastq_channel(LinkedHashMap row) {
     // create meta map
     def meta = [:]
-    meta.id         = row.sample
+    meta.id                     = row.sample
-    meta.single_end = row.single_end.toBoolean()
+    meta.run_accession          = row.run_accession
+    meta.instrument_platform    = row.instrument_platform
+    meta.single_end             = row.single_end.toBoolean()
+    meta.is_fasta               = false
 
     // add path(s) of the fastq file(s) to the meta map
     def fastq_meta = []
@@ -35,10 +55,34 @@ def create_fastq_channel(LinkedHashMap row) {
     if (meta.single_end) {
         fastq_meta = [ meta, [ file(row.fastq_1) ] ]
     } else {
-        if (!file(row.fastq_2).exists()) {
+        if (meta.instrument_platform == 'OXFORD_NANOPORE') {
-            exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}"
+            if (row.fastq_2 != '') {
+                exit 1, "ERROR: Please check input samplesheet -> For Oxford Nanopore reads Read 2 FastQ should be empty!\n${row.fastq_2}"
+            }
+            fastq_meta = [ meta, [ file(row.fastq_1) ] ]
+        } else {
+            if (!file(row.fastq_2).exists()) {
+                exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}"
+            }
+         fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ]
         }
-        fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ]
+
     }
     return fastq_meta
+}// Function to get list of [ meta, fasta ]
+def create_fasta_channel(LinkedHashMap row) {
+    def meta = [:]
+    meta.id                     = row.sample
+    meta.run_accession          = row.run_accession
+    meta.instrument_platform    = row.instrument_platform
+    meta.single_end             = true
+    meta.is_fasta               = true
+
+    def array = []
+    if (!file(row.fasta).exists()) {
+        exit 1, "ERROR: Please check input samplesheet -> FastA file does not exist!\n${row.fasta}"
+    }
+    array = [ meta, [ file(row.fasta) ] ]
+
+    return array
 }

subworkflows/local/longread_hostremoval.nf

@@ -0,0 +1,47 @@
+//
+// Remove host reads via alignment and export off-target reads
+//
+
+include { MINIMAP2_INDEX             } from '../../modules/nf-core/modules/minimap2/index/main'
+include { MINIMAP2_ALIGN             } from '../../modules/nf-core/modules/minimap2/align/main'
+include { SAMTOOLS_VIEW              } from '../../modules/nf-core/modules/samtools/view/main'
+include { SAMTOOLS_BAM2FQ            } from '../../modules/nf-core/modules/samtools/bam2fq/main'
+
+workflow LONGREAD_HOSTREMOVAL {
+    take:
+    reads     // [ [ meta ], [ reads ] ]
+    reference // /path/to/fasta
+    index     // /path/to/index
+
+    main:
+    ch_versions       = Channel.empty()
+    ch_multiqc_files  = Channel.empty()
+
+    if ( !params.longread_hostremoval_index ) {
+        ch_minimap2_index = MINIMAP2_INDEX ( reference ).index
+        ch_versions       = ch_versions.mix( MINIMAP2_INDEX.out.versions )
+    } else {
+        ch_minimap2_index = index
+    }
+
+    MINIMAP2_ALIGN ( reads, ch_minimap2_index, true, false, false )
+    ch_versions        = ch_versions.mix( MINIMAP2_ALIGN.out.versions.first() )
+    ch_minimap2_mapped = MINIMAP2_ALIGN.out.bam
+        .map {
+            meta, reads ->
+                [ meta, reads, [] ]
+        }
+
+
+    SAMTOOLS_VIEW ( ch_minimap2_mapped , [] )
+    ch_versions      = ch_versions.mix( SAMTOOLS_VIEW.out.versions.first() )
+
+    SAMTOOLS_BAM2FQ ( SAMTOOLS_VIEW.out.bam, false )
+    ch_versions      = ch_versions.mix( SAMTOOLS_BAM2FQ.out.versions.first() )
+
+
+    emit:
+    reads    = SAMTOOLS_BAM2FQ.out.reads   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions                 // channel: [ versions.yml ]
+}
+

subworkflows/local/longread_preprocessing.nf

@@ -0,0 +1,36 @@
+//
+// Process long raw reads with porechop
+//
+
+include { FASTQC as FASTQC_PROCESSED } from '../../modules/nf-core/modules/fastqc/main'
+include { PORECHOP                   } from '../../modules/nf-core/modules/porechop/main'
+
+workflow LONGREAD_PREPROCESSING {
+    take:
+    reads
+
+    main:
+    ch_versions      = Channel.empty()
+    ch_multiqc_files = Channel.empty()
+
+    PORECHOP ( reads )
+
+    ch_processed_reads = PORECHOP.out.reads
+                                .map {
+                                        meta, reads ->
+                                        def meta_new = meta.clone()
+                                        meta_new['single_end'] = 1
+                                        [ meta_new, reads ]
+                                    }
+
+    FASTQC_PROCESSED ( PORECHOP.out.reads )
+    ch_versions = ch_versions.mix(PORECHOP.out.versions.first())
+    ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+
+
+    emit:
+    reads    = ch_processed_reads   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions          // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/profiling.nf

@@ -0,0 +1,194 @@
+//
+// Run profiling
+//
+
+include { MALT_RUN                    } from '../../modules/nf-core/modules/malt/run/main'
+include { MEGAN_RMA2INFO              } from '../../modules/nf-core/modules/megan/rma2info/main'
+include { KRAKEN2_KRAKEN2             } from '../../modules/nf-core/modules/kraken2/kraken2/main'
+include { CENTRIFUGE_CENTRIFUGE       } from '../../modules/nf-core/modules/centrifuge/centrifuge/main'
+include { CENTRIFUGE_KREPORT          } from '../../modules/nf-core/modules/centrifuge/kreport/main'
+include { METAPHLAN3                  } from '../../modules/nf-core/modules/metaphlan3/main'
+include { KAIJU_KAIJU                 } from '../../modules/nf-core/modules/kaiju/kaiju/main'
+include { KAIJU_KAIJU2TABLE           } from '../../modules/nf-core/modules/kaiju/kaiju2table/main'
+include { DIAMOND_BLASTX              } from '../../modules/nf-core/modules/diamond/blastx/main'
+
+
+workflow PROFILING {
+    take:
+    reads // [ [ meta ], [ reads ] ]
+    databases // [ [ meta ], path ]
+
+    main:
+    ch_versions             = Channel.empty()
+    ch_multiqc_files        = Channel.empty()
+    ch_raw_profiles    = Channel.empty()
+
+/*
+        COMBINE READS WITH POSSIBLE DATABASES
+    */
+
+    // e.g. output [DUMP: reads_plus_db] [['id':'2612', 'run_accession':'combined', 'instrument_platform':'ILLUMINA', 'single_end':1], <reads_path>/2612.merged.fastq.gz, ['tool':'malt', 'db_name':'mal95', 'db_params':'"-id 90"'], <db_path>/malt90]
+    ch_input_for_profiling = reads
+            .map {
+                meta, reads ->
+                    def meta_new = meta.clone()
+                        pairtype = meta_new['single_end'] ? '_se' : '_pe'
+                        meta_new['id'] =  meta_new['id'] + pairtype
+                    [meta_new, reads]
+            }
+            .combine(databases)
+            .branch {
+                malt:    it[2]['tool'] == 'malt'
+                kraken2: it[2]['tool'] == 'kraken2'
+                metaphlan3: it[2]['tool'] == 'metaphlan3'
+                centrifuge: it[2]['tool'] == 'centrifuge'
+                kaiju: it[2]['tool'] == 'kaiju'
+                diamond: it[2]['tool'] == 'diamond'
+                unknown: true
+            }
+
+    /*
+        PREPARE PROFILER INPUT CHANNELS & RUN PROFILING
+    */
+
+    // Each tool as a slightly different input structure and generally separate
+    // input channels for reads vs databases. We restructure the channel tuple
+    // for each tool and make liberal use of multiMap to keep reads/databases
+    // channel element order in sync with each other
+
+    if ( params.run_malt ) {
+
+
+        // MALT: We groupTuple to have all samples in one channel for MALT as database
+        // loading takes a long time, so we only want to run it once per database
+        // TODO document somewhere we only accept illumina short reads for MALT?
+        ch_input_for_malt =  ch_input_for_profiling.malt
+                                .filter { it[0]['instrument_platform'] == 'ILLUMINA' }
+                                .map {
+                                    it ->
+                                        def temp_meta =  [ id: it[2]['db_name']]  + it[2]
+                                        def db = it[3]
+                                        [ temp_meta, it[1], db ]
+                                }
+                                .groupTuple(by: [0,2])
+                                .multiMap {
+                                    it ->
+                                        reads: [ it[0], it[1].flatten() ]
+                                        db: it[2]
+                                }
+
+        MALT_RUN ( ch_input_for_malt.reads, params.malt_mode, ch_input_for_malt.db )
+
+        ch_maltrun_for_megan = MALT_RUN.out.rma6
+                                .transpose()
+                                .map{
+                                    meta, rma ->
+                                            // re-extract meta from file names, use filename without rma to
+                                            // ensure we keep paired-end information in downstream filenames
+                                            // when no pair-merging
+                                            def meta_new = meta.clone()
+                                            meta_new['db_name'] = meta.id
+                                            meta_new['id'] = rma.baseName
+                                        [ meta_new, rma ]
+                                }
+
+        MEGAN_RMA2INFO (ch_maltrun_for_megan, params.malt_generatemegansummary )
+        ch_multiqc_files   = ch_multiqc_files.mix( MALT_RUN.out.log.collect{it[1]}.ifEmpty([])  )
+        ch_versions        = ch_versions.mix( MALT_RUN.out.versions.first(), MEGAN_RMA2INFO.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( MEGAN_RMA2INFO.out.txt )
+
+    }
+
+    if ( params.run_kraken2 ) {
+
+        ch_input_for_kraken2 =  ch_input_for_profiling.kraken2
+                                .multiMap {
+                                    it ->
+                                        reads: [ it[0] + it[2], it[1] ]
+                                        db: it[3]
+                                }
+
+        KRAKEN2_KRAKEN2 ( ch_input_for_kraken2.reads, ch_input_for_kraken2.db  )
+        ch_multiqc_files   = ch_multiqc_files.mix( KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([])  )
+        ch_versions        = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( KRAKEN2_KRAKEN2.out.txt )
+
+    }
+
+    if ( params.run_centrifuge ) {
+
+        ch_input_for_centrifuge =  ch_input_for_profiling.centrifuge
+                                .filter{
+                                    if (it[0].is_fasta) log.warn "[nf-core/taxprofiler] Centrifuge currently does not accept FASTA files as input. Skipping Centrifuge for sample ${it[0].id}."
+                                    !it[0].is_fasta
+                                }
+                                .multiMap {
+                                    it ->
+                                        reads: [ it[0] + it[2], it[1] ]
+                                        db: it[3]
+                                }
+
+        CENTRIFUGE_CENTRIFUGE ( ch_input_for_centrifuge.reads, ch_input_for_centrifuge.db, params.centrifuge_save_unaligned, params.centrifuge_save_aligned, params.centrifuge_sam_format  )
+        CENTRIFUGE_KREPORT (CENTRIFUGE_CENTRIFUGE.out.results, ch_input_for_centrifuge.db)
+        ch_versions        = ch_versions.mix( CENTRIFUGE_CENTRIFUGE.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( CENTRIFUGE_KREPORT.out.kreport )
+
+    }
+
+    if ( params.run_metaphlan3 ) {
+
+        ch_input_for_metaphlan3 = ch_input_for_profiling.metaphlan3
+                            .filter{
+                                if (it[0].is_fasta) log.warn "[nf-core/taxprofiler] MetaPhlAn3 currently does not accept FASTA files as input. Skipping MetaPhlAn3 for sample ${it[0].id}."
+                                !it[0].is_fasta
+                            }
+                            .multiMap {
+                                it ->
+                                    reads: [it[0] + it[2], it[1]]
+                                    db: it[3]
+                            }
+
+        METAPHLAN3 ( ch_input_for_metaphlan3.reads, ch_input_for_metaphlan3.db )
+        ch_versions        = ch_versions.mix( METAPHLAN3.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( METAPHLAN3.out.biom )
+
+    }
+
+    if ( params.run_kaiju ) {
+
+        ch_input_for_kaiju = ch_input_for_profiling.kaiju
+                            .multiMap {
+                                it ->
+                                    reads: [it[0] + it[2], it[1]]
+                                    db: it[3]
+                            }
+
+        KAIJU_KAIJU ( ch_input_for_kaiju.reads, ch_input_for_kaiju.db)
+        KAIJU_KAIJU2TABLE (KAIJU_KAIJU.out.results, ch_input_for_kaiju.db, params.kaiju_taxon_name)
+        ch_multiqc_files = ch_multiqc_files.mix( KAIJU_KAIJU2TABLE.out.summary.collect{it[1]}.ifEmpty([])  )
+        ch_versions = ch_versions.mix( KAIJU_KAIJU.out.versions.first() )
+        ch_raw_profiles = ch_raw_profiles.mix( KAIJU_KAIJU2TABLE.out.summary )
+
+    }
+
+    if ( params.run_diamond ) {
+
+        ch_input_for_diamond = ch_input_for_profiling.diamond
+                                .multiMap {
+                                    it ->
+                                        reads: [it[0] + it[2], it[1]]
+                                        db: it[3]
+                                }
+
+        DIAMOND_BLASTX ( ch_input_for_diamond.reads, ch_input_for_diamond.db, params.diamond_output_format )
+        ch_versions        = ch_versions.mix( DIAMOND_BLASTX.out.versions.first() )
+        ch_raw_profiles    = ch_raw_profiles.mix( DIAMOND_BLASTX.out.output )
+
+    }
+
+    emit:
+    profiles = ch_raw_profiles    // channel: [ val(meta), [ reads ] ] - should be text files or biom
+    versions = ch_versions          // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/shortread_adapterremoval.nf

@@ -0,0 +1,98 @@
+//
+// Process short raw reads with AdapterRemoval
+//
+
+include { ADAPTERREMOVAL as ADAPTERREMOVAL_SINGLE       } from '../../modules/nf-core/modules/adapterremoval/main'
+include { ADAPTERREMOVAL as ADAPTERREMOVAL_PAIRED       } from '../../modules/nf-core/modules/adapterremoval/main'
+include { CAT_FASTQ                                     } from '../../modules/nf-core/modules/cat/fastq/main'
+
+workflow SHORTREAD_ADAPTERREMOVAL {
+
+    take:
+    reads // [[meta], [reads]]
+
+    main:
+    ch_versions = Channel.empty()
+    ch_multiqc_files      = Channel.empty()
+
+    ch_input_for_adapterremoval = reads
+                                    .branch{
+                                        single: it[0].single_end
+                                        paired: !it[0].single_end
+                                    }
+
+    ADAPTERREMOVAL_SINGLE ( ch_input_for_adapterremoval.single, [] )
+    ADAPTERREMOVAL_PAIRED ( ch_input_for_adapterremoval.paired, [] )
+
+    /*
+     * Due to the ~slightly~ very ugly output implementation of the current AdapterRemoval2 version, each file
+     * has to be exported in a separate channel and we must manually recombine when necessary.
+     */
+
+    if ( params.shortread_clipmerge_mergepairs && !params.shortread_clipmerge_excludeunmerged ) {
+
+        ch_concat_fastq = Channel.empty()
+            .mix(
+                ADAPTERREMOVAL_PAIRED.out.collapsed,
+                ADAPTERREMOVAL_PAIRED.out.collapsed_truncated,
+                ADAPTERREMOVAL_PAIRED.out.singles_truncated,
+                ADAPTERREMOVAL_PAIRED.out.paired_truncated
+            )
+            .map { meta, reads ->
+                def meta_new = meta.clone()
+                meta_new.single_end = true
+                [meta_new, reads]
+            }
+            .groupTuple()
+            // Paired-end reads cause a nested tuple during grouping.
+            // We want to present a flat list of files to `CAT_FASTQ`.
+            .map { meta, fastq -> [meta, fastq.flatten()] }
+
+
+        CAT_FASTQ(ch_concat_fastq)
+
+        ch_adapterremoval_reads_prepped = CAT_FASTQ.out.reads
+            .mix(ADAPTERREMOVAL_SINGLE.out.singles_truncated)
+
+    } else if ( params.shortread_clipmerge_mergepairs && params.shortread_clipmerge_excludeunmerged ) {
+
+        ch_concat_fastq = Channel.empty()
+            .mix(
+                ADAPTERREMOVAL_PAIRED.out.collapsed,
+                ADAPTERREMOVAL_PAIRED.out.collapsed_truncated
+            )
+            .map { meta, reads ->
+                def meta_new = meta.clone()
+                meta_new.single_end = true
+                [meta_new, reads]
+            }
+            .groupTuple()
+            .map { meta, fastq -> [meta, fastq.flatten()] }
+
+
+        CAT_FASTQ(ch_concat_fastq)
+
+        ch_adapterremoval_reads_prepped = CAT_FASTQ.out.reads
+            .mix(ADAPTERREMOVAL_SINGLE.out.singles_truncated)
+
+    } else {
+
+        ch_adapterremoval_reads_prepped = ADAPTERREMOVAL_PAIRED.out.paired_truncated
+            .mix(ADAPTERREMOVAL_SINGLE.out.singles_truncated)
+
+    }
+
+    ch_versions = ch_versions.mix( ADAPTERREMOVAL_SINGLE.out.versions.first() )
+    ch_versions = ch_versions.mix( ADAPTERREMOVAL_PAIRED.out.versions.first() )
+
+    ch_multiqc_files = ch_multiqc_files.mix(
+        ADAPTERREMOVAL_PAIRED.out.settings,
+        ADAPTERREMOVAL_SINGLE.out.settings
+    )
+
+    emit:
+    reads    = ch_adapterremoval_reads_prepped  // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions  // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/shortread_complexityfiltering.nf

@@ -0,0 +1,33 @@
+//
+// Check input samplesheet and get read channels
+//
+
+include { BBMAP_BBDUK     } from '../../modules/nf-core/modules/bbmap/bbduk/main'
+include { PRINSEQPLUSPLUS } from '../../modules/nf-core/modules/prinseqplusplus/main'
+
+workflow SHORTREAD_COMPLEXITYFILTERING {
+    take:
+    reads // [ [ meta ], [ reads ] ]
+
+    main:
+    ch_versions       = Channel.empty()
+    ch_multiqc_files  = Channel.empty()
+
+    // fastp complexity filtering is activated via modules.conf in shortread_preprocessing
+    if ( params.shortread_complexityfilter_tool == 'bbduk' ) {
+        ch_filtered_reads = BBMAP_BBDUK ( reads, [] ).reads
+        ch_versions        =  ch_versions.mix( BBMAP_BBDUK.out.versions.first() )
+        ch_multiqc_files   =  ch_multiqc_files.mix( BBMAP_BBDUK.out.log )
+    } else if ( params.shortread_complexityfilter_tool == 'prinseqplusplus' ) {
+        ch_filtered_reads = PRINSEQPLUSPLUS ( reads ).good_reads
+        ch_versions        =  ch_versions.mix( PRINSEQPLUSPLUS.out.versions.first() )
+    } else {
+        ch_filtered_reads = reads
+    }
+
+    emit:
+    reads    = ch_filtered_reads    // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions          // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/shortread_fastp.nf

@@ -0,0 +1,55 @@
+//
+// Process short raw reads with FastP
+//
+
+include { FASTP as FASTP_SINGLE       } from '../../modules/nf-core/modules/fastp/main'
+include { FASTP as FASTP_PAIRED       } from '../../modules/nf-core/modules/fastp/main'
+
+workflow SHORTREAD_FASTP {
+    take:
+    reads // [[meta], [reads]]
+
+    main:
+    ch_versions           = Channel.empty()
+    ch_multiqc_files      = Channel.empty()
+
+    ch_input_for_fastp = reads
+                            .branch{
+                                single: it[0]['single_end'] == true
+                                paired: it[0]['single_end'] == false
+                            }
+
+    FASTP_SINGLE ( ch_input_for_fastp.single, false, false )
+    // Last parameter here turns on merging of PE data
+    FASTP_PAIRED ( ch_input_for_fastp.paired, false, params.shortread_clipmerge_mergepairs )
+
+    if ( params.shortread_clipmerge_mergepairs ) {
+        ch_fastp_reads_prepped_pe = FASTP_PAIRED.out.reads_merged
+                                        .map {
+                                            meta, reads ->
+                                                def meta_new = meta.clone()
+                                                meta_new['single_end'] = true
+                                                [ meta_new, [ reads ].flatten() ]
+                                        }
+
+        ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )
+
+    } else {
+        ch_fastp_reads_prepped = FASTP_PAIRED.out.reads
+                                    .mix( FASTP_SINGLE.out.reads )
+    }
+
+    ch_versions = ch_versions.mix(FASTP_SINGLE.out.versions.first())
+    ch_versions = ch_versions.mix(FASTP_PAIRED.out.versions.first())
+
+    ch_processed_reads = ch_fastp_reads_prepped
+
+    ch_multiqc_files = ch_multiqc_files.mix( FASTP_SINGLE.out.json )
+    ch_multiqc_files = ch_multiqc_files.mix( FASTP_PAIRED.out.json )
+
+    emit:
+    reads    = ch_processed_reads   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions          // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/shortread_hostremoval.nf

@@ -0,0 +1,34 @@
+//
+// Remove host reads via alignment and export off-target reads
+//
+
+include { BOWTIE2_BUILD             } from '../../modules/nf-core/modules/bowtie2/build/main'
+include { BOWTIE2_ALIGN             } from '../../modules/nf-core/modules/bowtie2/align/main'
+
+workflow SHORTREAD_HOSTREMOVAL {
+    take:
+    reads     // [ [ meta ], [ reads ] ]
+    reference // /path/to/fasta
+    index     // /path/to/index
+
+    main:
+    ch_versions       = Channel.empty()
+    ch_multiqc_files  = Channel.empty()
+
+    if ( !params.shortread_hostremoval_index ) {
+        ch_bowtie2_index = BOWTIE2_BUILD ( reference ).index
+        ch_versions      = ch_versions.mix( BOWTIE2_BUILD.out.versions )
+    } else {
+        ch_bowtie2_index = index.first()
+    }
+
+    BOWTIE2_ALIGN ( reads, ch_bowtie2_index, true )
+    ch_versions      = ch_versions.mix( BOWTIE2_ALIGN.out.versions.first() )
+    ch_multiqc_files = ch_multiqc_files.mix( BOWTIE2_ALIGN.out.log )
+
+    emit:
+    reads    = BOWTIE2_ALIGN.out.fastq   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions               // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

subworkflows/local/shortread_preprocessing.nf

@@ -0,0 +1,39 @@
+//
+// Perform read trimming and merging
+//
+
+
+include { SHORTREAD_FASTP             } from './shortread_fastp'
+include { SHORTREAD_ADAPTERREMOVAL    } from './shortread_adapterremoval'
+include { FASTQC as FASTQC_PROCESSED       } from '../../modules/nf-core/modules/fastqc/main'
+
+workflow SHORTREAD_PREPROCESSING {
+    take:
+    reads //  [ [ meta ], [ reads ] ]
+
+    main:
+    ch_versions       = Channel.empty()
+    ch_multiqc_files  = Channel.empty()
+
+    if ( params.shortread_clipmerge_tool == "fastp" ) {
+        ch_processed_reads = SHORTREAD_FASTP ( reads ).reads
+        ch_versions        =  ch_versions.mix( SHORTREAD_FASTP.out.versions )
+        ch_multiqc_files   =  ch_multiqc_files.mix( SHORTREAD_FASTP.out.mqc )
+    } else if ( params.shortread_clipmerge_tool == "adapterremoval" ) {
+        ch_processed_reads = SHORTREAD_ADAPTERREMOVAL ( reads ).reads
+        ch_versions        = ch_versions.mix( SHORTREAD_ADAPTERREMOVAL.out.versions )
+        ch_multiqc_files   = ch_multiqc_files.mix( SHORTREAD_ADAPTERREMOVAL.out.mqc )
+    } else {
+        ch_processed_reads = reads
+    }
+
+    FASTQC_PROCESSED ( ch_processed_reads )
+    ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
+    ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+
+    emit:
+    reads    = ch_processed_reads   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions          // channel: [ versions.yml ]
+    mqc      = ch_multiqc_files
+}
+

workflows/taxprofiler.nf

@@ -11,11 +11,26 @@ WorkflowTaxprofiler.initialise(params, log)
 
 // TODO nf-core: Add all file path parameters for the pipeline to the list below
 // Check input path parameters to see if they exist
-def checkPathParamList = [ params.input, params.multiqc_config, params.fasta ]
+def checkPathParamList = [ params.input, params.databases, params.hostremoval_reference,
+                            params.shortread_hostremoval_index, params.multiqc_config
+                        ]
 for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
 
 // Check mandatory parameters
-if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' }
+if (params.input    ) { ch_input     = file(params.input)     } else { exit 1, 'Input samplesheet not specified!' }
+if (params.databases) { ch_databases = file(params.databases) } else { exit 1, 'Input database sheet not specified!' }
+
+if (params.shortread_clipmerge_mergepairs && params.run_malt ) log.warn "[nf-core/taxprofiler] MALT does not accept uncollapsed paired-reads. Pairs will be profiled as separate files."
+if (params.shortread_clipmerge_excludeunmerged && !params.shortread_clipmerge_mergepairs) exit 1, "ERROR: [nf-core/taxprofiler] cannot include unmerged reads when merging not turned on. Please specify --shortread_clipmerge_mergepairs"
+
+if (params.shortread_complexityfilter_tool == 'fastp' && ( params.perform_shortread_clipmerge == false || params.shortread_clipmerge_tool != 'fastp' ))  exit 1, "ERROR: [nf-core/taxprofiler] cannot use fastp complexity filtering if preprocessing not turned on and/or tool is not fastp. Please specify --perform_shortread_clipmerge and/or --shortread_clipmerge_tool 'fastp'"
+
+if (params.perform_shortread_hostremoval && !params.hostremoval_reference) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval requested but no --hostremoval_reference FASTA supplied. Check input." }
+if (!params.hostremoval_reference && params.hostremoval_reference_index) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval_index provided but no --hostremoval_reference FASTA supplied. Check input." }
+
+if (params.hostremoval_reference           ) { ch_reference = file(params.hostremoval_reference) }
+if (params.shortread_hostremoval_index     ) { ch_shortread_reference_index = file(params.shortread_hostremoval_index    ) } else { ch_shortread_reference_index = [] }
+if (params.longread_hostremoval_index      ) { ch_longread_reference_index  = file(params.longread_hostremoval_index     ) } else { ch_longread_reference_index  = [] }
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -35,7 +50,15 @@ ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multi
 //
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
 //
-include { INPUT_CHECK } from '../subworkflows/local/input_check'
+include { INPUT_CHECK                   } from '../subworkflows/local/input_check'
+
+include { DB_CHECK                      } from '../subworkflows/local/db_check'
+include { SHORTREAD_PREPROCESSING       } from '../subworkflows/local/shortread_preprocessing'
+include { LONGREAD_PREPROCESSING        } from '../subworkflows/local/longread_preprocessing'
+include { SHORTREAD_HOSTREMOVAL         } from '../subworkflows/local/shortread_hostremoval'
+include { LONGREAD_HOSTREMOVAL          } from '../subworkflows/local/longread_hostremoval'
+include { SHORTREAD_COMPLEXITYFILTERING } from '../subworkflows/local/shortread_complexityfiltering'
+include { PROFILING                     } from '../subworkflows/local/profiling'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -50,6 +73,8 @@ include { FASTQC                      } from '../modules/nf-core/modules/fastqc/
 include { MULTIQC                     } from '../modules/nf-core/modules/multiqc/main'
 include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/modules/custom/dumpsoftwareversions/main'
 
+include { CAT_FASTQ                   } from '../modules/nf-core/modules/cat/fastq/main'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW
@@ -63,29 +88,132 @@ workflow TAXPROFILER {
 
     ch_versions = Channel.empty()
 
-    //
+    /*
-    // SUBWORKFLOW: Read in samplesheet, validate and stage input files
+        SUBWORKFLOW: Read in samplesheet, validate and stage input files
-    //
+    */
     INPUT_CHECK (
         ch_input
     )
     ch_versions = ch_versions.mix(INPUT_CHECK.out.versions)
 
-    //
+    DB_CHECK (
-    // MODULE: Run FastQC
+        ch_databases
-    //
-    FASTQC (
-        INPUT_CHECK.out.reads
     )
+    ch_versions = ch_versions.mix(DB_CHECK.out.versions)
+
+    /*
+        MODULE: Run FastQC
+    */
+    ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore )
+
+    FASTQC (
+        ch_input_for_fastqc
+    )
+
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
+    /*
+        SUBWORKFLOW: PERFORM PREPROCESSING
+    */
+    if ( params.perform_shortread_clipmerge ) {
+        ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq ).reads
+        ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions )
+    } else {
+        ch_shortreads_preprocessed = INPUT_CHECK.out.fastq
+    }
+
+    if ( params.perform_longread_clip ) {
+        ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
+                                        .map { it -> [ it[0], [it[1]] ] }
+        ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions )
+    } else {
+        ch_longreads_preprocessed = INPUT_CHECK.out.nanopore
+    }
+
+    /*
+        SUBWORKFLOW: COMPLEXITY FILTERING
+    */
+
+    // fastp complexity filtering is activated via modules.conf in shortread_preprocessing
+    if ( params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool != 'fastp' ) {
+        ch_shortreads_filtered = SHORTREAD_COMPLEXITYFILTERING ( ch_shortreads_preprocessed ).reads
+        ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
+    } else {
+        ch_shortreads_filtered = ch_shortreads_preprocessed
+    }
+
+    /*
+        SUBWORKFLOW: HOST REMOVAL
+    */
+
+    if ( params.perform_shortread_hostremoval ) {
+        ch_shortreads_hostremoved = SHORTREAD_HOSTREMOVAL ( ch_shortreads_filtered, ch_reference, ch_shortread_reference_index ).reads
+        ch_versions = ch_versions.mix(SHORTREAD_HOSTREMOVAL.out.versions)
+    } else {
+        ch_shortreads_hostremoved = ch_shortreads_filtered
+    }
+
+    if ( params.perform_longread_hostremoval ) {
+        ch_longreads_hostremoved = LONGREAD_HOSTREMOVAL ( ch_longreads_preprocessed, ch_reference, ch_longread_reference_index ).reads
+        ch_versions = ch_versions.mix(LONGREAD_HOSTREMOVAL.out.versions)
+    } else {
+        ch_longreads_hostremoved = ch_longreads_preprocessed
+    }
+
+    if ( params.perform_runmerging ) {
+
+        ch_reads_for_cat_branch = ch_shortreads_hostremoved
+            .mix( ch_longreads_hostremoved )
+            .map {
+                meta, reads ->
+                    def meta_new = meta.clone()
+                    meta_new.remove('run_accession')
+                    [ meta_new, reads ]
+            }
+            .groupTuple()
+            .map {
+                meta, reads ->
+                    [ meta, reads.flatten() ]
+            }
+            .branch {
+                meta, reads ->
+                // we can't concatenate files if there is not a second run, we branch
+                // here to separate them out, and mix back in after for efficiency
+                cat: ( meta.single_end && reads.size() > 1 ) || ( !meta.single_end && reads.size() > 2 )
+                skip: true
+            }
+
+        ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads
+            .mix( ch_reads_for_cat_branch.skip )
+            .map {
+                meta, reads ->
+                [ meta, [ reads ].flatten() ]
+            }
+            .mix( INPUT_CHECK.out.fasta )
+
+        ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
+
+    } else {
+        ch_reads_runmerged = ch_shortreads_hostremoved
+            .mix( ch_longreads_hostremoved, INPUT_CHECK.out.fasta )
+    }
+
+    /*
+        SUBWORKFLOW: PROFILING
+    */
+
+    PROFILING ( ch_reads_runmerged, DB_CHECK.out.dbs )
+    ch_versions = ch_versions.mix( PROFILING.out.versions )
+
+    /*
+        MODULE: MultiQC
+    */
+
     CUSTOM_DUMPSOFTWAREVERSIONS (
         ch_versions.unique().collectFile(name: 'collated_versions.yml')
     )
 
-    //
+
-    // MODULE: MultiQC
-    //
     workflow_summary    = WorkflowTaxprofiler.paramsSummaryMultiqc(workflow, summary_params)
     ch_workflow_summary = Channel.value(workflow_summary)
 
@@ -96,6 +224,25 @@ workflow TAXPROFILER {
     ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
 
+    if (params.perform_shortread_clipmerge) {
+        ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
+    }
+
+    if (params.perform_longread_clip) {
+        ch_multiqc_files = ch_multiqc_files.mix( LONGREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
+    }
+
+    if (params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool != 'fastp'){
+        ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_COMPLEXITYFILTERING.out.mqc.collect{it[1]}.ifEmpty([]) )
+    }
+
+    if (params.perform_shortread_hostremoval) {
+        ch_multiqc_files = ch_multiqc_files.mix(SHORTREAD_HOSTREMOVAL.out.mqc.collect{it[1]}.ifEmpty([]))
+    }
+
+    ch_multiqc_files = ch_multiqc_files.mix( PROFILING.out.mqc )
+
+    // TODO create multiQC module for metaphlan
     MULTIQC (
         ch_multiqc_files.collect()
     )