diff --git a/docs/output.md b/docs/output.md
index be681bd..4ffad3f 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -33,6 +33,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
- [MALT](#malt) - Sequence alignment and analysis tool designed for processing high-throughput sequencing data, especially in the context of metagenomics
- [MetaPhlAn3](#metaphlan3) - Genome-level marker gene based taxonomic classifier
- [mOTUs](#motus) - Tool for marker gene-based OTU (mOTU) profiling.
+- [TAXPASTA](#taxpasta) - Tool to standardise taxonomic profiles as well as merge profiles across samples for the same classifier/profiler.
- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
- [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
@@ -435,6 +436,29 @@ Krona charts will be generated by the pipeline for supported tools (Kraken2, Cen
The resulting HTML files can be loaded into your web browser for exploration. Each file will have a dropdown to allow you to switch between each sample aligned against the given database of the tool.
+### TAXPASTA
+
+[TAXPASTA](https://github.com/taxprofiler/taxpasta) is a python package added as a module in nf-core/taxprofiler that can standardise and merge two or more taxonomic profiles across samples into one single table..
+
+
+Output files
+
+- `taxpasta`
+ - `.*.{tsv,csv,arrow,parquet,biom}`: A list of taxonomic profiler output files. The standard format is the `tsv`. The first column describes the taxonomy ID and the rest of the columns describe the read counts for each sample.
+
+
+The following report files are used for the taxpasta step:
+
+- Bracken: `_.tsv`
+- Centrifuge: `.centrifuge.txt`
+- Diamond: ``
+- Kaiju: `_.kaijutable.txt`
+- KrakenUniq: `_.report.txt`
+- Kraken2: `_.report.txt`
+- MALT: `.txt.gz`
+- MetaPhlAn3: `_profile.txt`
+- mOTUs: `.out`
+
### MultiQC
diff --git a/modules.json b/modules.json
index 9b87f43..5b07b07 100644
--- a/modules.json
+++ b/modules.json
@@ -8,301 +8,217 @@
"adapterremoval": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"bbmap/bbduk": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"bowtie2/align": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"bowtie2/build": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"bracken/bracken": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"bracken/combinebrackenoutputs": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"cat/fastq": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"centrifuge/centrifuge": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"centrifuge/kreport": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"custom/dumpsoftwareversions": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"diamond/blastx": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"falco": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ],
+ "installed_by": ["modules"],
"patch": "modules/nf-core/falco/falco.diff"
},
"fastp": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"fastqc": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"filtlong": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"gunzip": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"kaiju/kaiju": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"kaiju/kaiju2krona": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"kaiju/kaiju2table": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"kraken2/kraken2": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"krakentools/combinekreports": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"krakentools/kreport2krona": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"krakenuniq/preloadedkrakenuniq": {
"branch": "master",
"git_sha": "a6eb17f65b3ee5761c25c075a6166c9f76733cee",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"krona/ktimporttaxonomy": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"krona/ktimporttext": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"malt/run": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"megan/rma2info": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"metaphlan3/mergemetaphlantables": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"metaphlan3/metaphlan3": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"minimap2/align": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"minimap2/index": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"motus/merge": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"motus/profile": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"multiqc": {
"branch": "master",
"git_sha": "ee80d14721e76e2e079103b8dcd5d57129e584ba",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"porechop/porechop": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ],
+ "installed_by": ["modules"],
"patch": "modules/nf-core/porechop/porechop/porechop-porechop.diff"
},
"prinseqplusplus": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"samtools/bam2fq": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"samtools/index": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"samtools/stats": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"samtools/view": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"taxpasta/merge": {
"branch": "master",
"git_sha": "74ab450ed05e034d049c00f6e2853de2c31594b4",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
},
"untar": {
"branch": "master",
"git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",
- "installed_by": [
- "modules"
- ]
+ "installed_by": ["modules"]
}
}
}
}
}
-}
\ No newline at end of file
+}
diff --git a/nextflow_schema.json b/nextflow_schema.json
index a84a232..b17094f 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -509,6 +509,21 @@
"fa_icon": "fas fa-folder-open",
"description": "Specify path to krona taxonomy directories (required for MALT krona plots)",
"help_text": "Specify a path to a Krona taxonomy database directory (i.e. a directory containing a krona generated `.tab` file).\n\nThis is only required for generating Krona plots of MALT output.\n\nNote this taxonomy database must be downloaded and generated with the `updateTaxonomy.sh` script from the krona-tools package."
+ },
+ "taxpasta_add_taxonomy": {
+ "type": "boolean",
+ "description": "The path to a directory containing taxdump files.",
+ "help_text": "At least nodes.dmp and names.dmp are required. A merged.dmp file is optional."
+ },
+ "taxpasta_add_samplesheet": {
+ "type": "boolean",
+ "description": "A table with with two columns, one for the sample and one for the taxonomic profile.",
+ "help_text": "If this option is provided, any arguments are ignored."
+ },
+ "taxpasta_standardisation_format": {
+ "type": "string",
+ "default": "tsv",
+ "description": "The desired output format."
}
},
"fa_icon": "fas fa-chart-line"
@@ -767,19 +782,5 @@
{
"$ref": "#/definitions/reference_genome_options"
}
- ],
- "properties": {
- "add_taxonomy": {
- "type": "string",
- "default": "false"
- },
- "add_samplesheet": {
- "type": "string",
- "default": "false"
- },
- "standardisation_taxpasta_format": {
- "type": "string",
- "default": "tsv"
- }
- }
+ ]
}