diff --git a/assets/samplesheet_schema.yaml b/assets/samplesheet_schema.yaml index 88ff451..366ee93 100644 --- a/assets/samplesheet_schema.yaml +++ b/assets/samplesheet_schema.yaml @@ -53,3 +53,5 @@ properties: - fasta required: - samples + - run_accession + - instrument_platform diff --git a/bin/detect_reads.py b/bin/detect_reads.py deleted file mode 100644 index 14f6a07..0000000 --- a/bin/detect_reads.py +++ /dev/null @@ -1,117 +0,0 @@ -#!/usr/bin/env python -import argparse -import csv -import logging -import sys -from enum import Enum -from typing import List, NoReturn, Optional - - -class ColumnNames(str, Enum): - SAMPLE = "sample" - FASTQ_1 = "fastq_1" - FASTQ_2 = "fastq_2" - FASTA = "fasta" - SINGLE_END = "single_end" - - -def parse_args(args: Optional[List[str]] = None) -> argparse.Namespace: - """ - Reformatting is based on detecting whether the reads are paired or single end. - Script appends appropriate column to samplesheet.csv file. - """ - parser = argparse.ArgumentParser( - description="Reformat nf-core/taxprofiler samplesheet file.", - epilog="Example usage: python detect_reads.py ", - ) - parser.add_argument("FILE_IN", help="Input samplesheet file.") - parser.add_argument("FILE_OUT", help="Output file.") - return parser.parse_args(args) - - -class ReadsModifier: - def __init__(self): - self.headers = None - self.sample_index = None - self.fastq_1_index = None - self.fastq_2_index = None - self.fasta_index = None - - def detect_reads_and_reformat(self, input_file_path: str, output_file_path: str) -> NoReturn: - new_file_rows = [] - - with open(input_file_path, "r", newline="") as input_file: - csv_reader = csv.DictReader(input_file, delimiter=",") - self.headers = csv_reader.fieldnames - self.headers.append("single_end") - - for samplesheet_row in csv_reader: - - if self._is_paired_end_short_read(samplesheet_row): - samplesheet_row[ColumnNames.SINGLE_END] = "0" - new_file_rows.append(samplesheet_row.values()) - - elif self._is_single_end_short_long_read(samplesheet_row): - samplesheet_row[ColumnNames.SINGLE_END] = "1" - new_file_rows.append(samplesheet_row.values()) - - elif self._is_single_end_long_read(samplesheet_row): - samplesheet_row[ColumnNames.SINGLE_END] = "1" - new_file_rows.append(samplesheet_row.values()) - - elif self._is_error_row(samplesheet_row): - logging.error( - "FastQ and FastA files cannot be specified together in the same library!", - "Line", - ",".join(samplesheet_row.values()), - ) - else: - logging.error( - "Invalid combination of columns provided!", "Line", ",".join(samplesheet_row.values()) - ) - - ReadsModifier.save_reformatted_samplesheet([self.headers] + new_file_rows, output_file_path) - - def _get_row_values(self, samplesheet_row: dict): - """ - This method extracts data from the columns for given row of samplesheet table. - """ - return ( - samplesheet_row.get(ColumnNames.SAMPLE), - samplesheet_row.get(ColumnNames.FASTQ_1), - samplesheet_row.get(ColumnNames.FASTQ_2), - samplesheet_row.get(ColumnNames.FASTA), - ) - - def _is_paired_end_short_read(self, samplesheet_row: dict) -> bool: - sample, fastq_1, fastq_2, _ = self._get_row_values(samplesheet_row) - return sample and fastq_1 and fastq_2 - - def _is_single_end_short_long_read(self, samplesheet_row: dict) -> bool: - sample, fastq_1, fastq_2, _ = self._get_row_values(samplesheet_row) - return sample and fastq_1 and not fastq_2 - - def _is_single_end_long_read(self, samplesheet_row: dict) -> bool: - sample, fastq_1, fastq_2, fasta = self._get_row_values(samplesheet_row) - return sample and fasta and not fastq_1 and not fastq_2 - - def _is_error_row(self, samplesheet_row: dict) -> bool: - sample, fastq_1, fastq_2, fasta = self._get_row_values(samplesheet_row) - return fasta and (fastq_1 or fastq_2) - - @classmethod - def save_reformatted_samplesheet(cls, new_file_rows: List[List], output_file_path: str) -> NoReturn: - """ - Write new samplesheet. - """ - with open(output_file_path, "w") as output_file: - csv.writer(output_file).writerows(new_file_rows) - - -def main(args=None): - args = parse_args(args) - ReadsModifier().detect_reads_and_reformat(args.FILE_IN, args.FILE_OUT) - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/conf/modules.config b/conf/modules.config index 0efd251..73cc042 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -12,14 +12,6 @@ process { - withName: SAMPLESHEET_CHECK { - publishDir = [ - path: { "${params.outdir}/pipeline_info" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - } - withName: DATABASE_CHECK { publishDir = [ path: { "${params.outdir}/pipeline_info" }, diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index 91e0f04..0000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,27 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$samplesheet" - - conda (params.enable_conda ? "conda-forge::python=3.8.3" : null) - container "${ 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 samplesheet - - output: - path '*.csv' , emit: csv - path "versions.yml", emit: versions - - script: // detect_reads.py script is bundled with the pipeline, in nf-core/taxprofiler/bin/ - """ - python3 $projectDir/bin/detect_reads.py \\ - $samplesheet \\ - samplesheet_validated.csv - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - python: \$(python --version | sed 's/Python //g') - END_VERSIONS - """ -} diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf index 447eb15..e8d5e7a 100644 --- a/subworkflows/local/input_check.nf +++ b/subworkflows/local/input_check.nf @@ -2,7 +2,6 @@ // Check input samplesheet and get read channels // -include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' include { EIDO_VALIDATE } from '../../modules/nf-core/modules/eido/validate/main' include { EIDO_CONVERT } from '../../modules/nf-core/modules/eido/convert/main' @@ -12,26 +11,32 @@ workflow INPUT_CHECK { pep_input_base_dir main: + ch_versions = Channel.empty() + EIDO_VALIDATE ( samplesheet_or_pep_config, file("$projectDir/assets/samplesheet_schema.yaml"), pep_input_base_dir ) - converted_samplesheet = EIDO_CONVERT ( samplesheet_or_pep_config, "csv", pep_input_base_dir ) - parsed_samplesheet = SAMPLESHEET_CHECK ( converted_samplesheet.samplesheet_converted ) - .csv + ch_versions = ch_versions.mix(EIDO_VALIDATE.out.versions) + + EIDO_CONVERT ( samplesheet_or_pep_config, "csv", pep_input_base_dir ) + ch_versions = ch_versions.mix(EIDO_CONVERT.out.versions) + + ch_parsed_samplesheet = EIDO_CONVERT.out.samplesheet_converted .splitCsv ( header:true, sep:',' ) + .map { check_missing_and_singleend_autodetect(it) } .branch { fasta: it['fasta'] != '' nanopore: it['instrument_platform'] == 'OXFORD_NANOPORE' fastq: true } - parsed_samplesheet.fastq + ch_parsed_samplesheet.fastq .map { create_fastq_channel(it) } .set { fastq } - parsed_samplesheet.nanopore + ch_parsed_samplesheet.nanopore .map { create_fastq_channel(it) } .set { nanopore } - parsed_samplesheet.fasta + ch_parsed_samplesheet.fasta .map { create_fasta_channel(it) } .set { fasta } @@ -39,7 +44,20 @@ workflow INPUT_CHECK { 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 ] + versions = ch_versions // channel: [ versions.yml ] +} + +// Function to validate input sheet and auto-detect R1/R2 +def check_missing_and_singleend_autodetect(LinkedHashMap row) { + + // Checks not supported by EIDO(?) + if ( ( row['fastq_1'] != "" || row['fastq_2'] != "" ) && row['fasta'] != "" ) { exit 1, "[nf-core/taxprofiler] ERROR: FastQ and FastA files cannot be specified together in the same library. Check input samplesheet! Check sample: ${row['sample']}" } + if ( row['fastq_1'] == "" && row['fastq_2'] != "" ) { exit 1, "[nf-core/taxprofiler] ERROR: Input samplesheet has a missing fastq_1 when fastq_2 is specified. Check sample: ${row['sample']}" } + + single_end = row['fastq_2'] == "" ? true : false + row['single_end'] = single_end + + return row } // Function to get list of [ meta, [ fastq_1, fastq_2 ] ] @@ -69,11 +87,12 @@ def create_fastq_channel(LinkedHashMap row) { if (!file(row.fastq_2).exists()) { exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${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 = [:]