millironx/taxprofiler
1
0
Fork 0
mirror of https://github.com/MillironX/taxprofiler.git synced 2024-09-21 05:22:04 +00:00
Code Issues Releases Packages Activity

Merge pull request #24 from genomic-medicine-sweden/add_nanopore

Browse source 
Add nanopore reads input
This commit is contained in:
James A. Fellows Yates 2022-03-18 13:29:13 +01:00 committed by GitHub
commit 45428c2877
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 24 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
bin/check_samplesheet.py
View file

@ -173,7 +173,7 @@ def check_samplesheet(file_in, file_out):
## 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 reads
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

10
docs/usage.md
View file

@ -44,11 +44,11 @@ TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz,
TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz,
```
| 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 (`_`). |
| `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". |
| `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". |
| 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 (`_`). |
| `fastq_1` | Full path to FastQ file for Illumina short reads 1 or Nanopore reads. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". |
| `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". |
An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.

22
subworkflows/local/input_check.nf
View file

@ -15,14 +15,20 @@ workflow INPUT_CHECK {
.dump(tag: "input_split_csv_out")
.branch {
fasta: it['fasta'] != ''
nanopore: it['instrument_platform'] == 'OXFORD_NANOPORE'
fastq: true
}
parsed_samplesheet.fastq
.map { create_fastq_channels(it) }
.map { create_fastq_channel(it) }
.dump(tag: "fastq_channel_init")
.set { fastq }
parsed_samplesheet.nanopore
.map { create_fastq_channel(it) }
.dump(tag: "fastq_nanopore_channel_init")
.set { nanopore }
parsed_samplesheet.fasta
.map { create_fasta_channels(it) }
.dump(tag: "fasta_channel_init")
@ -30,6 +36,7 @@ workflow INPUT_CHECK {
emit:
fastq // channel: [ val(meta), [ reads ] ]
nanopore // channel: [ val(meta), [ reads ] ]
fasta // channel: [ val(meta), fasta ]
versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ]
}
@ -51,10 +58,17 @@ def create_fastq_channel(LinkedHashMap row) {
if (meta.single_end) {
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${row.fastq_2}"
if (meta.instrument_platform == 'OXFORD_NANOPORE') {
if (row.fastq_2 != '') {
exit 1, "ERROR: Please check input samplesheet -> For Oxford Nanopore reads Read 2 FastQ should be empty!\n${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
}