1
0
Fork 0
mirror of https://github.com/MillironX/taxprofiler.git synced 2024-11-25 16:59:54 +00:00

refactor: change parameter exclude unmerged to include

This commit is contained in:
Moritz E. Beber 2022-12-01 17:25:25 +01:00
parent 7992edd181
commit 4529e7e545
7 changed files with 11 additions and 11 deletions

View file

@ -28,10 +28,10 @@ jobs:
- "--perform_longread_qc false" - "--perform_longread_qc false"
- "--perform_shortread_qc false" - "--perform_shortread_qc false"
- "--shortread_qc_tool fastp" - "--shortread_qc_tool fastp"
- "--shortread_qc_tool fastp --shortread_qc_mergepairs --shortread_qc_excludeunmerged" - "--shortread_qc_tool fastp --shortread_qc_mergepairs --shortread_qc_includeunmerged"
- "--shortread_qc_tool fastp --shortread_qc_mergepairs" - "--shortread_qc_tool fastp --shortread_qc_mergepairs"
- "--shortread_qc_tool adapterremoval" - "--shortread_qc_tool adapterremoval"
- "--shortread_qc_tool adapterremoval --shortread_qc_mergepairs --shortread_qc_excludeunmerged" - "--shortread_qc_tool adapterremoval --shortread_qc_mergepairs --shortread_qc_includeunmerged"
- "--shortread_qc_tool adapterremoval --shortread_qc_mergepairs" - "--shortread_qc_tool adapterremoval --shortread_qc_mergepairs"
- "--shortread_complexityfilter_tool bbduk" - "--shortread_complexityfilter_tool bbduk"
- "--shortread_complexityfilter_tool prinseqplusplus" - "--shortread_complexityfilter_tool prinseqplusplus"

View file

@ -79,7 +79,7 @@ process {
withName: FASTP_PAIRED { withName: FASTP_PAIRED {
ext.args = [ ext.args = [
// collapsing options - option to retain singletons // collapsing options - option to retain singletons
params.shortread_qc_excludeunmerged ? '' : "--include_unmerged", params.shortread_qc_includeunmerged ? '--include_unmerged' : '',
// trimming options // trimming options
params.shortread_qc_skipadaptertrim ? "--disable_adapter_trimming" : "", params.shortread_qc_skipadaptertrim ? "--disable_adapter_trimming" : "",
params.shortread_qc_adapterlist ? "" : params.shortread_qc_adapter1 ? "--adapter_sequence ${params.shortread_qc_adapter1}" : "", params.shortread_qc_adapterlist ? "" : params.shortread_qc_adapter1 ? "--adapter_sequence ${params.shortread_qc_adapter1}" : "",

View file

@ -204,7 +204,7 @@ It is highly recommended to run this on raw reads to remove artifacts from seque
There are currently two options for short-read preprocessing: `fastp` or `adapterremoval`. 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_qc_adapter1` and `--shortread_qc_adapter2`) For adapter clipping, you can either rely on tool default adapter sequences, or supply your own adapters (`--shortread_qc_adapter1` and `--shortread_qc_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_qc_mergepairs` and `--shortread_qc_excludeunmerged`). 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 include unmerged reads in the reads sent for profiling (`--shortread_qc_mergepairs` and `--shortread_qc_includeunmerged`).
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_qc_skipadaptertrim`). 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_qc_skipadaptertrim`).
Both tools support length filtering of reads and can be tuned with `--shortread_qc_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. Both tools support length filtering of reads and can be tuned with `--shortread_qc_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.

View file

@ -66,7 +66,7 @@ params {
shortread_qc_tool = 'fastp' shortread_qc_tool = 'fastp'
shortread_qc_skipadaptertrim = false shortread_qc_skipadaptertrim = false
shortread_qc_mergepairs = true shortread_qc_mergepairs = true
shortread_qc_excludeunmerged = false shortread_qc_includeunmerged = false
shortread_qc_adapter1 = null shortread_qc_adapter1 = null
shortread_qc_adapter2 = null shortread_qc_adapter2 = null
shortread_qc_adapterlist = null shortread_qc_adapterlist = null

View file

@ -125,11 +125,11 @@
"default": true, "default": true,
"help_text": "Turn on the merging of read-pairs of paired-end short read sequencing data for AdapterRemoval (this is performed automatically with fastp).\n\n> Modifies tool parameter(s):\n> - AdapterRemoval: `--collapse`\n" "help_text": "Turn on the merging of read-pairs of paired-end short read sequencing data for AdapterRemoval (this is performed automatically with fastp).\n\n> Modifies tool parameter(s):\n> - AdapterRemoval: `--collapse`\n"
}, },
"shortread_qc_excludeunmerged": { "shortread_qc_includeunmerged": {
"type": "boolean", "type": "boolean",
"fa_icon": "far fa-times-circle", "fa_icon": "far fa-times-circle",
"description": "Discard unmerged reads from paired-end merging", "description": "Include unmerged reads from paired-end merging in the downstream processing",
"help_text": "Turns off the inclusion of unmerged reads in resulting processing FASTQ file of paired-end sequencing data when using `fastp`.\n\nThis can be useful in cases where you prefer to have very short reads (e.g. aDNA), thus excluding longer-reads or possibly faulty reads where one of the pair was discarded.\n\n> Modifies tool parameter(s):\n> - removed from reads `--include_unmerged`\n" "help_text": "Turns on the inclusion of unmerged reads in resulting processing FASTQ file of paired-end sequencing data when using `fastp`.\n\nExcluding unmerged reads can be useful in cases where you prefer to have very short reads (e.g. aDNA), thus excluding longer-reads or possibly faulty reads where one of the pair was discarded.\n\n> Modifies tool parameter(s):\n> - adds option `--include_unmerged`\n"
}, },
"shortread_qc_minlength": { "shortread_qc_minlength": {
"type": "integer", "type": "integer",

View file

@ -30,7 +30,7 @@ workflow SHORTREAD_ADAPTERREMOVAL {
* has to be exported in a separate channel and we must manually recombine when necessary. * has to be exported in a separate channel and we must manually recombine when necessary.
*/ */
if ( params.shortread_qc_mergepairs && !params.shortread_qc_excludeunmerged ) { if ( params.shortread_qc_mergepairs && params.shortread_qc_includeunmerged ) {
ch_concat_fastq = Channel.empty() ch_concat_fastq = Channel.empty()
.mix( .mix(
@ -55,7 +55,7 @@ workflow SHORTREAD_ADAPTERREMOVAL {
ch_adapterremoval_reads_prepped = CAT_FASTQ.out.reads ch_adapterremoval_reads_prepped = CAT_FASTQ.out.reads
.mix(ADAPTERREMOVAL_SINGLE.out.singles_truncated) .mix(ADAPTERREMOVAL_SINGLE.out.singles_truncated)
} else if ( params.shortread_qc_mergepairs && params.shortread_qc_excludeunmerged ) { } else if ( params.shortread_qc_mergepairs && !params.shortread_qc_includeunmerged ) {
ch_concat_fastq = Channel.empty() ch_concat_fastq = Channel.empty()
.mix( .mix(

View file

@ -28,7 +28,7 @@ if ( params.input ) {
if (params.databases) { ch_databases = file(params.databases) } else { exit 1, 'Input database sheet not specified!' } if (params.databases) { ch_databases = file(params.databases) } else { exit 1, 'Input database sheet not specified!' }
if (params.shortread_qc_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_qc_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_qc_excludeunmerged && !params.shortread_qc_mergepairs) exit 1, "ERROR: [nf-core/taxprofiler] cannot include unmerged reads when merging not turned on. Please specify --shortread_qc_mergepairs" if (params.shortread_qc_includeunmerged && !params.shortread_qc_mergepairs) exit 1, "ERROR: [nf-core/taxprofiler] cannot include unmerged reads when merging is not turned on. Please specify --shortread_qc_mergepairs"
if (params.shortread_complexityfilter_tool == 'fastp' && ( params.perform_shortread_qc == false || params.shortread_qc_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_qc and/or --shortread_qc_tool 'fastp'" if (params.shortread_complexityfilter_tool == 'fastp' && ( params.perform_shortread_qc == false || params.shortread_qc_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_qc and/or --shortread_qc_tool 'fastp'"