From 54dacb9a7c2414eddb53701c778202126442fb22 Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Thu, 17 Oct 2024 16:13:05 +0200
Subject: [PATCH 1/9] Change email fields to coherent with AViTi data
Ref: #114
---
assets/begin_template.txt | 2 +-
assets/final_email_template.txt | 2 +-
conf/functions.config | 4 ++--
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/assets/begin_template.txt b/assets/begin_template.txt
index 69415f3..719c716 100644
--- a/assets/begin_template.txt
+++ b/assets/begin_template.txt
@@ -1,7 +1,7 @@
----------------------------------------------------------------------------------
==================================================
------------------------------- get-nf workflow ----------------------------
- I L L U M I N A - N F P I P E L I N E
+ S H O R T R E A D S - N F P I P E L I N E
V$version
==================================================
----------------------------------------------------------------------------------
diff --git a/assets/final_email_template.txt b/assets/final_email_template.txt
index f31632f..1edfcc2 100644
--- a/assets/final_email_template.txt
+++ b/assets/final_email_template.txt
@@ -1,7 +1,7 @@
----------------------------------------------------------------------------------
==================================================
------------------------------- get-nf workflow ----------------------------
- I L L U M I N A - N F P I P E L I N E
+ S H O R T R E A D S - N F P I P E L I N E
V$version
==================================================
----------------------------------------------------------------------------------
diff --git a/conf/functions.config b/conf/functions.config
index 7c8b722..67f0543 100644
--- a/conf/functions.config
+++ b/conf/functions.config
@@ -103,7 +103,7 @@ def sendBeginMail(formatted_date) {
def pipeline_project = pipeline_info[1]
def pipeline_techno = pipeline_project.split('-')[1]
- def begin_subject = "[" + pipeline_techno + "] [" + pipeline_group + "] " + params.inputdir.split('/')[-1]
+ def begin_subject = "[" + params.sequencer + "] [" + pipeline_group + "] " + params.inputdir.split('/')[-1]
def begin_email_fields = [:]
begin_email_fields['version'] = workflow.manifest.version
begin_email_fields['wfRunName'] = workflow.runName
@@ -140,7 +140,7 @@ def sendFinalMail(formatted_date, summary) {
def pipeline_project = pipeline_info[1]
def pipeline_techno = pipeline_project.split('-')[1]
- def subject = "[" + pipeline_techno + "] [" + pipeline_group + "] " + params.inputdir.split('/')[-1]
+ def subject = "[" + params.sequencer + "] [" + pipeline_group + "] " + params.inputdir.split('/')[-1]
if (workflow.success) {
subject += " : Successful"
} else {
--
GitLab
From 9e2e7ba05b903e988d49b173d96d45099d9278c4 Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Thu, 17 Oct 2024 16:14:43 +0200
Subject: [PATCH 2/9] Resource factor are now correct in cas of simplex
sequencing
And deals with subset with AViTi data
Ref: #113
---
nextflow.config | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/nextflow.config b/nextflow.config
index 1a5d1b7..a736cab 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -31,6 +31,7 @@ params {
large_sampling_threshold = 200 // 200 samples run is high multiplexed
miseq_subset_seq = "50000" // in reads must be a string
nova_subset_seq = "50000000" // in reads
+ aviti_subset_seq = "50000000" // in reads
large_indexing_nova_subset_seq = "500000" // in reads
coverage = 0 // coverage in X
len_r1 = 150
@@ -112,7 +113,8 @@ def n_read_files = Files.walk(Paths.get(params.inputdir.toString()), 3)
// on retire les 2 fichiers undetermined
def n_samples = ( n_read_files - 2 ) / 2
System.out.println "\nNombre d'échantillons trouvés sur cette lane : $n_samples"
-params.resource_factor = java.lang.Math.round(0.1 * n_samples)
+def factor = java.lang.Math.round(0.1 * n_samples)
+params.resource_factor = factor > 1 ? factor : 1
import java.text.SimpleDateFormat
SimpleDateFormat uniqueness_format = new SimpleDateFormat("yyyyMMddHHmmss")
@@ -125,12 +127,15 @@ params {
outdir = inputdir + "/nextflow/" + run_name + "/" + outdir_prefix + "_" + nf_uniqueness
subset_seq = miseq_subset_seq
- if ( sequencer =~ /NovaSeq.*/ ) {
+ if ( sequencer =~ /NovaSeq.*/ || sequencer =~ /AVITI.*/ ) {
if ( n_samples >= large_sampling_threshold ) {
nova_subset_seq = large_indexing_nova_subset_seq
}
subset_seq = nova_subset_seq
}
+ if ( DTM_mode ) {
+ subset_seq = "1000000000"
+ }
}
// ========================================
--
GitLab
From 83d0333bd4d11fefbc50bc2b968930976a74961c Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Thu, 17 Oct 2024 16:19:22 +0200
Subject: [PATCH 3/9] Detect Amplicon data_nature
---
workflow/short_reads_qc.nf | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/workflow/short_reads_qc.nf b/workflow/short_reads_qc.nf
index f393c3d..79115bb 100644
--- a/workflow/short_reads_qc.nf
+++ b/workflow/short_reads_qc.nf
@@ -182,7 +182,7 @@ workflow SHORT_READS_QC {
)
ch_versions = ch_versions.mix(RNA_QC.out.versions)
- } else if (params.data_nature =~ "16S|Amplicon|METAGENOMIC|METATRANSCRIPTOMIC") {
+ } else if (params.data_nature =~ "16S|AMPLICON|METAGENOMIC|METATRANSCRIPTOMIC") {
DIVERSITY_QC(fastq
.collect{it[1]}
.flatten()
--
GitLab
From 9872e44f1e3075c3364f81046c3ffd0810139ee3 Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Fri, 18 Oct 2024 13:57:58 +0200
Subject: [PATCH 4/9] AllOther Undetermined sequences have the rigth amount
Ref: #115
---
bin/demuxStatsFromXML.R | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/bin/demuxStatsFromXML.R b/bin/demuxStatsFromXML.R
index 3c5c1ff..b526179 100755
--- a/bin/demuxStatsFromXML.R
+++ b/bin/demuxStatsFromXML.R
@@ -178,7 +178,7 @@ tabDemuxSum<-read.table(opt$demuxSum, skip=linesToSkip, col.names=c("Index", "Co
tabUndetermined<-tabDemuxSum[which(tabDemuxSum$Count >= bcCount.threshold),]
-cat("\tRésumé des inforamtions extraites :\n")
+cat("\tRésumé des informations extraites :\n")
cat(paste0("\tNombre d'index indéterminés retrouvés :\t", dim(tabUndetermined)[1], "\n"))
if(nrow(tabUndetermined) > 0) { head(tabUndetermined) }
@@ -194,7 +194,6 @@ if (dim(tabUndetermined)[1] != 0) {
df.tabUndetermined.tmp<-data.frame("default", "Undetermined", tabUndetermined[i, "Index"], tabUndetermined[i, "Count"], NA, NA)
df.tabUndetermined<-concat_df(df.tabUndetermined, df.tabUndetermined.tmp, vec.names)
}
-
df2<-concat_df(df2, df.tabUndetermined, vec.names)
cat("\tLes index indéterminés ont été ajouté au data.table.\n")
} else {
@@ -207,7 +206,7 @@ cat("\nQuelques calculs sur les données avant de les exporter.\n")
cat("\tActualisation du nombre d'index 'AllOthers'.\n")
undertermined.count<-sum(as.numeric(tabUndetermined[,"Count"]))
df2[which(df2$Barcode == "unknown"), "bcCount"]<-as.numeric(df2[which(df2$Barcode == "unknown"), "bcCount"])-undertermined.count
-
+df2[which(df2$Barcode == "unknown"), "bcPerfect"]<-0 # C'est la somme de tous les undermined récupéré depuis le XML
# Calcul pourcentages de chaque barcode
cat("\tCalcul du pourcentage sur le nombre de fragments total.\n")
totalOfFragments<-sum(as.numeric(df2$bcCount))
--
GitLab
From 04fca066a7f41a6702c7cdca05a74da005284e7d Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Fri, 18 Oct 2024 14:02:43 +0200
Subject: [PATCH 5/9] Emit versions channels in DNA module
Ref: #116
---
modules/local/module_dna.nf | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/modules/local/module_dna.nf b/modules/local/module_dna.nf
index 66fc4e2..7355e77 100644
--- a/modules/local/module_dna.nf
+++ b/modules/local/module_dna.nf
@@ -13,7 +13,7 @@ process BWA_ALIGNMENT {
output:
tuple val(sample), path("*.log"), emit: log
tuple val(sample), path("*.sam"), emit: sam
- path("versions.yml"), versions
+ path("versions.yml"), emit: versions
script:
def reference = params.reference_genome ?: params.reference_transcriptome
@@ -38,7 +38,7 @@ process SAMTOOLS_VIEW {
output:
tuple val(sample), path("*.bam"), emit: bam
- path("versions.yml"), versions
+ path("versions.yml"), emit: versions
script:
def analyse_type = task.ext.analyse_type ?: params.default_label
@@ -63,7 +63,7 @@ process SAMTOOLS_SORT {
output:
tuple val(sample), path("*.log"), emit: log
tuple val(sample), path("*.bam"), emit: bam
- path("versions.yml"), versions
+ path("versions.yml"), emit: versions
//path("*.bam"), emit: bam
script: // Pourquoi unmerged ??? https://forgemia.inra.fr/genotoul-bioinfo/ng6/-/blob/master/workflows/components/bwa.py#L97
@@ -89,7 +89,7 @@ process SAMTOOLS_FLAGSTATS {
output:
tuple val(sample), path("*.log"), emit: log
tuple val(sample), path("*.txt"), emit: txt
- path("versions.yml"), versions
+ path("versions.yml"), emit: versions
script:
def analyse_type = task.ext.analyse_type ?: params.default_label
--
GitLab
From 6465b1cba0890d39c75dc23c185e7e68df616b88 Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Fri, 18 Oct 2024 14:56:34 +0200
Subject: [PATCH 6/9] elembio demultiplexStat run correctly
Ref: #112
---
bin/demuxStatsElement.R | 16 +++++++++-------
modules/local/module_core_element.nf | 2 +-
2 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/bin/demuxStatsElement.R b/bin/demuxStatsElement.R
index 7e25e17..c622209 100755
--- a/bin/demuxStatsElement.R
+++ b/bin/demuxStatsElement.R
@@ -60,7 +60,7 @@ unassigned <- opt$unassigned
runManifestJson <- opt$runManifest
lane <- opt$lane
threshold <- opt$threshold
-demultiplexStat <- paste0(launchDir,"/demultiplexStat.csv")
+demultiplexStat <- paste0(launchDir,"/demultiplexStat_", lane,".csv")
demultiplex_stat <- data.frame(
Project = character(),
Sample = character(),
@@ -88,8 +88,7 @@ for (i in 1:nrow(assigned_filtered)) {
sample <- assigned_filtered[i, 2]
bc1 <- assigned_filtered[i, 3]
bc2 <- assigned_filtered[i, 4]
- bcCount <- assigned_filtered[i, 5]
- perc <- assigned_filtered[i, 6]
+ bcCount <- assigned_filtered[i, 5]*2
project <- run_manifest$Samples %>%
filter(SampleName == sample) %>%
@@ -100,7 +99,7 @@ for (i in 1:nrow(assigned_filtered)) {
Sample = sample,
Barcode = paste(bc1, bc2, sep = "-"),
bcCount = bcCount,
- percOfFrag = perc,
+ percOfFrag = NA,
stringsAsFactors = FALSE
)
@@ -118,8 +117,7 @@ for (i in 1:nrow(unassigned_filtered)) {
sample <- "Undetermined"
bc1 <- unassigned_filtered[i, 1]
bc2 <- unassigned_filtered[i, 2]
- bcCount <- unassigned_filtered[i, 4]
- perc <- unassigned_filtered[i, 3]
+ bcCount <- unassigned_filtered[i, 4]*2
project <- "DefaultProject"
@@ -128,7 +126,7 @@ for (i in 1:nrow(unassigned_filtered)) {
Sample = sample,
Barcode = paste(bc1, bc2, sep = "-"),
bcCount = bcCount,
- percOfFrag = perc,
+ percOfFrag = NA,
stringsAsFactors = FALSE
)
@@ -138,6 +136,10 @@ for (i in 1:nrow(unassigned_filtered)) {
}
cat("\n")
+# Calcul perfOfFrag
+totalFrag <- sum(demultiplex_stat$bcCount)
+demultiplex_stat$percOfFrag <- (100 * demultiplex_stat$bcCount) / totalFrag
+
# Filtrer les lignes selon le seuil de bcCount
initial_nrow <- nrow(demultiplex_stat)
demultiplex_stat <- demultiplex_stat %>%
diff --git a/modules/local/module_core_element.nf b/modules/local/module_core_element.nf
index c1e26a2..a8ff5da 100644
--- a/modules/local/module_core_element.nf
+++ b/modules/local/module_core_element.nf
@@ -12,7 +12,7 @@ process DEMUX_STATS {
path unassigned
output:
- path "demultiplexStat.csv", emit: csv
+ path "demultiplexStat_*.csv", emit: csv
script:
def threshold = task.ext.threshold ?: ''
--
GitLab
From 6f02b72898668665c08e7f4d95bee9513237b98e Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Mon, 21 Oct 2024 14:44:24 +0200
Subject: [PATCH 7/9] Move every NGL process into new subworkflow
- Better ergonomy
- Better readability of procvess names
Ref: #117
---
conf/base.config | 8 ++-
sub-workflows/local/core_element.nf | 21 ++-----
sub-workflows/local/core_illumina.nf | 12 ----
sub-workflows/local/ngl.nf | 82 ++++++++++++++++++++++++++++
workflow/short_reads_qc.nf | 73 ++++++++++++-------------
5 files changed, 128 insertions(+), 68 deletions(-)
create mode 100644 sub-workflows/local/ngl.nf
diff --git a/conf/base.config b/conf/base.config
index 965385f..49d7135 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -255,6 +255,12 @@ process {
// SHARED MODULES
//=========================================
process {
+ withName: CREATE_ANALYSIS {
+ def techno = params.sequencer =~ "MiSeq|NovaSeq" ? 'illumina' : params.sequencer =~ "AVITI" ? 'elembio' : 'other'
+ ext.args = "--techno $techno "
+ ext.args += params.project_hash ? "--projectDir '${params.project}-${params.project_hash}'" : ''
+ }
+
withName: CREATE_READSETS {
ext.args = [
params.run_name ? "--poolName '${params.run_name}'" : '',
@@ -262,7 +268,7 @@ process {
].join(' ')
}
- withName: TREATMENT_DEMUX_RUN {
+ withName: ILLUMINA_TREATMENT_DEMUX_RUN {
ext.args = [
"--lane '${params.lane}'",
].join(' ')
diff --git a/sub-workflows/local/core_element.nf b/sub-workflows/local/core_element.nf
index 6207685..9cb970d 100644
--- a/sub-workflows/local/core_element.nf
+++ b/sub-workflows/local/core_element.nf
@@ -12,11 +12,6 @@ include {
DEMUX_STATS
} from "$baseDir/modules/local/module_core_element.nf"
-include {
- TREATMENT_DEMUXSTAT_ELEMENT as TREATMENT_DEMUX_RUN;
- TREATMENT_DEMUXSTAT_ELEMENT as TREATMENT_DEMUX_READSETS;
-} from "$baseDir/modules/local/module_NGL-Bi.nf"
-
// -------------------------------------------------
// LOCAL PARAMS
// -------------------------------------------------
@@ -27,21 +22,15 @@ include {
// -------------------------------------------------
workflow CORE_ELEMENT {
- take:
- runManifestJson
- assigned
- unassigned
- nglBiRunCode
- readsetsFile
+ take:
+ runManifestJson
+ assigned
+ unassigned
main:
// ----------- DemultiplexStat
DEMUX_STATS(runManifestJson, assigned, unassigned)
- // ----------- NGL-Bi
- TREATMENT_DEMUX_RUN(nglBiRunCode, DEMUX_STATS.out.csv)
- TREATMENT_DEMUX_READSETS(readsetsFile, DEMUX_STATS.out.csv)
-
- emit:
+ emit:
demuxStat = DEMUX_STATS.out.csv
}
\ No newline at end of file
diff --git a/sub-workflows/local/core_illumina.nf b/sub-workflows/local/core_illumina.nf
index bb1c476..4fd8542 100644
--- a/sub-workflows/local/core_illumina.nf
+++ b/sub-workflows/local/core_illumina.nf
@@ -15,10 +15,6 @@ include {
ILLUMINA_FILTER;
} from "$baseDir/modules/local/module_core.nf"
-include {
- TREATMENT_DEMUXSTAT_ILLUMINA as TREATMENT_DEMUX_RUN;
- TREATMENT_DEMUXSTAT_ILLUMINA as TREATMENT_DEMUX_READSETS;
-} from "$baseDir/modules/local/module_NGL-Bi.nf"
// -------------------------------------------------
// LOCAL PARAMS
@@ -35,8 +31,6 @@ workflow CORE_ILLUMINA {
demuxStatXML
demuxSummary
fastq
- nglBiRunCode
- readsetsFile
main:
ch_versions = Channel.empty()
@@ -55,12 +49,6 @@ workflow CORE_ILLUMINA {
ch_versions = ch_versions.mix(ILLUMINA_FILTER.out.versions)
}
- if (params.insert_to_ngl){
- // Add demultiplexStat treatments
- TREATMENT_DEMUX_RUN(nglBiRunCode, DEMUX_STATS.out.demultiplexStatsTSV, params.lane)
- TREATMENT_DEMUX_READSETS(readsetsFile, DEMUX_STATS.out.demultiplexStatsTSV, '')
- }
-
emit:
fastq = fastq_good
demuxStat = DEMUX_STATS.out.demultiplexStatsTSV
diff --git a/sub-workflows/local/ngl.nf b/sub-workflows/local/ngl.nf
new file mode 100644
index 0000000..d5102d5
--- /dev/null
+++ b/sub-workflows/local/ngl.nf
@@ -0,0 +1,82 @@
+// -------------------------------------------------
+// NGL
+// -------------------------------------------------
+/*
+ * Tout process en lien avec NGL (Bi ou SQ)
+ *
+ *
+*/
+
+// -------------------------------------------------
+// MODULES
+// -------------------------------------------------
+include { BEGIN_NGLBI as BEGIN } from "${params.shared_modules}/workflows/begin_nglbi.nf"
+include { COPY_TO_SAVE } from "${params.shared_modules}/workflows/copy_to_save.nf"
+include { MD5SUM as MD5SUM_FASTQ;
+ md5sum as MD5SUM_INDEX } from "${params.shared_modules}/md5sum.nf"
+include { READSET_FILE_FROM_FILE as ADD_RS_INDEX_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'INDEX')
+include { READSET_FILE_FROM_FILE as ADD_RS_RAW_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'RAW')
+include { UPDATE_NGLBI_STATE_FROM_FILE as UPDATE_STATE_FQC;
+ CREATE_ANALYSIS } from "${params.shared_modules}/ngl_bi.nf"
+
+include { FILE_RENAME as RENAME_FASTQ;
+ FILE_RENAME as RENAME_INDEX } from "$baseDir/modules/local/module_NGL-Bi.nf"
+// -------------------------------------------------
+// WORKFLOW
+// -------------------------------------------------
+workflow NGL {
+ take:
+ sequencer_name
+ run_name
+ bi_run_code
+ sq_xp_code
+ fastq
+ index_files
+ multiqc_html
+ project
+ project_hash
+ is_single_cell
+
+ main:
+ // First steps
+ BEGIN(bi_run_code, sq_xp_code, '', sequencer_name)
+
+ nglBiRunCode = BEGIN.out.nglBiRunCode
+ readsets_created = BEGIN.out.readsets_created
+ ready = BEGIN.out.ready
+
+ bi_run_code = nglBiRunCode.collect().map { it.toString() }
+
+ // Compute results
+ if (is_single_cell) {
+ RENAME_INDEX(index_files.map{it[1]}.collect(), readsets_created, sq_xp_code, 'fastq_index')
+ MD5SUM_INDEX(RENAME_INDEX.out.fastq.collect(), run_name+'_fastq_index')
+ ADD_RS_INDEX_FILES(readsets_created, MD5SUM_INDEX.out, 'INDEX', ready)
+ }
+
+ RENAME_FASTQ(fastq.map{it[1]}.collect(), readsets_created, sq_xp_code, 'fastq_read')
+ fq = RENAME_FASTQ.out.fastq
+ .flatMap()
+ .map { it -> [[type: 'fastq', barcode:run_name], it]}
+
+ MD5SUM_FASTQ(fq.groupTuple())
+
+ ADD_RS_RAW_FILES(readsets_created, MD5SUM_FASTQ.out.md5sum.map{it -> it[1]}, 'RAW', ready)
+ UPDATE_STATE_FQC(readsets_created, 'F-QC', multiqc_html)
+ techno = sequencer_name =~ "MiSeq|NovaSeq" ? 'illumina' : sequencer_name =~ "AVITI" ? 'elembio' : 'other'
+ COPY_TO_SAVE(
+ nglBiRunCode,
+ readsets_created,
+ multiqc_html.map{it -> [[type:'report'], it]},
+ project,
+ project_hash,
+ fq,
+ MD5SUM_FASTQ.out.md5sum,
+ techno
+ )
+
+ emit:
+ run_code = BEGIN.out.nglBiRunCode?: Channel.empty()
+ readsets_file = BEGIN.out.readsets_created?: Channel.empty()
+ ready = BEGIN.out.ready?: Channel.empty()
+}
\ No newline at end of file
diff --git a/workflow/short_reads_qc.nf b/workflow/short_reads_qc.nf
index 79115bb..db97c09 100644
--- a/workflow/short_reads_qc.nf
+++ b/workflow/short_reads_qc.nf
@@ -97,6 +97,11 @@ include { DNA_QC } from "$baseDir/sub-workflows/local/dna_qc.nf"
include { RNA_QC } from "$baseDir/sub-workflows/local/rna_qc.nf"
include { DIVERSITY_QC } from "$baseDir/sub-workflows/local/diversity_qc.nf"
include { PARSE_REPORTS } from "$baseDir/modules/local/module_DTM.nf"
+include { TREATMENT_DEMUXSTAT_ILLUMINA as ILLUMINA_TREATMENT_DEMUX_RUN;
+ TREATMENT_DEMUXSTAT_ILLUMINA as ILLUMINA_TREATMENT_DEMUX_READSETS;
+ // TREATMENT_DEMUXSTAT_ELEMENT as ELEMBIO_TREATMENT_DEMUX_RUN;
+ // TREATMENT_DEMUXSTAT_ELEMENT as ELEMBIO_TREATMENT_DEMUX_READSETS;
+ } from "$baseDir/modules/local/module_NGL-Bi.nf"
include { FILE_RENAME as RENAME_FASTQ;
FILE_RENAME as RENAME_INDEX;
} from "$baseDir/modules/local/module_NGL-Bi.nf"
@@ -107,11 +112,13 @@ include { UPDATE_NGLBI_STATE_FROM_FILE as UPDATE_STATE_FQC;
CREATE_ANALYSIS; } from "${params.shared_modules}/ngl_bi.nf"
include { READSET_FILE_FROM_FILE as ADD_RS_INDEX_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'INDEX')
include { READSET_FILE_FROM_FILE as ADD_RS_RAW_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'RAW')
-include { md5sum as MD5SUM_FASTQ;
+include { MD5SUM as MD5SUM_FASTQ;
md5sum as MD5SUM_INDEX;
} from "${params.shared_modules}/md5sum.nf"
include { BEGIN_NGLBI as NGLBI } from "${params.shared_modules}/workflows/begin_nglbi.nf"
+include { COPY_TO_SAVE } from "${params.shared_modules}/workflows/copy_to_save.nf"
include { TREATMENT_MULTIQC as ADD_MULTIQC } from "${params.shared_modules}/ngl_bi_treatments.nf"
+include { NGL } from "$baseDir/sub-workflows/local/ngl.nf"
// -------------------------------------------------
// EMAIL ON START
@@ -129,26 +136,20 @@ workflow SHORT_READS_QC {
WORKFLOW_SUMMARY()
- if (params.insert_to_ngl){
- NGLBI(params.bi_run_code, params.sq_xp_code, '', params.sequencer)
- nglBiRunCode = NGLBI.out.nglBiRunCode
- readsets_created = NGLBI.out.readsets_created
- ready = NGLBI.out.ready
- } else {
- nglBiRunCode = Channel.empty()
- readsets_created = Channel.empty()
- ready = Channel.empty()
- }
-
if (! params.skip_core_illumina && params.sequencer =~ "NovaSeq|MiSeq" ) {
- CORE_ILLUMINA(ch_ss, ch_DemuxStatXML, ch_DemuxSummary, ch_read, nglBiRunCode, readsets_created)
+ CORE_ILLUMINA(ch_ss, ch_DemuxStatXML, ch_DemuxSummary, ch_read)
fastq = CORE_ILLUMINA.out.fastq
ch_versions = ch_versions.mix(CORE_ILLUMINA.out.versions)
+ illumina_demux_stats = CORE_ILLUMINA.out.demuxStat
} else {
fastq = ch_read
+ illumina_demux_stats = channel.empty()
}
if (! params.skip_core_element && params.sequencer =~ "AVITI") {
- CORE_ELEMENT(ch_runManifestJSON, ch_indexAssigned, ch_indexUnassigned, nglBiRunCode, readsets_created)
+ CORE_ELEMENT(ch_runManifestJSON, ch_indexAssigned, ch_indexUnassigned)
+ elembio_demux_stats = CORE_ELEMENT.out.demuxStat
+ } else {
+ elembio_demux_stats = Channel.empty()
}
CORE(fastq)
@@ -220,32 +221,26 @@ workflow SHORT_READS_QC {
)
if (params.insert_to_ngl){
- if (params.single_cell) {
- RENAME_INDEX(ch_index.map{it[1]}.collect(), readsets_created, params.sq_xp_code, 'fastq_index')
- MD5SUM_INDEX(RENAME_INDEX.out.fastq.collect(), params.run_name+'_fastq_index')
- ADD_RS_INDEX_FILES(readsets_created, MD5SUM_INDEX.out, 'INDEX', ready)
- }
- RENAME_FASTQ(fastq.map{it[1]}.collect(), readsets_created, params.sq_xp_code, 'fastq_read')
- MD5SUM_FASTQ(RENAME_FASTQ.out.fastq.collect(), params.run_name+'_fastq_read')
- ADD_RS_RAW_FILES(readsets_created, MD5SUM_FASTQ.out, 'RAW', ready)
- UPDATE_STATE_FQC(readsets_created, 'F-QC', MULTIQC.out.html)
- CREATE_ANALYSIS(nglBiRunCode, readsets_created, 1)
- ADD_MULTIQC(CREATE_ANALYSIS.out.createdFile, MULTIQC.out.html, CREATE_ANALYSIS.out.ready)
- }
-
- /*
- if overlap, alors :
- diversity_qc sub-workflow
-
- else :
- if DNA, alors :
- dna_qc sub-worflow
- if RNA, alors :
- rna_qc sub-workflow
- if Methyl, alors :
- methyl_qc sub-worflow
- */
+ NGL(
+ params.sequencer,
+ params.run_name,
+ params.bi_run_code,
+ params.sq_xp_code,
+ fastq,
+ ch_index,
+ MULTIQC.out.html,
+ params.project,
+ params.project_hash,
+ params.single_cell
+ )
+ // Add demultiplexStat treatments
+ ILLUMINA_TREATMENT_DEMUX_RUN(NGL.out.run_code, illumina_demux_stats, params.lane)
+ ILLUMINA_TREATMENT_DEMUX_READSETS(NGL.out.readsets_file, illumina_demux_stats, '')
+
+ // ELEMBIO_TREATMENT_DEMUX_RUN(NGL.out.run_code, elembio_demux_stats)
+ // ELEMBIO_TREATMENT_DEMUX_READSETS(NGL.out.readsets_file, elembio_demux_stats)
+ }
}
// -------------------------------------------------
--
GitLab
From 0f17db5d97a198cc54a7a362dd5fab02f885ee84 Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Mon, 21 Oct 2024 14:49:57 +0200
Subject: [PATCH 8/9] Remove old includes related with NGL
Ref: #117
---
workflow/short_reads_qc.nf | 16 ++--------------
1 file changed, 2 insertions(+), 14 deletions(-)
diff --git a/workflow/short_reads_qc.nf b/workflow/short_reads_qc.nf
index db97c09..5031ac2 100644
--- a/workflow/short_reads_qc.nf
+++ b/workflow/short_reads_qc.nf
@@ -97,28 +97,16 @@ include { DNA_QC } from "$baseDir/sub-workflows/local/dna_qc.nf"
include { RNA_QC } from "$baseDir/sub-workflows/local/rna_qc.nf"
include { DIVERSITY_QC } from "$baseDir/sub-workflows/local/diversity_qc.nf"
include { PARSE_REPORTS } from "$baseDir/modules/local/module_DTM.nf"
+include { NGL } from "$baseDir/sub-workflows/local/ngl.nf"
include { TREATMENT_DEMUXSTAT_ILLUMINA as ILLUMINA_TREATMENT_DEMUX_RUN;
TREATMENT_DEMUXSTAT_ILLUMINA as ILLUMINA_TREATMENT_DEMUX_READSETS;
// TREATMENT_DEMUXSTAT_ELEMENT as ELEMBIO_TREATMENT_DEMUX_RUN;
// TREATMENT_DEMUXSTAT_ELEMENT as ELEMBIO_TREATMENT_DEMUX_READSETS;
} from "$baseDir/modules/local/module_NGL-Bi.nf"
-include { FILE_RENAME as RENAME_FASTQ;
- FILE_RENAME as RENAME_INDEX;
- } from "$baseDir/modules/local/module_NGL-Bi.nf"
include { MULTIQC } from "${params.shared_modules}/multiqc.nf"
include { GCBIAS as GC_BIAS } from "${params.shared_modules}/gcbias.nf"
include { workflow_summary as WORKFLOW_SUMMARY } from "${params.shared_modules}/workflow_summary.nf"
-include { UPDATE_NGLBI_STATE_FROM_FILE as UPDATE_STATE_FQC;
- CREATE_ANALYSIS; } from "${params.shared_modules}/ngl_bi.nf"
-include { READSET_FILE_FROM_FILE as ADD_RS_INDEX_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'INDEX')
-include { READSET_FILE_FROM_FILE as ADD_RS_RAW_FILES } from "${params.shared_modules}/ngl_bi.nf" addParams(ext: 'RAW')
-include { MD5SUM as MD5SUM_FASTQ;
- md5sum as MD5SUM_INDEX;
- } from "${params.shared_modules}/md5sum.nf"
-include { BEGIN_NGLBI as NGLBI } from "${params.shared_modules}/workflows/begin_nglbi.nf"
-include { COPY_TO_SAVE } from "${params.shared_modules}/workflows/copy_to_save.nf"
-include { TREATMENT_MULTIQC as ADD_MULTIQC } from "${params.shared_modules}/ngl_bi_treatments.nf"
-include { NGL } from "$baseDir/sub-workflows/local/ngl.nf"
+
// -------------------------------------------------
// EMAIL ON START
--
GitLab
From 1b435c29dd7426882dea6afc5ba5a2a9bf6b114b Mon Sep 17 00:00:00 2001
From: jsabban <jules.sabban@inrae.fr>
Date: Mon, 21 Oct 2024 14:51:42 +0200
Subject: [PATCH 9/9] Update manifest version
---
conf/report.config | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/conf/report.config b/conf/report.config
index 5ee8982..e84365d 100644
--- a/conf/report.config
+++ b/conf/report.config
@@ -29,5 +29,5 @@ manifest {
description = "Workflow for Illumina data quality control"
mainScript = 'main.nf'
nextflowVersion = '>=0.32.0'
- version = '1.23.0'
+ version = '1.24.0'
}
\ No newline at end of file
--
GitLab