diff --git a/assets/fastq_screen.conf_example b/assets/fastq_screen.conf_example
index 78180aedd6af036d755ac20046b302818472966e..dbbb7bcb7c49f4053af9020f13f4d0f4feb80ec9 100644
--- a/assets/fastq_screen.conf_example
+++ b/assets/fastq_screen.conf_example
@@ -10,7 +10,7 @@
#BOWTIE /usr/local/bin/bowtie/bowtie
#BOWTIE2 /usr/local/bioinfo/src/bowtie/bowtie2-2.4.4-linux-x86_64/bowtie2
-BWA /usr/local/bioinfo/src/bwa/bwa-0.7.15/bwa
+BWA /usr/local/bioinfo/src/bwa/bwa-0.7.17/bwa
############################################
## Bismark (for bisulfite sequencing only) #
diff --git a/bin/DTM/make_bedgraph.sh b/bin/DTM/make_bedgraph.sh
index 1eab8918d443762ca0ffb71ce6a68d5b2e160ed8..099a9ad322eb502b80247aae5aeeb8c0c5a76445 100644
--- a/bin/DTM/make_bedgraph.sh
+++ b/bin/DTM/make_bedgraph.sh
@@ -21,10 +21,8 @@ I_NAMES=$2 # path to chrom_names file
R_PATTERN=$3 # chr pattern to remove from bedgraph file
#### MODULES ####
-module load bioinfo/samtools-1.16.1
-module load bioinfo/bedtools-2.27.1
-
-
+module load bioinfo/samtools/1.18
+module load bioinfo/bedtools/2.27.1
replace_chr_names() {
# replace chr names
@@ -82,7 +80,7 @@ remove_unwanted_scaffold(){
main() {
- BAM=$(find $I_DIR -type f -name '*R1*unmerged.bam' -execdir basename '{}' ';'|sed -n ${SLURM_ARRAY_TASK_ID}p)
+ BAM=$(find $I_DIR -type f -name '*unmerged.bam' -execdir basename '{}' ';'|sed -n ${SLURM_ARRAY_TASK_ID}p)
echo -e "Traitement de ${BAM}"
BAM_PATH="${I_DIR}/${BAM}"
@@ -97,4 +95,4 @@ main() {
remove_unwanted_scaffold
}
-main
\ No newline at end of file
+main
diff --git a/bin/parse_reports.sh b/bin/parse_reports.sh
index 03d309de371f6980accac9e5b61572a116b936a0..24042e7079964afd9f849f1b3d05745ff0902b3c 100755
--- a/bin/parse_reports.sh
+++ b/bin/parse_reports.sh
@@ -17,7 +17,7 @@ MEAN_COV=$(sed -n 's/mean coverageData.*= \(.*X\)/\1/p' $QUALIMAP_REPORT | sed '
ALIGN=$(sed -n 's/number of mapped reads =.*(\(.*%\))/\1/p' $QUALIMAP_REPORT | sed 's/ //g')
AT_DROPOUT=$(grep '^ACCUMULATION_LEVEL' -A 1 $GCBIAS_REPORT | cut -d$'\t' -f6 | tail -1)
-GC_DROPOUT=$(grep '^ACCUMULATION_LEVEL' -A 1 $GCBIAS_REPORT | cut -d$'\t' -f6 | tail -1)
+GC_DROPOUT=$(grep '^ACCUMULATION_LEVEL' -A 1 $GCBIAS_REPORT | cut -d$'\t' -f7 | tail -1)
## Write stat file
echo "duplication_rate: $DUPLI" >> $O_STAT
diff --git a/conf/base.config b/conf/base.config
index 0060fd2aebdffc2d7c90fcbcf6e8445fa3616b19..e62053e612fca82da9fad3df50e811bb8be279dd 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -105,6 +105,7 @@ process {
module = toolsModuleHash['FASTQC']
maxRetries = 4
+ cpus = { checkMax( 2 * task.attempt, 'cpus' ) }
time = { checkMax( 5.h * task.attempt * params.resource_factor, 'time' ) }
}
@@ -338,7 +339,7 @@ process {
withName: SORTMERNA {
module = toolsModuleHash['SORTMERNA']
- memory = { checkMax( 2.GB * task.attempt, 'memory' ) }
+ memory = { checkMax( 10.GB * task.attempt * params.resource_factor, 'memory' ) }
time = { checkMax( 10.h * task.attempt, 'time' ) }
cpus = { checkMax( 1 * task.attempt, 'cpus' ) }
@@ -361,7 +362,7 @@ process {
withName: QUALIMAP {
module = toolsModuleHash['QUALIMAP']
cpus = { checkMax( 8 * task.attempt, 'cpus' ) }
- memory = { checkMax( 8.GB * task.attempt, 'memory' ) }
+ memory = { checkMax( 30.GB * task.attempt * params.resource_factor, 'memory' ) }
time = { checkMax( 3.h * task.attempt, 'time' ) }
publishDir = [
diff --git a/conf/dependencies_genobioinfo.config b/conf/dependencies_genobioinfo.config
index de6c332aef3e2b19a2e61c7f2acfe861b754cf28..b715b7a99798c50ea7d6d49776c65603a14b6ffd 100644
--- a/conf/dependencies_genobioinfo.config
+++ b/conf/dependencies_genobioinfo.config
@@ -7,7 +7,7 @@ toolsModuleHash['FASTP'] = ['bioinfo/fastp/0.23.2']
toolsModuleHash['FASTQC'] = ['bioinfo/FastQC/0.12.1'] // version upgraded face to genologin
toolsModuleHash['FASTQSCREEN'] = ['bioinfo/FastQScreen/0.15.3']
toolsModuleHash['R'] = ['statistics/R/4.3.0']
-toolsModuleHash['PICARD'] = ['devel/java/17.0.6', 'bioinfo/picard-tools/3.0.0'] // a vérifier pour R miniconda!!
+toolsModuleHash['PICARD'] = ['statistics/R/4.3.0', 'devel/java/17.0.6', 'bioinfo/picard-tools/3.0.0'] // a vérifier pour R miniconda!!
// ----- RNA ----- //
toolsModuleHash['SALMON'] = ['bioinfo/Salmon/1.10.0'] // version upgraded face to genologin
diff --git a/conf/report.config b/conf/report.config
index 520c00b48c85a8f167893b1a3ced4251eb5036a6..c9f0e97a82711a599e74e370de57db8aa2c811a8 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 = '1.10.0'
+ version = '1.15.0'
}
\ No newline at end of file
diff --git a/conf/test.config b/conf/test.config
index 39d54d62bcb2453f425e2480d3a0a791c9c53690..b8095b6487b0aa61cb6c8fb971619f8801c52e6f 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -4,7 +4,7 @@
System.out.println "Profil dev => on ajuste les paramètres..."
params {
ngl_bi_client = '/home/sbsuser/work/test/jules/VisualStudioSources/ngl-bi_client/'
- shared_modules = '/home/sbsuser/work/Nextflow/shared_modules/ExportSources_Jules/'
+ shared_modules = '/save/user/sbsuser/scripts-ngs/shared_modules_Current/'
is_dev_mode = true
}
diff --git a/modules/local/module_rna.nf b/modules/local/module_rna.nf
index 2cf07ecff83b6a52dd24d57121d859001463907c..2563adfe9f7f58dc704ac1ea8613a1d3fc83f811 100644
--- a/modules/local/module_rna.nf
+++ b/modules/local/module_rna.nf
@@ -91,6 +91,7 @@ process STAR_ALIGN {
output:
tuple val(sample), path("${sample}_Log.final.out"), emit: results
tuple val(sample), path("${sample}_Log.out"), emit: log
+ tuple val(sample), path("${sample}_Aligned.out.sam"), emit: sam
script:
def args = task.ext.args ?: ''
diff --git a/nextflow.config b/nextflow.config
index 4627edbf8205e964a7f2a7c635c5eaa868a9fc5b..a823a406f1e3567a265a33aeffd1c47af7364d86 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -38,12 +38,6 @@ params {
make_star_index = false
reference_transcriptome = ""
sortmerna_db_path = '/usr/local/bioinfo/src/SortMeRNA/sortmerna-2.1b/rRNA_databases'
- sortmerna_bac_16s = sortmerna_db_path + '/silva-bac-16s-id90.fasta'
- sortmerna_bac_23s = sortmerna_db_path + '/silva-bac-23s-id98.fasta'
- sortmerna_arc_16s = sortmerna_db_path + '/silva-arc-16s-id95.fasta'
- sortmerna_arc_23s = sortmerna_db_path + '/silva-arc-23s-id98.fasta'
- sortmerna_euk_18s = sortmerna_db_path + '/silva-euk-18s-id95.fasta'
- sortmerna_euk_28s = sortmerna_db_path + '/silva-euk-28s-id98.fasta'
// Amplicon / 16S params
min_overlap = 20
@@ -114,7 +108,7 @@ params {
samplesheet = inputdir.toString() + "/SampleSheet.csv"
nf_uniqueness = uniqueness_format.format(new Date())
outdir_prefix = outdir_prefix ?: project + "_" + run_name
- outdir = inputdir + "/nextflow/" + outdir_prefix + "_" + nf_uniqueness
+ outdir = inputdir + "/nextflow/" + run_name + "/" + outdir_prefix + "_" + nf_uniqueness
subset_seq = miseq_subset_seq
if ( sequencer =~ /NovaSeq.*/ ) {
diff --git a/sub-workflows/local/core_pipeline.nf b/sub-workflows/local/core_pipeline.nf
index 73c5fd873fcd737108ff37ced9eb34b08033f10f..eb171419713f8799c17a9d70a460f443c4b3d9a4 100644
--- a/sub-workflows/local/core_pipeline.nf
+++ b/sub-workflows/local/core_pipeline.nf
@@ -72,7 +72,7 @@ workflow CORE {
DUPLICATED_READS(unzipped_fastq
.collect{it[1]}
.flatten()
- .map { $it -> [ ($it.simpleName =~ /(.*)_R[1-2]_.*/)[0][1] , $it ] }
+ .map { $it -> [ ($it.simpleName =~ /(.*)_R[1-2].*/)[0][1] , $it ] }
.groupTuple()
) // need fastq paired !!!
diff --git a/sub-workflows/local/rna_qc.nf b/sub-workflows/local/rna_qc.nf
index c7afbaa2173856ff7f1cc0a8a50fb5b56d34cbba..2c32b0b42f75cb7e71dce35148747b3e348a72b5 100644
--- a/sub-workflows/local/rna_qc.nf
+++ b/sub-workflows/local/rna_qc.nf
@@ -11,7 +11,7 @@
* QC des données ARN :
* - Alignement contre génome de référence avec STAR
* - Pseudo alignement contre transcriptome de référence avec SALMON
- * - Rapport d'alignement avec Qualimap ??
+ * - Rapport d'alignement avec Qualimap
*/
// -------------------------------------------------
@@ -22,7 +22,11 @@ include { STAR_INDEX;
SALMON_INDEX;
SALMON_QUANT;
} from "$baseDir/modules/local/module_rna.nf"
-
+include { SAMTOOLS_VIEW;
+ SAMTOOLS_SORT;
+ SAMTOOLS_FLAGSTATS;
+} from "$baseDir/modules/local/module_dna.nf"
+include { QUALIMAP } from "${params.shared_modules}/qualimap.nf"
include { SAMTOOLS_FAIDX } from "${params.shared_modules}/samtools.nf"
include { SORTMERNA } from "${params.shared_modules}/sortmerna.nf"
// -------------------------------------------------
@@ -34,7 +38,7 @@ workflow RNA_QC {
sortmerna_db
main:
- fastq = fastq.collect{it[1]}.flatten().map { $it -> [ ($it.simpleName =~ /(.*)_R[1-2]_.*/)[0][1] , $it ] }.groupTuple()
+ fastq = fastq.collect{it[1]}.flatten().map { $it -> [ ($it.simpleName =~ /(.*)_R[1-2].*/)[0][1] , $it ] }.groupTuple()
align_results = Channel.empty()
if ( "$params.reference_genome" != '' ) {
@@ -47,7 +51,12 @@ workflow RNA_QC {
} else {
star_index = Channel.from(file(params.reference_genome).getParent())
}
- align_results = STAR_ALIGN(fastq, star_index).results // R1 et R2 en même temps
+ STAR_ALIGN(fastq, star_index).results // R1 et R2 en même temps
+ align_results = STAR_ALIGN.out.results
+ SAMTOOLS_VIEW(STAR_ALIGN.out.sam)
+ SAMTOOLS_SORT(SAMTOOLS_VIEW.out.bam)
+ SAMTOOLS_FLAGSTATS(SAMTOOLS_VIEW.out.bam)
+ qualimap_report_emitted = QUALIMAP(SAMTOOLS_SORT.out.bam).report
} else if ("$params.reference_transcriptome" != '') {
// if indexFiles does not exist
@@ -75,6 +84,7 @@ workflow RNA_QC {
salmon_index,
ch_lib_type
).results
+ qualimap_report_emitted= Channel.empty()
} else {
// If Qualimap and Samtools were not executed
@@ -88,5 +98,6 @@ workflow RNA_QC {
emit:
align_results = align_results
sortmerna_log = SORTMERNA.out.log
+ qualimap_report = qualimap_report_emitted
//flagstats_output = flagstats_output_emitted
}
\ No newline at end of file
diff --git a/workflow/illumina_qc.nf b/workflow/illumina_qc.nf
index 9b17503f6ef00485e758588b9dbe1d8fb54a9a53..a3525002faf027541b3876d36b38abb0db3564a5 100644
--- a/workflow/illumina_qc.nf
+++ b/workflow/illumina_qc.nf
@@ -44,12 +44,12 @@ ch_read=Channel
// Channel of rRNA databases for sortmerna
ch_sortmerna_db = Channel.from(
- params.sortmerna_euk_18s,
- params.sortmerna_euk_28s,
- params.sortmerna_bac_16s,
- params.sortmerna_bac_23s,
- params.sortmerna_arc_16s,
- params.sortmerna_arc_23s
+ params.sortmerna_db_path + '/silva-bac-16s-id90.fasta',
+ params.sortmerna_db_path + '/silva-bac-23s-id98.fasta',
+ params.sortmerna_db_path + '/silva-arc-16s-id95.fasta',
+ params.sortmerna_db_path + '/silva-arc-23s-id98.fasta',
+ params.sortmerna_db_path + '/silva-euk-18s-id95.fasta',
+ params.sortmerna_db_path + '/silva-euk-28s-id98.fasta',
)
mismatchNumber = params.sequencer == 'MiSeq'? 0 : 1
@@ -130,7 +130,8 @@ workflow ILLUMINA_QC {
RNA_QC(CORE.out.subset_fastq, ch_sortmerna_db)
ch_mqc = ch_mqc.mix(
RNA_QC.out.align_results.collect{it[1]}.ifEmpty([]),
- RNA_QC.out.sortmerna_log.collect{it[1]}.ifEmpty([])
+ RNA_QC.out.sortmerna_log.collect{it[1]}.ifEmpty([]),
+ RNA_QC.out.qualimap_report.collect{it[1]}.ifEmpty([]),
)
} else if (params.data_nature =~ "16S|Amplicon") {
@@ -188,7 +189,7 @@ workflow.onComplete {
end_mail_sent = sendFinalMail(format.format(new Date()), params.summary)
// remove work directory if pipeline is successful
- if (workflow.success && (!params.is_dev_mode || !params.DTM_mode)) {
+ if (workflow.success && !( params.is_dev_mode || params.DTM_mode)) {
println "Pipeline terminé avec succès => suppression du workdir : $workflow.workDir"
exec:
workflow.workDir.deleteDir()