diff --git a/main.nf b/main.nf
index 83bc9b30dd93b2cfddfd9f8ce81e2bc370187692..353959c9796cc12cf655f4007adbe4f4d7444622 100644
--- a/main.nf
+++ b/main.nf
@@ -3,7 +3,11 @@
include { prepare_genome_files } from './subworkflows/prepare_genome_files.nf'
include { prepare_annotation_files } from './subworkflows/prepare_annotation_files.nf'
-include { copyFilesForTracking } from './modules/copyFilesForTracking.nf'
+include { copyFilesForTracking as copySpeciesFiles } from './modules/copyFilesForTracking.nf'
+include { copyFilesForTracking as copyAnnotationFiles } from './modules/copyFilesForTracking.nf'
+include { copyFilesForTracking as copyTranscriptomicFiles } from './modules/copyFilesForTracking.nf'
+include { copyFilesForTracking as copyQtlFiles } from './modules/copyFilesForTracking.nf'
+include { copyFilesForTracking as copySpeciesInfoFiles } from './modules/copyFilesForTracking.nf'
include { getGeneFamilies } from './modules/getGeneFamilies.nf'
include { getGenomeInfo } from './modules/getGenomeInfo.nf'
include { getGeneToRnaEdges } from './modules/getGeneToRnaEdges.nf'
@@ -97,38 +101,84 @@ workflow {
}
.set { annotation_ch }
- if(!params.transcriptomic_files) {
- error("please specify --transcriptomic_files option")
+ copySpeciesFiles(Channel.fromPath(params.species_files, checkIfExists: false).map { tuple('species', it) })
+ copyAnnotationFiles(Channel.fromPath(params.annotation_files, checkIfExists: false).map { tuple('annotation', it) })
+
+
+ if(params.transcriptomic_files ) {
+ transcriptomic_f_ch = Channel
+ .fromPath(params.transcriptomic_files, checkIfExists: false)
+ .splitCsv(header:true, sep:"\t", strip:true)
+ .map { row -> tuple(row.ID, row.status, file(row.bioinfo_protocol), file(row.dataset), file(row.counts), file(row.tpm), file(row.metadata), file(row.samples_annotation)) }
+ .set { transcriptomics_ch }
+
+ getTranscriptomicCounts(transcriptomics_ch)
+
+ merge_results(getTranscriptomicCounts.out.bioinfo_protocol, subdir = '')
+ merge_results(getTranscriptomicCounts.out.dataset, subdir = '')
+ merge_results(getTranscriptomicCounts.out.condition, subdir = '')
+ merge_results(getTranscriptomicCounts.out.free_term, subdir = '')
+ merge_results(getTranscriptomicCounts.out.sample, subdir = '')
+ merge_results(getTranscriptomicCounts.out.dataset_bioinfo_protocol, subdir = '')
+ merge_results(getTranscriptomicCounts.out.condition_dataset, subdir = '')
+ merge_results(getTranscriptomicCounts.out.sample_condition, subdir = '')
+ merge_results(getTranscriptomicCounts.out.gene_sample, subdir = '')
+ merge_results(getTranscriptomicCounts.out.gene_condition, subdir = '')
+ merge_results(getTranscriptomicCounts.out.condition_onto, subdir = params.merged_subdir)
+ merge_results(getTranscriptomicCounts.out.condition_free_term, subdir = '')
+
+ copyTranscriptomicFiles(Channel.fromPath(params.transcriptomic_files, checkIfExists: false).map { tuple('transcriptomic', it) })
+
+
+
}
- transcriptomic_f_ch = Channel
- .fromPath(params.transcriptomic_files, checkIfExists: false)
- if(!params.qtl_files) {
- error("please specify --qtl_files option")
+ if(params.qtl_files) {
+ qtl_f_ch = Channel
+ .fromPath(params.qtl_files, checkIfExists: false)
+ .splitCsv(header:true, sep:"\t", strip:true)
+ .map { row -> tuple(row.ID, row.status, row.species, file(row.dataset), file(row.qtl), file(row.qtl_annotation)) }
+ .set { qtl_ch }
+
+ qtl_ch
+ .map { tuple( it[2], *it ) }
+ .combine( samples_ch.gff3, by: 0 )
+ .combine( samples_ch.chr_conv, by: 0 )
+ .map { it[1..-1] }
+ .set { qtl_genome_ch }
+
+
+ getQTLInfo(qtl_genome_ch)
+
+ merge_results(getQTLInfo.out.qtl, subdir = '')
+ merge_results(getQTLInfo.out.dataset, subdir = '')
+ merge_results(getQTLInfo.out.population, subdir = '')
+ merge_results(getQTLInfo.out.site, subdir = '')
+ merge_results(getQTLInfo.out.year, subdir = '')
+ merge_results(getQTLInfo.out.free_term, subdir = '')
+ merge_results(getQTLInfo.out.gene_qtl, subdir = '')
+ merge_results(getQTLInfo.out.qtl_chromosome, subdir = '')
+ merge_results(getQTLInfo.out.qtl_dataset, subdir = '')
+ merge_results(getQTLInfo.out.qtl_population, subdir = '')
+ merge_results(getQTLInfo.out.qtl_site, subdir = '')
+ merge_results(getQTLInfo.out.qtl_year, subdir = '')
+ merge_results(getQTLInfo.out.qtl_onto, subdir = params.merged_subdir)
+ merge_results(getQTLInfo.out.qtl_free_term, subdir = '')
+
+ copyQtlFiles(Channel.fromPath(params.qtl_files, checkIfExists: false).map { tuple('qtl', it) })
+
}
- qtl_f_ch = Channel
- .fromPath(params.qtl_files, checkIfExists: false)
- // copy input files to results directory
- copyFilesForTracking(Channel.fromPath(params.species_files, checkIfExists: false),
- Channel.fromPath(params.annotation_files, checkIfExists: false),
- transcriptomic_f_ch, qtl_f_ch, sp_info_ch)
+
- //-------------------------------------------------//
- // Prepare inputs //
- //-------------------------------------------------//
+ // copy input files to results directory
+ copySpeciesInfoFiles(Channel.fromPath(params.species_info, checkIfExists: false).map { tuple('species_info', it) })
- // transcriptomic files
- transcriptomic_f_ch
- .splitCsv(header:true, sep:"\t", strip:true)
- .map { row -> tuple(row.ID, row.status, file(row.bioinfo_protocol), file(row.dataset), file(row.counts), file(row.tpm), file(row.metadata), file(row.samples_annotation)) }
- .set { transcriptomics_ch }
+ //copyFilesForTracking(Channel.fromPath(params.species_files, checkIfExists: false),
+ //Channel.fromPath(params.annotation_files, checkIfExists: false),
+ //transcriptomic_f_ch, qtl_f_ch, sp_info_ch)
- // qtl files
- qtl_f_ch
- .splitCsv(header:true, sep:"\t", strip:true)
- .map { row -> tuple(row.ID, row.status, row.species, file(row.dataset), file(row.qtl), file(row.qtl_annotation)) }
- .set { qtl_ch }
+
//-------------------------------------------------//
// Get basic genetic nodes and edges //
@@ -192,19 +242,12 @@ workflow {
// need to add the gff3 and chr_conv table to all datasets lines of the qtl
// table, since multiple datasets for each species, join is not possible
- qtl_ch
- .map { tuple( it[2], *it ) }
- .combine( samples_ch.gff3, by: 0 )
- .combine( samples_ch.chr_conv, by: 0 )
- .map { it[1..-1] }
- .set { qtl_genome_ch }
- getQTLInfo(qtl_genome_ch)
+
//-------------------------------------------------//
// Get transcriptomics info //
//-------------------------------------------------//
- getTranscriptomicCounts(transcriptomics_ch)
//-------------------------------------------------//
// Create missing ontology terms //
@@ -251,32 +294,4 @@ workflow {
// interpro
merge_results(getInterProAnnotation.out.interpro, subdir = '')
merge_results(getInterProAnnotation.out.protein_interpro, subdir = '')
- // qtl
- merge_results(getQTLInfo.out.qtl, subdir = '')
- merge_results(getQTLInfo.out.dataset, subdir = '')
- merge_results(getQTLInfo.out.population, subdir = '')
- merge_results(getQTLInfo.out.site, subdir = '')
- merge_results(getQTLInfo.out.year, subdir = '')
- merge_results(getQTLInfo.out.free_term, subdir = '')
- merge_results(getQTLInfo.out.gene_qtl, subdir = '')
- merge_results(getQTLInfo.out.qtl_chromosome, subdir = '')
- merge_results(getQTLInfo.out.qtl_dataset, subdir = '')
- merge_results(getQTLInfo.out.qtl_population, subdir = '')
- merge_results(getQTLInfo.out.qtl_site, subdir = '')
- merge_results(getQTLInfo.out.qtl_year, subdir = '')
- merge_results(getQTLInfo.out.qtl_onto, subdir = params.merged_subdir)
- merge_results(getQTLInfo.out.qtl_free_term, subdir = '')
- // transcriptomics
- merge_results(getTranscriptomicCounts.out.bioinfo_protocol, subdir = '')
- merge_results(getTranscriptomicCounts.out.dataset, subdir = '')
- merge_results(getTranscriptomicCounts.out.condition, subdir = '')
- merge_results(getTranscriptomicCounts.out.free_term, subdir = '')
- merge_results(getTranscriptomicCounts.out.sample, subdir = '')
- merge_results(getTranscriptomicCounts.out.dataset_bioinfo_protocol, subdir = '')
- merge_results(getTranscriptomicCounts.out.condition_dataset, subdir = '')
- merge_results(getTranscriptomicCounts.out.sample_condition, subdir = '')
- merge_results(getTranscriptomicCounts.out.gene_sample, subdir = '')
- merge_results(getTranscriptomicCounts.out.gene_condition, subdir = '')
- merge_results(getTranscriptomicCounts.out.condition_onto, subdir = params.merged_subdir)
- merge_results(getTranscriptomicCounts.out.condition_free_term, subdir = '')
}
diff --git a/modules/copyFilesForTracking.nf b/modules/copyFilesForTracking.nf
index c4998ef2e9e14886d974cf0c7eab0ae961f51fd8..613f9ce56f648f778fd5974ce3b2c2eac6564c5b 100755
--- a/modules/copyFilesForTracking.nf
+++ b/modules/copyFilesForTracking.nf
@@ -3,20 +3,12 @@
//*************************************************//
process copyFilesForTracking {
- // publishDir "${params.outdir}/conf_files/", mode: params.publish_dir_mode, enabled: params.publish_copyFilesForTracking
input:
- path species
- path annotation
- path transcriptomic
- path qtl
- path sp_info
+ tuple val(name), path(file)
+
output:
- path species
- path annotation
- path transcriptomic
- path qtl
- path sp_info
+ path file
script:
"""