pipeline.nf: adjusting to new parameters required by get_best_motif; …

…get_motif_seq

pipeline.nf

@@ -189,7 +189,7 @@ bigwig_input.combine(bed_input).set{footprint_in}
 This process uses the uncontinuous score from a bigWig file to estimate footpints within peaks of interest
 */
 process footprint_extraction {
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	tag{name}
 	publishDir "${params.out}/1.1_footprint_extraction/", mode: 'copy', pattern: '*.bed'
@@ -214,7 +214,7 @@ for_tfbs = fa_overlap.combine(db_for_motivscan).combine(bed_for_tfbsscan)
 */
 process extract_known_TFBS {
 
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	publishDir "${params.out}/1.2_filter_motifs/TFBSscan/", mode: 'copy', pattern: '*.bed'
 
@@ -250,7 +250,7 @@ if(params.tfbs_path == "") {
 /*
 */
 process overlap_with_known_TFBS {
-	conda "${path_env}"
+	//conda "${path_env}"
 	publishDir "${params.out}/1.2_filter_motifs/compareBed/", mode :'copy'
 
 	input:
@@ -272,8 +272,8 @@ process overlap_with_known_TFBS {
 Reduce each sequence to its most conserved region.
 */
 process reduce_sequence {
-	conda "${path_env}"
-	echo true
+	//conda "${path_env}"
+
 	publishDir "${params.out}/2.1_clustering/reduced_bed/", mode: 'copy'
 
 	input:
@@ -293,7 +293,7 @@ process reduce_sequence {
 Cluster all sequences. Appends a column with cluster numbers to the bed-file.
 */
 process clustering {
-	conda "${path_env}"
+	//conda "${path_env}"
 	echo true
 
 	publishDir "${params.out}/2.1_clustering/", mode: 'copy', pattern: '*.bed'
@@ -316,7 +316,7 @@ Converting BED-File to one FASTA-File per cluster
 */
 process bed_to_clustered_fasta {
 
-	conda "${path_env}"
+	//conda "${path_env}"
 	publishDir "${params.out}/2.2_motif_estimation/fasta/", mode: 'copy'
     tag{name}
 
@@ -347,7 +347,7 @@ process glam2 {
 
     tag{name}
 	publishDir "${params.out}/2.2_motif_estimation/glam2/", mode: 'copy'
-	conda "${path_env}"
+	//conda "${path_env}"
 
     input:
     set name, file (fasta) from fasta_for_glam2
@@ -373,7 +373,7 @@ The paths are sorted numerically depending on the cluster ID.
 process merge_meme {
 
 	publishDir "${params.out}/2.2_motif_estimation/cluster_motifs/merged_meme/", mode: 'copy'
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	input:
 	val (memelist) from meme_to_merge.toList()
@@ -406,7 +406,7 @@ process find_similar_motifs {
 
 	tag{name}
 	publishDir "${params.out}/2.2_motif_estimation/cluster_motifs/cluster_similarity/", mode: 'copy'
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	input:
 	set name, file (meme) ,file (merged_meme) from to_find_similar_motifs
@@ -429,7 +429,7 @@ Label first column of TSV-file with Cluster ID
 process label_cluster {
 
 	tag{name}
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	input:
 	set name, file (tsv) from motif_similarity
@@ -480,7 +480,7 @@ Merging FASTA-files of similar clusters
 */
 process merge_fasta {
 
-	conda "${path_env}"
+	//conda "${path_env}"
 	publishDir "${params.out}/2.2_motif_estimation/cluster_motifs/merged_fasta/", mode: 'copy'
 
 	input:
@@ -511,7 +511,7 @@ process clustered_glam2 {
 
 	publishDir "${params.out}/2.2_motif_estimation/cluster_motifs/glam2/", mode: 'copy'
 	tag{name}
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	input:
 	file (fasta) from motif_clustered_fasta_flat
@@ -555,7 +555,7 @@ process tomtom {
 
     tag{name}
 	publishDir "${params.out}/2.2_motif_estimation/tomtom/", mode: 'copy'
-	conda "${path_env}"
+	//conda "${path_env}"
 
     input:
     set name, file (meme) from for_tomtom
@@ -601,7 +601,7 @@ process check_for_unknown_motifs {
 //Get the best (first) X Motifs from each MEME-file
 process get_best_motif {
 
-	conda "${path_env}"
+	//conda "${path_env}"
 	tag{name}
 	publishDir "${params.out}/2.2_motif_estimation/best_unknown_motifs/", mode: 'copy'
 
@@ -612,27 +612,29 @@ process get_best_motif {
 	set name, file('*_best.meme') into best_motif
 
 	script:
+	cluster_id = name.split('_')[-1]
 	"""
-	python ${path_bin}/2.2_motif_estimation/get_best_motif.py ${meme} ${name}_best.meme ${params.best_motif}
+	python ${path_bin}/2.2_motif_estimation/get_best_motif.py ${meme} ${name}_best.meme ${params.best_motif} ${cluster_id}
 	"""
 }
 
 
 process get_best_motif_seq {
 
-	conda "${path_env}"
+	//conda "${path_env}"
 	tag{name}
 	publishDir "${params.out}/2.2_motif_estimation/best_unknown_motifs/motif_sequences/", mode: 'copy'
 
 	input:
-	set name, file(txt) from seq_to_json
+	set name, file (txt) from seq_to_json
 
 	output:
-	file('*.json')
+	file("${name}_seq.json")
 
 	script:
+	cluster_id = name.split('_')[-1]
 	"""
-	Rscript ${path_bin}/2.2_motif_estimation/ get_motif_seq.R -i ${txt} -o ${name}_seq.json -n ${þærams.best_motif}
+	Rscript ${path_bin}/2.2_motif_estimation/get_motif_seq.R -i ${txt} -o ${name}_seq.json -n ${params.best_motif} -t ${path_bin}/2.2_motif_estimation/tmp/cluster_${cluster_id} -c ${cluster_id}
 	"""
 }
 
@@ -641,7 +643,7 @@ best_motif.combine(fa_scan).set {files_for_genome_scan}
 
 /*
 process genome_scan {
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	input:
 	set name, file(meme), file(fasta) from files_for_genome_scan
@@ -670,7 +672,7 @@ process cluster_quality {
 
 
 process create_GTF {
-	conda "${path_env}"
+	//conda "${path_env}"
 
 	publishDir "${params.out}/3.1_create_gtf/", mode: 'copy'