pipeline.nf: Added check for unknown parameters; update parameter nam…

…es; if compareBed.sh is not executable chmod +x is called

pipeline.nf

@@ -35,7 +35,7 @@
   	params.identity=0.8
   	params.sequence_coverage=8
   	params.memory=800
- 	params.throw_away_seq=9
+ 		params.throw_away_seq=9
   	params.strand=0
 
 //motif_estimation
@@ -60,7 +60,7 @@
 
 //creating_gtf
 	params.organism=""
-	params.tissue=""
+	params.tissues=""
 
 if (params.bigwig == "" || params.bed == "" || params.organism == "" || params.genome_fasta == "" || params.motif_db == "" || params.config == "" || "${params.help}" != "0" ){
 log.info """
@@ -144,20 +144,27 @@ int_params = ["window_length", "step", "min_size_fp", "max_size_fp", "kmer",
              "aprox_motif_len", "motif_occurence", "min_seq_length", "global",
              "sequence_coverage", "memory", "throw_away_seq", "strand",
              "min_seq", "motif_min_key", "motif_max_key", "iteration",
-             "edge_weight", "best_motif", "min_gap", "gap_penalty", "edge_weight"]
+             "edge_weight", "best_motif", "min_gap", "gap_penalty", "edge_weight",
+						 "threads", ]
 req_params = ["bigwig", "bed", "genome_fasta", "motif_db", "config"]
+all_params = int_params + req_params + ["organism" , "identity", "tfbsscan_method",
+							"percentage", "tomtom_treshold", "motif_similarity_thresh", "out",
+							"tissues", "gtf_path", "cluster_motif", "tfbs_path", "help"]
 
 valid_organism = ["hg38", "hg19", "mm9", "mm10"]
 valid_tfbsscan_methods = ["moods","fimo"]
 
 params.each { key, value ->
+	if (!(all_params.contains(key))){
+		println("Warning: Parameter $key is unknown. Please check for typos or the parameter list!")
+	}
   if(int_params.contains(key)) {
     if (!("${value}" ==~ /\d+/ )){
       println("ERROR: $key needs to be an Integer")
       System.exit(2)
     }
   }
-  if(req_params.contains(key)) {
+  if(req_params.contains(key) || (key == "gtf_path" && value != "") ) {
     if(!file(value).exists()) {
       println("ERROR: $key not found. Please check the given path.")
       System.exit(2)
@@ -243,12 +250,20 @@ process overlap_with_known_TFBS {
 	script:
 	if(params.tfbs_path == ""){
 		"""
+		if [[ ! -x "${path_bin}/1.2_filter_motifs/compareBed.sh" ]]
+		then
+			chmod +x ${path_bin}/1.2_filter_motifs/compareBed.sh
+		fi
 		python ${path_bin}/1.2_filter_motifs/tfbsscan.py --use ${params.tfbsscan_method} --core ${params.threads} -m ${db} -g ${fasta} -o ./known_tfbs -b ${bed_peaks}
 		${path_bin}/1.2_filter_motifs/compareBed.sh --data ${bed_footprints} --motifs ./known_tfbs --fasta ${fasta} -o ${name}_unknown.bed -min ${params.min_size_fp} -max ${params.max_size_fp}
 		cp -r ./known_tfbs/ ${params.out}/1.2_filter_motifs/
 		"""
 	} else {
 		"""
+		if [[ ! -x "${path_bin}/1.2_filter_motifs/compareBed.sh" ]]
+		then
+			chmod +x ${path_bin}/1.2_filter_motifs/compareBed.sh
+		fi
 		${path_bin}/1.2_filter_motifs/compareBed.sh --data ${bed_footprints} --motifs ${known_tfbs} --fasta ${fasta} -o ${name}_unknown.bed -min ${params.min_size_fp} -max ${params.max_size_fp}
 		"""
 	}
@@ -274,6 +289,9 @@ process reduce_sequence {
 	set name, file ('*.bed') into bed_for_clustering
 	file ('*.log')
 
+	when:
+	params.lalal == "1"
+
 	script:
 	"""
 	Rscript ${path_bin}/2.1_clustering/reduce_sequence.R -i ${bed} -k ${params.kmer} -m ${params.aprox_motif_len} -o ${name}_reduced.bed -t ${params.threads} -f ${params.motif_occurence} -s ${params.min_seq_length} --summary reduce_sequence.log