Dev

README.md

@@ -69,7 +69,7 @@ Optional arguments:
 	--window_length INT	This parameter sets the length of a sliding window. (Default: 200)
 	--step INT		This parameter sets the number of positions to slide the window forward. (Default: 100)
 	--percentage INT	Threshold in percent (Default: 0)
-	--max_bp_between INT	If footprints are less than X bases appart the footprints will be merged (Default: 6)
+	--min_gap INT		If footprints are less than X bases appart the footprints will be merged (Default: 6)
 
 	Filter motifs:
 	--min_size_fp INT	Minimum sequence length threshold. Smaller sequences are discarded. (Default: 10)

pipeline.nf

@@ -16,7 +16,7 @@
 	params.window_length = 200
 	params.step = 100
 	params.percentage = 0
-	params.max_bp_between = 6
+	params.min_gap = 6
 
 //filter_unknown_motifs
 	params.min_size_fp=10
@@ -46,6 +46,7 @@
 	params.motif_min_key = 8 // Minimum number of key positions (aligned columns)
 	params.motif_max_key = 20 // Maximum number of key positions (aligned columns)
 	params.iteration = 10000 // Number of Iterations done by glam2. A high iteration number equals a more accurate result but with an higher runtime.
+	params.gap_penalty = 1000
 
 	//tomtom
 	params.tomtom_treshold = 0.01 // threshold for similarity score.
@@ -57,6 +58,7 @@
 
 	params.best_motif = 3 // Top n motifs per cluster
 
+
 //creating_gtf
 	params.organism=""
 	params.tissue=""
@@ -86,7 +88,7 @@ Optional arguments:
 	--window_length INT	This parameter sets the length of a sliding window. (Default: 200)
 	--step INT		This parameter sets the number of positions to slide the window forward. (Default: 100)
 	--percentage INT	Threshold in percent (Default: 0)
-	--max_bp_between INT	If footprints are less than X bases appart the footprints will be merged (Default: 6)
+	--min_gap INT	If footprints are less than X bases appart the footprints will be merged (Default: 6)
 
 	Filter motifs:
 	--min_size_fp INT	Minimum sequence length threshold. Smaller sequences are discarded. (Default: 10)
@@ -114,6 +116,7 @@ Optional arguments:
 	--iteration INT		Number of iterations done by GLAM2. More Iterations: better results, higher runtime. (Default: 10000)
 	--tomtom_treshold FLOAT	Threshold for similarity score. (Default: 0.01)
 	--best_motif INT	Get the best X motifs per cluster. (Default: 3)
+	--gap_penalty INT	Set penalty for gaps in GLAM2 (Default: 1000)
 	Moitf clustering:
 	--cluster_motif	Boolean	If 1 pipeline clusters motifs. If its 0 it does not. (Defaul: 0)
 	--edge_weight INT	Minimum weight of edges in motif-cluster-graph (Default: 5)
@@ -141,7 +144,7 @@ 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"]
+             "edge_weight", "best_motif", "min_gap", "gap_penalty", "edge_weight"]
 req_params = ["bigwig", "bed", "genome_fasta", "motif_db", "config"]
 
 valid_organism = ["hg38", "hg19", "mm9", "mm10"]
@@ -212,7 +215,7 @@ process footprint_extraction {
 
 	script:
 	"""
-	python ${path_bin}/1.1_footprint_extraction/footprints_extraction.py --bigwig ${bigWig} --bed ${bed} --output_file ${name}_called_peaks.bed --window_length ${params.window_length} --step ${params.step} --percentage ${params.percentage} --max_bp_between ${params.max_bp_between}
+	python ${path_bin}/1.1_footprint_extraction/footprints_extraction.py --bigwig ${bigWig} --bed ${bed} --output_file ${name}_called_peaks.bed --window_length ${params.window_length} --step ${params.step} --percentage ${params.percentage} --min_gap ${params.min_gap}
 	"""
 }
 
@@ -375,7 +378,7 @@ process glam2 {
 
     script:
     """
-    glam2 n ${fasta} -O ./${name}/ -a ${params.motif_min_key} -b ${params.motif_max_key} -z 5 -n ${params.iteration}
+    glam2 n ${fasta} -O ./${name}/ -E ${params.gap_penalty} -J ${params.gap_penalty} -a ${params.motif_min_key} -b ${params.motif_max_key} -z 5 -n ${params.iteration}
     """
 }
 
@@ -541,7 +544,7 @@ process clustered_glam2 {
 	script:
   	name = fasta.getBaseName()
 	"""
-	glam2 n ${fasta} -O ./${name}/ -a ${params.motif_min_key} -b ${params.motif_max_key} -z 5 -n ${params.iteration}
+	glam2 n ${fasta} -O ./${name}/ -E ${params.gap_penalty} -J ${params.gap_penalty} -a ${params.motif_min_key} -b ${params.motif_max_key} -z 5 -n ${params.iteration}
 	"""
 }