From a159e4137773e7e2e0ebbafb0a4c93101136801c Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 19:49:39 +0100 Subject: [PATCH] Update pipeline.nf --- pipeline.nf | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/pipeline.nf b/pipeline.nf index e1977d2..3148d11 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -71,23 +71,23 @@ Required arguments: Optional arguments: --tfbs_path Path to directory with output from tfbsscan. If given tfbsscan will not be run. - + Footprint extraction: - --window_length INT (Default: 200) - --step INT (Default: 100) - --percentage INT (Default: 0) - + --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) + Filter unknown motifs: - --min_size_fp INT (Default: 10) - --max_size_fp INT (Default: 100) - + --min_size_fp INT Minimum sequence length threshold. Smaller sequences are discarded. (Default: 10) + --max_size_fp INT Maximum sequence length threshold. Discards all sequences longer than this value. (Default: 100) + Clustering: Sequence preparation/ reduction: --kmer INT Kmer length (Default: 10) --aprox_motif_len INT Motif length (Default: 10) --motif_occurence FLOAT Percentage of motifs over all sequences. Use 1 (Default) to assume every sequence contains a motif. --min_seq_length Interations Remove all sequences below this value. (Default: 10) - + Clustering: --global INT Global (=1) or local (=0) alignment. (Default: 0) --identity FLOAT Identity threshold. (Default: 0.8) @@ -95,7 +95,7 @@ Optional arguments: --memory INT Memory limit in MB. 0 for unlimited. (Default: 800) --throw_away_seq INT Remove all sequences equal or below this length before clustering. (Default: 9) --strand INT Align +/+ & +/- (= 1). Or align only +/+ (= 0). (Default: 0) - + Motif estimation: --min_seq INT Sets the minimum number of sequences required for the FASTA-files given to GLAM2. (Default: 100) --motif_min_key INT Minimum number of key positions (aligned columns) in the alignment done by GLAM2. (Default: 8) @@ -103,12 +103,12 @@ 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) - + 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) --motif_similarity_thresh FLOAT Threshold for motif similarity score (Default: 0.00001) - + Creating GTF: --organism [hg38 | hg19 | mm9 | mm10] Input organism --tissues List/String List of one or more keywords for tissue-/category-activity, categories must be specified as in JSON