From 906942e1bc02c9faa421fb7e48d01932fb8aa7df Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Wiegandt?= Date: Fri, 14 Dec 2018 18:21:58 -0500 Subject: [PATCH 01/10] major bugfix --- bin/bed_to_fasta.R | 8 ++++---- pipeline.nf | 7 ++++--- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/bin/bed_to_fasta.R b/bin/bed_to_fasta.R index 13bd026..6cefe43 100644 --- a/bin/bed_to_fasta.R +++ b/bin/bed_to_fasta.R @@ -9,17 +9,17 @@ args = commandArgs(trailingOnly = TRUE) bedInput <- args[1] -prefix <- args[2] -min_seq <- args[3] +prefix <- args[2] +min_seq <- args[3] bed <- data.table::fread(bedInput, header = FALSE, sep = "\t") -clusters <- split(bed, bed$V8, sorted = TRUE, flatten = FALSE) # <---- Spalte mit Cluster +clusters <- split(bed, bed$V11, sorted = TRUE, flatten = FALSE) # <---- Spalte mit Cluster discard <- lapply(1:length(clusters), function(i){ clust <- as.data.frame(clusters[i]) print(nrow(clust)) if (nrow(clust) >= as.numeric(min_seq) ) { - sequences <- as.list(clust[[7]]) # <---- Splate mit Sequenz + sequences <- as.list(clust[[10]]) # <---- Splate mit Sequenz outfile <- paste0(prefix,"_cluster_",i,".FASTA") seqinr::write.fasta(sequences = sequences, names = clust[[4]], file.out = outfile, as.string = TRUE) # <---- Spalte mit Name } else { diff --git a/pipeline.nf b/pipeline.nf index ef2b0f5..c20c277 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -55,7 +55,7 @@ params.tfbs_path="" params.organism="hg38" params.tissue="" - params.tmpdir = "/mnt/workspace1/rene.wiegandt/tmp/" + params.tmpdir = "./" if (params.bigwig == "" || params.bed == "" || params.genome_fasta == "" || params.motif_db == "" || params.config == ""){ log.info """ @@ -240,7 +240,7 @@ if(params.tfbs_path == "") { process overlap_with_known_TFBS { conda "${path_env}" - publishDir "${params.out}/unknown_overlap/" + publishDir "${params.out}/unknown_overlap/", mode :'copy' input: set name, file (bed_footprints), val (bed_motifs), file (fasta) from for_overlap @@ -339,6 +339,7 @@ process glam2 { file("${name}/*.meme") into meme_to_merge set name, file("${name}/*.meme") into meme_for_tomtom set name, file("${name}/*.meme") into meme_for_filter + file ('*') script: """ @@ -477,7 +478,7 @@ process tomtom { script: """ - tomtom ${meme} ${params.motif_db} -thresh ${params.thresh} -mi 1 -text | sed '/^#/ d' | sed '/^\$/d' > ${name}_known_motif.tsv + tomtom ${meme} ${params.motif_db} -thresh ${params.tomtom_treshold} -mi 1 -text | sed '/^#/ d' | sed '/^\$/d' > ${name}_known_motif.tsv """ } From 1e3b771493d084fd651025d16c845316a8deac2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Wiegandt?= Date: Fri, 14 Dec 2018 18:38:57 -0500 Subject: [PATCH 02/10] minor changes --- pipeline.nf | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/pipeline.nf b/pipeline.nf index c20c277..5cd3c8c 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -8,6 +8,8 @@ params.motif_db="" params.config="" params.tfbs_path="" +params.create_known_tfbs_path = "./" + //peak_calling params.window_length = 200 params.step = 100 @@ -55,8 +57,6 @@ params.tfbs_path="" params.organism="hg38" params.tissue="" - params.tmpdir = "./" - if (params.bigwig == "" || params.bed == "" || params.genome_fasta == "" || params.motif_db == "" || params.config == ""){ log.info """ Usage: nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta [FASTA-file] --motif_db [MEME-file] @@ -65,7 +65,10 @@ Required arguments: --bigwig Path to BigWig-file --bed Path to BED-file --genome_fasta Path to genome in FASTA-format - --jaspar_db Path to motif-database in MEME-format + --motif_db Path to motif-database in MEME-format + --config Path to UROPA configuration file + --create_known_tfbs_path Path to directory where output from tfbsscan (known motifs) are stored. + Path can be set as tfbs_path in next run. (Default: './') Optional arguments: @@ -101,13 +104,14 @@ Optional arguments: --motif_max_len INT Maximum length of Motif (Default: 20) --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: --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 [homo_sapiens | mus_musculus] + --organism [hg38 | hg19 | mm9 | mm10] --tissues All arguments can be set in the configuration files. @@ -217,7 +221,7 @@ process extract_known_TFBS { script: """ - python ${path_bin}/tfbsscan.py --use moods --core ${params.threads} -m ${db} -g ${fasta} -o ${params.tmpdir} + python ${path_bin}/tfbsscan.py --use moods --core ${params.threads} -m ${db} -g ${fasta} -o ${params.create_known_tfbs_path} """ } @@ -226,7 +230,7 @@ Sets path to known tfbs BED-files. If tfbs_path is set the process extract_known */ if(params.tfbs_path == "") { bed_for_overlap_with_TFBS.combine(known_TFBS_for_overlap.toList()).combine(fa_overlap_2).set {for_overlap} - motif_path = params.tmpdir + motif_path = params.create_known_tfbs_path } else { Channel.from('skipped').set {workaround} bed_for_overlap_with_TFBS.combine(workaround).combine(fa_overlap_2).set {for_overlap} From fafe237bca92cc32b20beabd6253c74f15aa81d7 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:41:07 +0100 Subject: [PATCH 03/10] Update README.md --- README.md | 77 ++++++++++++++++++++++++------------------------------- 1 file changed, 34 insertions(+), 43 deletions(-) diff --git a/README.md b/README.md index a884632..38b2d10 100644 --- a/README.md +++ b/README.md @@ -47,57 +47,48 @@ nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta For a detailed overview for all parameters follow this [link](https://github.molgen.mpg.de/loosolab/masterJLU2018/wiki/Configuration). ``` Required arguments: - --bigwig Path to BigWig-file with scores on the peaks of interest - --bed Path to BED-file with peaks of interest corresponding to the BigWig file - --genome_fasta Path to genome in FASTA-format - --motif_db Path to motif-database in MEME-format - - + --bigwig Path to BigWig-file + --bed Path to BED-file + --genome_fasta Path to genome in FASTA-format + --motif_db Path to motif-database in MEME-format + --config Path to UROPA configuration file + --create_known_tfbs_path Path to directory where output from tfbsscan (known motifs) are stored. + Path can be set as tfbs_path in next run. (Default: './') Optional arguments: - - --tfbs_path Path to directory with output BED-files from tfbsscan. If given tfbsscan will not be run. - + --tfbs_path Path to directory with output from tfbsscan. If given tfbsscan will not be run. Footprint extraction: - --window_length INT (Default: 200) a length of a window - --step INT (Default: 100) an interval to slide the window - --percentage INT(Default: 0) a percentage to be added to background while searching for footprints - + --window_length INT (Default: 200) + --step INT (Default: 100) + --percentage INT (Default: 0) Filter unknown motifs: - --min_size_fp INT (Default: 10) - --max_size_fp INT (Default: 100) - - Cluster: + --min_size_fp INT (Default: 10) + --max_size_fp INT (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 INT Remove all sequences below this value. (Default: 10) - + --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) - --sequence_coverage INT Minimum aligned nucleotides on both sequences. (Default: 8) - --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) - + --global INT Global (=1) or local (=0) alignment. (Default: 0) + --identity FLOAT Identity threshold. (Default: 0.8) + --sequence_coverage INT Minimum aligned nucleotides on both sequences. (Default: 8) + --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 Minimum number of sequences required in the FASTA-files for GLAM2 (Default: 100) - --motif_min_key INT Maximum number of key positions (aligned columns) (Default: 8) - --motif_max_key INT Maximum number of key positions (aligned columns) (Default: 20) + --motif_min_len INT Minimum length of Motif (Default: 8) + --motif_max_len INT Maximum length of Motif (Default: 20) --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) - - Motif clustering: - --cluster_motif BOOLEAN IF its 1 motifs will be clustered (Default: 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: - --tissue STRING Filter for one or more tissue/category activity, categories as in JSON config (Default: None) - --organism STRING Source organism: [ hg19 | hg38 or mm9 | mm10 ] (Default: hg38) - -All arguments can be set in the configuration files. + --best_motif INT Get the best X motifs per cluster. (Default: 3) + Moitf clustering: + --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] + --tissues +All arguments can be set in the configuration files ``` From aed0e60532a1e35b0d7f61f11b40e6c70a62d4b6 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:43:37 +0100 Subject: [PATCH 04/10] Update README.md --- README.md | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 38b2d10..0a64a9f 100644 --- a/README.md +++ b/README.md @@ -53,22 +53,27 @@ Required arguments: --motif_db Path to motif-database in MEME-format --config Path to UROPA configuration file --create_known_tfbs_path Path to directory where output from tfbsscan (known motifs) are stored. - Path can be set as tfbs_path in next run. (Default: './') + Path can be set as tfbs_path in next run. (Default: './') 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) + Filter unknown motifs: --min_size_fp INT (Default: 10) --max_size_fp INT (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) @@ -76,15 +81,20 @@ 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_len INT Minimum length of Motif (Default: 8) --motif_max_len INT Maximum length of Motif (Default: 20) - --iteration INT Number of iterations done by glam2. More Iterations: better results, higher runtime. (Default: 10000) + --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] --tissues From 3ec60362665d6219a36e0bc7c81b05c31f0853b3 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:45:49 +0100 Subject: [PATCH 05/10] Update README.md --- README.md | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 0a64a9f..fa7ed4b 100644 --- a/README.md +++ b/README.md @@ -47,11 +47,11 @@ nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta For a detailed overview for all parameters follow this [link](https://github.molgen.mpg.de/loosolab/masterJLU2018/wiki/Configuration). ``` Required arguments: - --bigwig Path to BigWig-file - --bed Path to BED-file - --genome_fasta Path to genome in FASTA-format - --motif_db Path to motif-database in MEME-format - --config Path to UROPA configuration file + --bigwig Path to BigWig-file + --bed Path to BED-file + --genome_fasta Path to genome in FASTA-format + --motif_db Path to motif-database in MEME-format + --config Path to UROPA configuration file --create_known_tfbs_path Path to directory where output from tfbsscan (known motifs) are stored. Path can be set as tfbs_path in next run. (Default: './') Optional arguments: @@ -60,7 +60,7 @@ Optional arguments: Footprint extraction: --window_length INT (Default: 200) - --step INT (Default: 100) + --step INT (Default: 100) --percentage INT (Default: 0) Filter unknown motifs: @@ -69,23 +69,23 @@ Optional arguments: Clustering: Sequence preparation/ reduction: - --kmer INT Kmer length (Default: 10) + --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) + --global INT Global (=1) or local (=0) alignment. (Default: 0) --identity FLOAT Identity threshold. (Default: 0.8) --sequence_coverage INT Minimum aligned nucleotides on both sequences. (Default: 8) - --memory INT Memory limit in MB. 0 for unlimited. (Default: 800) + --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) + --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_len INT Minimum length of Motif (Default: 8) - --motif_max_len INT Maximum length of Motif (Default: 20) + --motif_min_key INT Minimum number of key positions (aligned columns) in the alignment done by GLAM2. (Default: 8) + --motif_max_key INT Maximum number of key positions (aligned columns) in the alignment done by GLAM2.f (Default: 20) --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) From 6f263b5bfba9569e6fc518d2656eef568fef4d72 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:46:16 +0100 Subject: [PATCH 06/10] Update pipeline.nf --- pipeline.nf | 52 ++++++++++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/pipeline.nf b/pipeline.nf index 5cd3c8c..c208d4a 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -62,59 +62,59 @@ log.info """ Usage: nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta [FASTA-file] --motif_db [MEME-file] Required arguments: - --bigwig Path to BigWig-file - --bed Path to BED-file - --genome_fasta Path to genome in FASTA-format - --motif_db Path to motif-database in MEME-format - --config Path to UROPA configuration file + --bigwig Path to BigWig-file + --bed Path to BED-file + --genome_fasta Path to genome in FASTA-format + --motif_db Path to motif-database in MEME-format + --config Path to UROPA configuration file --create_known_tfbs_path Path to directory where output from tfbsscan (known motifs) are stored. - Path can be set as tfbs_path in next run. (Default: './') - - + Path can be set as tfbs_path in next run. (Default: './') Optional arguments: - --tfbs_path Path to directory with output from tfbsscan. If given tfbsscan will not be run. - + --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) + --step INT (Default: 100) --percentage INT (Default: 0) - + Filter unknown motifs: --min_size_fp INT (Default: 10) --max_size_fp INT (Default: 100) - + Clustering: Sequence preparation/ reduction: - --kmer INT Kmer length (Default: 10) + --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) + --global INT Global (=1) or local (=0) alignment. (Default: 0) --identity FLOAT Identity threshold. (Default: 0.8) --sequence_coverage INT Minimum aligned nucleotides on both sequences. (Default: 8) - --memory INT Memory limit in MB. 0 for unlimited. (Default: 800) + --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) - + --strand INT Align +/+ & +/- (= 1). Or align only +/+ (= 0). (Default: 0) + Motif estimation: - --motif_min_len INT Minimum length of Motif (Default: 8) - --motif_max_len INT Maximum length of Motif (Default: 20) - --iteration INT Number of iterations done by glam2. More Iterations: better results, higher runtime. (Default: 10000) + --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) + --motif_max_key INT Maximum number of key positions (aligned columns) in the alignment done by GLAM2.f (Default: 20) + --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] --tissues - -All arguments can be set in the configuration files. +All arguments can be set in the configuration files + ``` """ } else { Channel.fromPath(params.bigwig).map {it -> [it.simpleName, it]}.set {bigwig_input} From 13d4447189c87a532d8f56b401c051bd16573016 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:47:16 +0100 Subject: [PATCH 07/10] Update pipeline.nf --- pipeline.nf | 41 ++++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 21 deletions(-) diff --git a/pipeline.nf b/pipeline.nf index c208d4a..c7b64e1 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -1,14 +1,13 @@ #!/usr/bin/env nextflow //setting default values -params.bigwig="" -params.bed="" -params.genome_fasta="" -params.motif_db="" -params.config="" -params.tfbs_path="" - -params.create_known_tfbs_path = "./" + params.bigwig="" + params.bed="" + params.genome_fasta="" + params.motif_db="" + params.config="" + params.tfbs_path="" + params.create_known_tfbs_path = "./" //peak_calling params.window_length = 200 @@ -20,19 +19,19 @@ params.create_known_tfbs_path = "./" params.max_size_fp=100 //clustering - //reduce_bed - params.kmer=10 - params.aprox_motif_len=10 - params.motif_occurence=1 - params.min_seq_length=10 - - //cdhit_wrapper - params.global=0 - params.identity=0.8 - params.sequence_coverage=8 - params.memory=800 - params.throw_away_seq=9 - params.strand=0 + //reduce_bed + params.kmer=10 + params.aprox_motif_len=10 + params.motif_occurence=1 + params.min_seq_length=10 + + //cdhit_wrapper + params.global=0 + params.identity=0.8 + params.sequence_coverage=8 + params.memory=800 + params.throw_away_seq=9 + params.strand=0 //motif_estimation //bed_to_clustered_fasta From 565eeaa55639c0b8582caf441eb892e80cf9254c Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:53:00 +0100 Subject: [PATCH 08/10] Update README.md --- README.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index fa7ed4b..3bf19c3 100644 --- a/README.md +++ b/README.md @@ -96,8 +96,9 @@ Optional arguments: --motif_similarity_thresh FLOAT Threshold for motif similarity score (Default: 0.00001) Creating GTF: - --organism [hg38 | hg19 | mm9 | mm10] - --tissues + --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 + config All arguments can be set in the configuration files ``` From 43646c6fd84d5bc3f8920c1f399a53df94416d02 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:53:21 +0100 Subject: [PATCH 09/10] Update pipeline.nf --- pipeline.nf | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/pipeline.nf b/pipeline.nf index c7b64e1..0855e37 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -58,8 +58,6 @@ if (params.bigwig == "" || params.bed == "" || params.genome_fasta == "" || params.motif_db == "" || params.config == ""){ log.info """ -Usage: nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta [FASTA-file] --motif_db [MEME-file] - Required arguments: --bigwig Path to BigWig-file --bed Path to BED-file @@ -70,7 +68,7 @@ Required arguments: Path can be set as tfbs_path in next run. (Default: './') Optional arguments: - --tfbs_path Path to directory with output from tfbsscan. If given tfbsscan will not be run. + --tfbs_path Path to directory with output from tfbsscan. If given tfbsscan will not be run. Footprint extraction: --window_length INT (Default: 200) @@ -110,8 +108,9 @@ Optional arguments: --motif_similarity_thresh FLOAT Threshold for motif similarity score (Default: 0.00001) Creating GTF: - --organism [hg38 | hg19 | mm9 | mm10] - --tissues + --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 + config All arguments can be set in the configuration files ``` """ From a390459b6bcf1fb13fe66cdca836502503f73ca4 Mon Sep 17 00:00:00 2001 From: renewiegandt Date: Sat, 15 Dec 2018 00:54:40 +0100 Subject: [PATCH 10/10] Update pipeline.nf --- pipeline.nf | 2 ++ 1 file changed, 2 insertions(+) diff --git a/pipeline.nf b/pipeline.nf index 0855e37..d4a1a11 100644 --- a/pipeline.nf +++ b/pipeline.nf @@ -58,6 +58,8 @@ if (params.bigwig == "" || params.bed == "" || params.genome_fasta == "" || params.motif_db == "" || params.config == ""){ log.info """ +Usage: nextflow run pipeline.nf --bigwig [BigWig-file] --bed [BED-file] --genome_fasta [FASTA-file] --motif_db [MEME-file] + Required arguments: --bigwig Path to BigWig-file --bed Path to BED-file