Skip to content

Estimation motifs #91

Merged
merged 5 commits into from
Jan 23, 2019
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion config/create_gtf.config
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
params{
tissue=""
tissues=""
}
2 changes: 1 addition & 1 deletion config/footprint_extraction.config
Original file line number Diff line number Diff line change
Expand Up @@ -2,5 +2,5 @@ params{
window_length = 200
step = 100
percentage = 0
max_bp_between = 6
gap_penalty = 6
}
6 changes: 3 additions & 3 deletions config/motif_estimation.config
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@ params {
min_seq = 10

//glam2
motif_min_len = 8
motif_max_len = 20
interation = 10000
motif_min_key = 8
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think motif_min_len was more obvious in it's meaning.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, but the parameter sets the number of minimum key positions not the length of the motif.

motif_max_key = 20
iteration = 10000

//tomtom
tomtom_treshold = 0.01
Expand Down
21 changes: 18 additions & 3 deletions pipeline.nf
Original file line number Diff line number Diff line change
Expand Up @@ -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 """
Expand Down Expand Up @@ -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: $key not found. Please check the given path.")
System.exit(2)
Expand Down Expand Up @@ -243,12 +250,20 @@ process overlap_with_known_TFBS {
script:
if(params.tfbs_path == ""){
"""
if [[ ! -x "${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}
"""
}
Expand Down