Commit 58ed058e authored by Jean Mainguy's avatar Jean Mainguy
Browse files

preserve fasta file names in GLOBAL_CD_HIT to cat file in a consistent way

parent 97ab5025
......@@ -26,18 +26,18 @@ process GLOBAL_CD_HIT {
label 'CD_HIT'
input:
path "*.fasta"
path cluster_fasta
val pct_id
output:
path "All-cd-hit-est.${pct_id}.fasta"
path "table_clstr.txt", emit: clstr_table
// when: ('06_func_annot' in step)
script:
"""
cat * > All-cd-hit-est.${pct_id}
# *fasta is important to get the correct order
cat *.fasta > All-cd-hit-est.${pct_id}
cd-hit-est -c ${pct_id} -i All-cd-hit-est.${pct_id} -o All-cd-hit-est.${pct_id}.fasta -T ${task.cpus} -M ${task.mem} -d 150
cat All-cd-hit-est.${pct_id}.fasta.clstr | cd_hit_produce_table_clstr.py > table_clstr.txt
"""
......@@ -54,7 +54,9 @@ ch_percentage_identity // channel: val
main:
INDIVIDUAL_CD_HIT( ch_assembly, ch_percentage_identity )
GLOBAL_CD_HIT( INDIVIDUAL_CD_HIT.out.clstr_fasta.collect(), ch_percentage_identity )
ch_individual_clusters = INDIVIDUAL_CD_HIT.out.clstr_fasta.collect()
GLOBAL_CD_HIT(ch_individual_clusters , ch_percentage_identity )
emit:
individual_clstr_table = INDIVIDUAL_CD_HIT.out.clstr_table
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment