Skip to content
Snippets Groups Projects

Split a FASTA file in chunks

Merged Kenzo-Hugo Hillion requested to merge 15-split-fasta-chunks into master
3 files
+ 53
0
Compare changes
  • Side-by-side
  • Inline

Files

configfile: "config.yaml"
def count_sequences(fasta_file):
with open(fasta_file, 'r') as file:
seq = 0
for line in file:
if '>' in line:
seq += 1
return seq
# ==== Snakefile path ====
__split_fasta_rules = config.get("snakefiles", {}).get("split_fasta")
__main_output_dir = config.get('output_dir', 'output')
# ==== Split FASTA ====
__split_fasta_output_dir = __main_output_dir + "/split_fasta"
__split_fasta_input = config['input_fasta']
__split_fasta_number_sequences = config.get('split_fasta', {}).get('number_sequences', 1000000)
total_number_sequences = count_sequences(__split_fasta_input)
EXTENSIONS = [f"{i:05d}" for i in range(0, int(total_number_sequences/__split_fasta_number_sequences) + 1)]
__split_fasta_prefix = "/".join([__split_fasta_output_dir, config['split_fasta']['prefix']])
__split_fasta_output = expand(__split_fasta_prefix + "{ext}.fa", ext=EXTENSIONS)
include: __split_fasta_rules
rule all:
input: __split_fasta_output
Loading