idolawoye

#!/usr/bin/env python3
"""
Filter sequences from a multifasta file based on an exclusion list.

Usage:
    python filter_fasta.py -i input.fasta -e exclude_ids.txt -o output.fasta

The exclude list should have one sequence ID per line (without the leading '>').
Matching is done against the first word of each FASTA header.
"""

idolawoye

grep -w -F -f taxon.txt *report.txt | awk 'BEGIN{OFS="\t"}{ print $1,$2}' > tb.txt

# taxon.txt is a file containing the Taxon name you want to summarize, e.g: Mycobacterium tuberculosis complex
# *.report.txt is the wildcard for selecting multiple Kraken report files
# tb.txt is the output TSV file

idolawoye

#!/usr/bin/env python

from Bio import SeqIO

fasta = "the_fasta_file.fasta"

for record in SeqIO.parse(fasta, "fasta"):
  print("ID: %s" % record.id)
  print("Sequence length: %s" % len(record))
  print("Number of Ns: %s" % record.seq.count('N'))

idolawoye

samtools depth CIV3724802_ref_bwa_sorted.bam | awk '{sum+=$3} END { print "Average = ",sum/NR}'

idolawoye

list=`cat TEXT_FILE` # list of the record file  IDs.
for i in $list
  do  echo $i
  SHELL COMMAND [OPTIONS] $i  #Command with file id 
done

idolawoye

total_files=`find -name '*.fastq' | wc -l`
arr=( $(ls *.fastq) )
echo "mapping started" >> map.log
echo "---------------" >> map.log

for ((i=0; i<$total_files; i+=2))
{
ref_genome=../ref.gb
sample_name=`echo ${arr[$i]} | awk -F "_" '{print $1}'`
echo "[mapping running for] $sample_name"