GitHub - MrOlm/inStrain: Bioinformatics program inStrain

安装

conda create -n instrain
conda activate instrain
pip install instrain
inStrain -h

 需要准备一个 scaffold-to-bin file

（.text 文件，包含由制表符分隔的两列，其中第一列是脚手架的名称，第二列是脚手架所属的 bin/基因组的名称。）

https://github.com/MrOlm/drep/blob/master/helper_scripts/parse_stb.py

可使用这个脚本提取(scaffold_to_bin.tsv是需要的)

 profile部分

#! /usr/bin/env python
#########################################################
# split Vir contig for each ">"
# written by PeiZhong in IFR of CAAS

import argparse
from Bio import SeqIO
import os

parser = argparse.ArgumentParser(description='split Vir contig for each ">" ')
parser.add_argument('--input_fa', required=True, help='< input fasta >')

args = parser.parse_args()
input_fa = args.input_fa

def split_fasta(fasta_file):
    folder_name = os.path.splitext(fasta_file)[0]
    if not os.path.exists(folder_name):
        os.makedirs(folder_name)
    fasta_sequences = SeqIO.parse(open(fasta_file), 'fasta')
    for fasta in fasta_sequences:
        name, sequence = fasta.id, str(fasta.seq)
        new_file = os.path.join(folder_name, name + ".fasta")
        with open(new_file, "w") as output_file:
            output_file.write(">" + name + "\n" + sequence + "\n")

split_fasta(input_fa)

instrain=$(pwd)
fp_path="/home/zhongpei/hard_disk_sda2/zhongpei/Virome/rawdata/upload_20230812/zhongpei_analyse/fastp"
source /home/zhongpei/miniconda3/bin/activate /home/zhongpei/hard_disk_sda2/zhongpei/LBSWrap/LBSWrap-inStrain
for i in all_virome_95.fa
do
	num=${i%%.fa}
	/home/zhongpei/hard_disk_sda2/zhongpei/Software/my_script/fasta_split_bin.py --input_fa ${i}
	/home/zhongpei/hard_disk_sda2/zhongpei/Software/my_script/parse_stb.py --reverse -f ${num}/* -o ${num}.stb
	bowtie2-build ${i} ${i} 
	cd ${fp_path}
	for x in *_clean_2.fastq
	do
		cd ${fp_path}
		numx=${x%%_clean_2.fastq}
		bowtie2 -p 180 -x ${instrain}/${i} -1 ${numx}_clean_1.fastq -2 ${x} > ${instrain}/${numx}_instrain.sam
		cd ${instrain}
		samtools view -Sb -@180 ${numx}_instrain.sam > ${numx}_instrain.bam
		samtools sort -@180 ${numx}_instrain.bam -o ${numx}_instrain_sort.bam
		samtools index -@ 180 ${numx}_instrain_sort.bam
		rm ${numx}_instrain.sam
		rm ${numx}_instrain.bam
		inStrain profile ${numx}_instrain_sort.bam ${i} -o ${numx}.IS -p 180 -s ${num}.stb
	done
	rm *.bt2
done

conda deactivate
conda deactivate

compare部分

inStrain compare \
  -i /path/to/output/Mom1_phage_instrain /path/to/output/W1_phage_instrain \
  -o /path/to/output/Mom1_W1_phage_vertical \
  -p 4 \
  --breadth 0.75 \
  -ani 0.99 \
  -cov 0.75