二代测序-对kraken2的结果分析转化

1.对kraken2处理

inputpath1 = r'22-12373O.5.10000.kraken2'

with open(inputpath1, 'r') as f1:
    for line in f1:
        line = line.strip('\n')
        list_line = line.split('\t')
        # print(line)
        if list_line[0] == 'C':
            # print(list_line[4].split(' '))
            list_all_value = list_line[4].split(' ')
            list_all_value.remove('|:|')
            # print(list_all_value)
            list_last = [item for item in list_all_value if item.split(':')[0] != 'A']
            sum

2.deal_k2report_to_xls

#!/usr/bin/env python3
import os, sys, re
# ms, infile_name, outfile_name = sys.argv
infile_name=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-last\捕获\20-9263L.2.kreport2'
outfile_name=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-last\捕获\20-9263L.2.kreport2.trans.xls'


with open(infile_name, 'r') as infile:
    with open(outfile_name, 'w') as o:
        Domain = ""
        for line in infile:
            line = line.strip()
            lines = re.split(r'\t', line)
            lines[5] = re.split(r'^[ ]*', lines[5])[1]
            if lines[3] == "D":
                Domain = lines[5]
                o.write("\t".join(lines))
                o.write("\n")
                Kingdom = "NG"  ## Kingdom非必须，Domain必须，在这里赋空值
            elif lines[3] == "K":
                Kingdom = lines[5]
                lines[5] = Domain+";"+Kingdom
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "P":
                Phylum = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "C":
                Class = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum+";"+Class
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "O":
                Order = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum+";"+Class+";"+Order
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "F":
                Family = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum+";"+Class+";"+Order+";"+Family
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "G":
                Genus = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum+";"+Class+";"+Order+";"+Family+";"+Genus
                o.write("\t".join(lines))
                o.write("\n")
            elif lines[3] == "S":
                Species = lines[5]
                lines[5] = Domain+";"+Kingdom+";"+Phylum+";"+Class+";"+Order+";"+Family+";"+Genus+";"+Species
                o.write("\t".join(lines))
                o.write("\n")

3.对kraken2的report进行输出

import os
import click

@click.command()
@click.option('-i1','--inputpath1',help='inputpath1(nanorv-crpm002-double-cap.report.out.xls)|...',required=True)
@click.option('-o1','--outputpath1',help='outputpath1(nanorv-crpm002-double-cap.classify.xls)|...',required=True)
# inputpath1=r'C:\Users\Administrator\Desktop\20230327需要查看的\nanorv-crpm002-double-cap.report.out.xls'
# outputpath1=r'C:\Users\Administrator\Desktop\20230327需要查看的\nanorv-crpm002-double-cap.classify.xls'

def classify_kraken2(inputpath1,outputpath1):

    with open(inputpath1,'r') as f1,open(outputpath1,'w') as f2:
        f2.write('Ename\ttaxid\treads/all_reads(%)\n')
        for line in f1:
            line=line.strip('\n')
            list_1=line.split('\t')
            # list_1[1] = list_1[1].strip(' ')
            list_1[-1]=list_1[-1].strip()
            print(list_1)
            if list_1[3].startswith('S'):
                if int(list_1[2]) != 0:
                    f2.write('{}\t{}\t{}\n'.format(list_1[-1],list_1[-2],list_1[0]))

if __name__=='__main__':
    classify_kraken2()