【python练习题二】正则表达式

Riven

test1.

1. #!/usr/bin/env python
   
2. # -*- coding=utf-8 -*-
   
3. 
   
4. import os
   
5. import gzip
   
6. import re
   
7. import argparse
   
8. 
   
9. parser = argparse.ArgumentParser()
   
10. parser.add_argument('-i', '--infile', required=True, help="the inpute file path")
    
11. parser.add_argument('-o', '--outfile', help="the output file path", default="gene.xls")
    
12. args = vars(parser.parse_args())
    
13. 
    
14. inf = os.path.abspath(args['infile'])
    
15. outf = os.path.abspath(args['outfile'])
    
16. 
    
17. def safe_open(file, mode):
    
18.     if file.endswith(".gz"):

复制代码

1. 
   
2. 
   
3.         return gzip.open(file, mode)
   
4.     else:
   
5.         return open(file, mode)
   
6. 
   
7. def extract_gene(str):
   
8.     pattern = re.compile('GENE=(\w+);')
   
9.     gene_name = pattern.search(str)
   
10.     # print(gene_name)
    
11.     return gene_name.group(1)
    
12. 
    
13. with safe_open(inf, 'rb') as infile, open(outf, 'w') as outfile:
    
14.     for line in infile:
    
15.         if line.startswith('#'):
    
16.             continue
    
17.         else:
    
18.             g_name = extract_gene(line)
    
19.             outfile.write(g_name + '\n')

复制代码

Riven

1. test2.
   
2. #!/usr/bin/env python
   
3. # -*- coding=utf-8 -*-
   
4. 
   
5. import os
   
6. import gzip
   
7. import re
   
8. import argparse
   
9. from Bio import SeqIO
   
10. 
    
11. parser = argparse.ArgumentParser()
    
12. parser.add_argument('-r', '--ref', help="the reference file path, default:human b37, *.fasta", default="/PUBLIC/database/HUMAN/genome/Human/human_g1k_v37_decoy.fasta")
    
13. parser.add_argument('-c', '--chr', help="specify the chromosome to search", required=True)
    
14. parser.add_argument('-b', '--bases', help="the group of bases to search", required=True)
    
15. parser.add_argument('-o', '--outfile', help="the output file path", default="search_out.xls")
    
16. args = vars(parser.parse_args())
    
17. print(args)
    
18. 
    
19. ref = os.path.abspath(args['ref'].strip())
    
20. chr = args['chr'].strip()
    
21. base_group = args['bases'].strip()
    
22. out = os.path.abspath(args['outfile'].strip())
    
23. 
    
24. def get_base_group_info(ref, chrom, residue, file):
    
25.     with open(file, 'w') as out:
    
26.         recod_dict = SeqIO.to_dict(SeqIO.parse(ref, "fasta"))
    
27.         chr_seq = str(recod_dict[chrom].seq)
    
28.         match = re.finditer(residue, chr_seq)
    
29.         for i in match:
    
30.             tup = i.span()
    
31.             start_pos = int(tup[0]) + 1
    
32.             end_pos = tup[1]
    
33.             # out.write(chrom + ':' + str(start_pos) + '-' + end_pos + '\n')
    
34.             out.write(chrom + ':' + str(start_pos) + '-' + str(end_pos) + '\n')
    
35. 
    
36. if __name__ == "__main__":
    
37.     get_base_group_info(ref, chr, base_group, out)

复制代码

Riven

1. test3.
   
2. 
   
3. #!/usr/bin/env python
   
4. # -*- coding=utf-8 -*-
   
5. 
   
6. import re
   
7. import os
   
8. import argparse
   
9. 
   
10. parser = argparse.ArgumentParser()
    
11. parser.add_argument('-i', '--infile', help="infile path", required=True)
    
12. parser.add_argument('-o', '--outfile', help="outfile path", default="out_share.xls")
    
13. args = vars(parser.parse_args())
    
14. 
    
15. infile = os.path.abspath(args['infile'].strip())
    
16. outfile = os.path.abspath(args['outfile'].strip())
    
17. 
    
18. def is_variation(string):
    
19.     if string == "0/0" or string == "./.":
    
20.         return False
    
21.     else:
    
22.         return True
    
23. 
    
24. var_sp_lst =[]
    
25. with open(infile, 'r') as inf, open(outfile, 'w') as out:
    
26.     idx_lst = []
    
27.     header_lst = []
    
28.     for line in inf:
    
29.         if line.startswith('Priority'):
    
30.             header_lst = line.strip().split('\t')
    
31.             out.write(line.strip('\n') + '\t' + 'Variation_sample' + '\n')
    
32.             match_obj = re.search(r'FORMAT(.+)Ori_REF', line)
    
33.             sample_lst = match_obj.group(1).strip('\t').split('\t')
    
34.             for i in sample_lst:
    
35.                 sp_idx = header_lst.index(i)
    
36.                 idx_lst.append(sp_idx)
    
37.         else:
    
38.             lst = []
    
39.             content_lst = line.strip().split('\t')
    
40.             for j in idx_lst:
    
41.                 variation_info = content_lst[j].split(':')[0]
    
42.                 if is_variation(variation_info):
    
43.                     lst.append(header_lst[j])
    
44.                 else:
    
45.                     continue
    
46.             # print(lst)
    
47.             if len(lst)==0:
    
48.                 out.write(line.strip('\n') + '\t' + '.' + '\n')
    
49.             else:
    
50.                 out.write(line.strip('\n') + '\t' + ','.join(lst) + '\n')

复制代码

helili

#!usr/bin/env python
#-*- coding=utf-8 -*-

import os
import re
import sys

infile = sys.argv[1]
outfile = sys.argv[2]

def safe_open(file,mode):
    file = os.path.abspath(file)
    if not os.path.exists(file):
        exit("%s is not exists" % file)
    if file.endswith('.gz'):
        import gzip
        return gzip.open(file,mode)
    else:
        return open(file,mode)

pattern = re.compile(r'GENE=(.+?);.+')
dic = {}
with safe_open(infile,"r") as f, open(outfile,"w") as out:
    for line in f:
        line = line.strip()
        if line.startswith('#'):
            out.write(line)
            out.write('\n')
        else:
            site = line.split('\t')[0:7]
            info = line.split('\t')[7]
            gene = pattern.findall(info)[0]
            outline = '{}\t{}\t{}\t{}\t{}\t{}\t{}\n'.format(*site)
            out.write(outline)
            out.write(gene+"\n")
f.close()

chenming

https://gitee.com/biocoder/pytho ... aster/re/re_test.py re模块一些需要注意的点