从耐药数据库card中—index文件中提取gene的fasta序列id_20220307

import json
import pandas as pd

df1=pd.read_csv(r'card数据\aro_index.tsv',sep='\t',header=0)
print(df1)
print(df1['AMR Gene Family'])
print(df1.iloc[:,8])

list_family=['TEM beta-lactamase','glycopeptide resistance gene cluster','major facilitator superfamily (MFS) antibiotic efflux pump','methicillin resistant PBP2','Penicillin-binding protein mutations conferring resistance to beta-lactam antibiotics','Erm 23S ribosomal RNA methyltransferase','SHV beta-lactamase','CTX-M beta-lactamase','OXA beta-lactamase','KPC beta-lactamase','NDM beta-lactamase','IMP beta-lactamase','VIM beta-lactamase','ROB beta-lactamase','fluoroquinolone resistant gyrA']

list_gene_accession=[]
for i in range(len(df1)):
    for j in list_family:
        if j==df1.iloc[i,8]:
            # print(df1['Model Name'][i])
            list_gene_accession.append(df1['DNA Accession'][i])
print(list_gene_accession)
print(len(list_gene_accession))
print(list_gene_accession[0][-2:]) # .1
print(list_gene_accession[0][:-1]) # AF002716.
line=''
with open(r'提取的耐药基因对应的nt完整序列id2.txt','w') as f:
    for i in range(len(list_gene_accession)):
        if list_gene_accession[i][-2]== '.':
            line+=list_gene_accession[i][:-2]+'\n'
        else:
            # line+=list_gene_accession[i]+'.1'+'\n'
            line += list_gene_accession[i]  + '\n'
    f.write(line)
f.close()