python - 错误的请求biopython出了什么问题

Question

嘿，我的脚本出了什么问题？它响应错误的请求。我不知道出了什么问题

from Bio import Entrez
Entrez.email = 'matro@gmail.com'
import time



  def fetch(ID):
        handle = Entrez.efetch(db = 'Protein', id = ID, retmode = 'fasta', rettype = 'text') #<--- here 
        seq = handle.read()
        time.sleep(1)
        return seq
  ids = ['ATK1','Cat','Lig1']
  out = [fetch(id) for id in ids] 
  with open('out.fasta', 'w') as f:
      f.writelines(out)

引文:

File "<ipython-input-42-0be173f176eb>", line 1, in <module>
runfile('C:/Users/MGrad/bioPythonSearch.py', wdir='C:/Users/MGrad/Dropbox/Leg')

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)

File "C:\Users\Local\conda\conda\envs\my_root\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/Leg/bioPythonSearch.py", line 20, in <module>
out = [fetch(id) for id in ids] # where ids is a Python list containing gene ids/accession numbers

File "C:/Users/MGrad/bioPythonSearch.py", line 20, in <listcomp>
out = [fetch(id) for id in ids] # where ids is a Python list containing gene ids/accession numbers

File "C:/Users/MGrad/bioPythonSearch.py", line 14, in fetch
handle = Entrez.efetch(db = 'Protein', id = ID, retmode = 'fasta', rettype = 'text')

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\site-packages\Bio\Entrez\__init__.py", line 180, in efetch
return _open(cgi, variables, post=post)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\site-packages\Bio\Entrez\__init__.py", line 526, in _open
raise exception

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\site-packages\Bio\Entrez\__init__.py", line 524, in _open
handle = _urlopen(cgi)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 223, in urlopen
return opener.open(url, data, timeout)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 532, in open
response = meth(req, response)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 642, in http_response
'http', request, response, code, msg, hdrs)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 570, in error
return self._call_chain(*args)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 504, in _call_chain
result = func(*args)

File "C:\Users\MGrad\AppData\Local\conda\conda\envs\my_root\lib\urllib\request.py", line 650, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)

HTTPError: Bad Request

Answer 1

Entrez.efetch() 适用于精确的 ID 号。如果您想查找像 ATK1 这样的术语，您需要首先通过 Entrez.esearch() 将其解析为一个或多个 ID 号。这是一个简单但有效的示例:

import time
from Bio import SeqIO
from Bio import Entrez

import xml.etree.cElementTree as ElementTree

TERMS = ['ATK1', 'Cat', 'Lig1']

Entrez.email = 'matro@gmail.com'

def fetch(term):
    # retmax=1 just returns first result of possibly many;  i.e. may be wrong, use more specific ID
    handle = Entrez.esearch(db='Protein', term=term, retmax=1)
    root = ElementTree.fromstring(handle.read())

    id_number = root.find("IdList/Id").text

    print(term, '->', id_number)  # ATK1 -> 1039008188

    handle = Entrez.efetch(db='Protein', id=id_number, retmode='text', rettype='fasta')
    seq_record = SeqIO.read(handle, 'fasta')

    time.sleep(1)
    return seq_record

out = [fetch(my_term) for my_term in TERMS]

with open('out.fasta', 'w') as f:
    for record in out:
        SeqIO.write(record, f, 'fasta')

Entrez.esearch() 结果以 XML 文档的形式返回，因此我们使用 cElementTree 来解析它。此查询有多个结果，但我们天真地只要求一个 - 您需要通过检查多个结果或提供更具体的术语来解决这个问题。

此外，您的代码还颠倒了 retmode 和 rettype 的值。