Question

所以我在python中使用Biopython和Clustalw2进行一些生物信息学工作来对齐蛋白质序列。我是相当新的（只有几个月的经验），我遇到了使用stdout和迭代整个目录的问题。任何帮助将不胜感激。

所以我写了这个，它一次处理一个文件并产生所需的结果......

#!/usr/bin/python

import Bio
import os
from Bio.Align.Applications import ClustalwCommandline
from Bio import Seq
from Bio import SeqIO
from Bio import AlignIO
from Bio.SeqRecord import SeqRecord


clustal_loc=r"/Users/Wes/Desktop/eggNOG_files/clustalw-2.1-macosx/clustalw2"
try:
    f_in=raw_input("Enter the filepath of the FASTA to align: ")
    f_out= raw_input("Enter the output filename: ")
    fh= open(f_in)
    fo=open(f_out,'w')
    for record in SeqIO.parse(fh,"fasta"):
            id = record.id
            seq = record.seq
            print("Name: %s, size: %s"%(id,len(seq)))
    try:
            cl = ClustalwCommandline(clustal_loc,infile=f_in, outfile=f_out, align=True, outorder="ALIGNED", convert=True, output="pir")
            assert os.path.isfile(clustal_loc), "Clustal W not found"
            stdout, stderr = cl()
            print cl
    except:
            print("There was a problem aligning. Check ClustalW path and .fasta input.")


    fh.close()
    fo.close()


except:
        print("Could not parse. Check to make sure filepath is correct and that file is in   FASTA format")

......这似乎工作得很好。问题来自于我尝试在整个目录上迭代这个问题（比如需要对齐的1000多个蛋白质序列文件。我知道问题是stdout，但我现在有点太业余了解知道如何修复它这是下面的破解代码 -

/usr/bin/python

import Bio
import os
from Bio.Align.Applications import ClustalwCommandline
from Bio import Seq
from Bio import SeqIO
from Bio import AlignIO
from Bio.SeqRecord import SeqRecord
import subprocess
from subprocess import Popen
clustal_loc=r"/Users/Wes/Desktop/eggNOG_files/clustalw-2.1-macosx/clustalw2"

try:

    folder= raw_input("Enter the folder of .fasta files to iterate over and align: ")
    listing = os.listdir(folder)

    for infile in listing:
        print folder+'/'+infile
        f_in = open(folder+'/'+infile,'r')

        f_out=open(folder+'/'+infile+".pir",'w')


        for record in SeqIO.parse(f_in,"fasta"):
                id = record.id
                seq = record.seq
                print("Name: %s, size: %s"%(id,len(seq)))

        clustalw_cline= ClustalwCommandline(clustal_loc,infile=f_in, outfile=f_out, align=True, outorder="ALIGNED", convert=True, output="pir")

        assert os.path.isfile(clustal_loc), "Clustal W not found"
        saveout = sys.stdout
        sys.stdout = clustalw_cline()
        sys.stdout = saveout






        f_in.close()

        f_out.close()
except:
    print("There was a problem aligning. Check ClustalW path and .fasta folder format/location")

正如你所看到的那样，我一直在捣乱这个。感谢您提供的任何帮助。

Answer 1

您看到的错误究竟是什么？您不应该将sys.sterr和sys.stdout设置为字符串值（clustalw_cline（）函数将clustal stderr和stdout作为字符串返回），因为您无法从python向stdout写入任何内容。

我尝试清理并更正下面的代码。

#!/usr/bin/env python

import Bio
import os
from glob import glob
from Bio.Align.Applications import ClustalwCommandline
from Bio import Seq
from Bio import SeqIO
from Bio import AlignIO
from Bio.SeqRecord import SeqRecord
import subprocess
from subprocess import Popen
clustal_loc=r"/Users/Wes/Desktop/eggNOG_files/clustalw-2.1-macosx/clustalw2"

try:
    folder= raw_input("Enter the folder of .fasta files to iterate over and align: ")
    listing = glob(os.path.join(folder, '*.fasta'))
    for infile in listing:
        print infile
        with open(os.path.splitext(infile) + '.pir') as f_out:
            with open(infile) as f_in:
                for record in SeqIO.parse(infile,"fasta"):
                        id = record.id
                        seq = record.seq
                        print("Name: %s, size: %s"%(id,len(seq)))
                assert os.path.isfile(clustal_loc), "Clustal W not found"
                clustalw_cline= ClustalwCommandline(clustal_loc,infile=f_in,
                                                    outfile=f_out, align=True, 
                                                    outorder="ALIGNED",convert=True, output="pir")
                stdout, stderr = clustalw_cline()
except Exception:
    print("There was a problem aligning. Check ClustalW path and .fasta folder format/location")

生物信息学脚本使用Python / Biopython / Clustalw使用stdout迭代蛋白质目录

1 个答案: