个人学习随笔

下面是我自己最近所学习的知识。

之前自己处理的数据集发现了大问题，现在又重新处理。

关于从pdb数据库中提取一级序列

定义一个PDBparser类，定义parsePrimaryStructure（）函数，用pdbparser.parsePrimaryStructure(file)实现一级序列提取的功能。

import json;
class PDBparser():
def parse(self,PDBfile,indent = False):
'''
@return: The full information parsed from the PDBFile
@param PDBFile: The full path of the PDB file, str
'''
content = {} # The full information parsed from the PDBFile
priStructure = content['primary_structure'] = []  # The primary structure parsed from the PDBFile
tertiary_structure = content['tertiary_structure'] ={}
terStructure = tertiary_structure['chains'] = [] # The teritary structure parsed from the PDBFile
#residueindexlist = set()
lines = self.__loadPDBfile(PDBfile)
langthinformation = self.__parseLine(lines,content)
if indent:
return content,langthinformation # for test
else:
return content
def parsePrimaryStructure(self,PDBfile):
'''
@return: The full information parsed from the PDBFile
@param PDBFile: The full path of the PDB file, str
'''
priStructure = []; # The primary structure parsed from the PDBFile
lines = self.__loadPDBfile(PDBfile)
for line in lines:
header = line.split()[0]
if header == 'SEQRES':
self.__parsePriLine(line, priStructure)
return priStructure

定义main函数

if __name__ == "__main__":
print('please input the path of the PDBfile:such as E:\\pdb\\pdb3rum.ent')#输入pdb文件
file=input()
pdbparser = PDBparser()
#content = pdbparser.parseTertiaryStructure(file)
content = pdbparser.parsePrimaryStructure(file)
formatinput = json.dumps(content, indent=1)
print(formatinput)
print("Done")