Extracting only the chains that we need from a PDB file

问题

I need to extract specific chains from PDB files( Sometiems more than one chain). How to extract chains from a PDB file?. It's the same question and "marked" answer, answers my problem. But it does not work in python 3. It gives errors one after the other. Does anybody knows how can i work this in python 3?

Or any other code for the same kind of problem

Thank you in advance.

import os
from Bio import PDB


class ChainSplitter:
    def __init__(self, out_dir=None):
        """ Create parsing and writing objects, specify output directory. """
        self.parser = PDB.PDBParser()
        self.writer = PDB.PDBIO()
        if out_dir is None:
            out_dir = os.path.join(os.getcwd(), "chain_PDBs")
        self.out_dir = out_dir

    def make_pdb(self, pdb_path, chain_letters, overwrite=False, struct=None):
        """ Create a new PDB file containing only the specified chains.

        Returns the path to the created file.

        :param pdb_path: full path to the crystal structure
        :param chain_letters: iterable of chain characters (case insensitive)
        :param overwrite: write over the output file if it exists
        """
        chain_letters = [chain.upper() for chain in chain_letters]

        # Input/output files
        (pdb_dir, pdb_fn) = os.path.split(pdb_path)
        pdb_id = pdb_fn[3:7]
        out_name = "pdb%s_%s.ent" % (pdb_id, "".join(chain_letters))
        out_path = os.path.join(self.out_dir, out_name)
        print ("OUT PATH:",out_path)
        plural = "s" if (len(chain_letters) > 1) else ""  # for printing

        # Skip PDB generation if the file already exists
        if (not overwrite) and (os.path.isfile(out_path)):
            print("Chain%s %s of '%s' already extracted to '%s'." %
                    (plural, ", ".join(chain_letters), pdb_id, out_name))
            return out_path

        print("Extracting chain%s %s from %s..." % (plural,
                ", ".join(chain_letters),  pdb_fn))

        # Get structure, write new file with only given chains
        if struct is None:
            struct = self.parser.get_structure(pdb_id, pdb_path)
        self.writer.set_structure(struct)
        self.writer.save(out_path, select=SelectChains(chain_letters))

        return out_path


class SelectChains(PDB.Select):
    """ Only accept the specified chains when saving. """
    def __init__(self, chain_letters):
        self.chain_letters = chain_letters

    def accept_chain(self, chain):
        return (chain.get_id() in self.chain_letters)


if __name__ == "__main__":
    """ Parses PDB id's desired chains, and creates new PDB structures. """
    import sys
    if not len(sys.argv) == 2:
        print ("Usage: $ python %s 'pdb.txt'" % __file__)
        sys.exit()

    pdb_textfn = sys.argv[1]

    pdbList = PDB.PDBList()
    splitter = ChainSplitter("/home/patrick/Desktop/chain_splitting")

    with open(pdb_textfn) as pdb_textfile:
        for line in pdb_textfile:
            pdb_id = line[:4].lower()
            chain = line[4]
            pdb_fn = pdbList.retrieve_pdb_file(pdb_id)
            splitter.make_pdb(pdb_fn, chain)

回答1:

retrieve_pdb_file has the optional parameter file_format. When no information is provided, the PDB server returns cif files. Biopython's parser expects a PDB file.

You can change the line to

pdbList.retrieve_pdb_file(pdb_id, file_format='pdb')

and you should get a PDB file and the rest of the code runs through..

来源：https://stackoverflow.com/questions/57543344/extracting-only-the-chains-that-we-need-from-a-pdb-file

标签

python-3.x

bioinformatics

biopython