mirror of
https://github.com/biopython/biopython.git
synced 2025-10-20 21:53:47 +08:00
129 lines
3.8 KiB
Python
129 lines
3.8 KiB
Python
# Copyright 2001 by Gavin E. Crooks. All rights reserved.
|
|
# Revisions copyright 2010 Jeffrey Finkelstein. All rights reserved.
|
|
#
|
|
# This file is part of the Biopython distribution and governed by your
|
|
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
|
|
# Please see the LICENSE file that should have been included as part of this
|
|
# package.
|
|
"""Handle the SCOP CLAssification file, which describes SCOP domains.
|
|
|
|
The file format is described in the scop
|
|
"release notes.":http://scop.mrc-lmb.cam.ac.uk/scop/release-notes.html
|
|
The latest CLA file can be found
|
|
"elsewhere at SCOP.":http://scop.mrc-lmb.cam.ac.uk/scop/parse/
|
|
|
|
"Release 1.73": http://scop.mrc-lmb.cam.ac.uk/scop/parse/dir.cla.scop.txt_1.73
|
|
(July 2008)
|
|
|
|
"""
|
|
|
|
from . import Residues
|
|
|
|
|
|
class Record:
|
|
"""Holds information for one SCOP domain.
|
|
|
|
Attributes:
|
|
- sid - SCOP identifier. e.g. d1danl2
|
|
- residues - The domain definition as a Residues object
|
|
- sccs - SCOP concise classification strings. e.g. b.1.2.1
|
|
- sunid - SCOP unique identifier for this domain
|
|
- hierarchy - A dictionary, keys are nodetype, values are sunid,
|
|
describing the location of this domain in the SCOP hierarchy. See
|
|
the Scop module for a description of nodetypes. This used to be a
|
|
list of (key,value) tuples in older versions of Biopython (see
|
|
Bug 3109).
|
|
|
|
"""
|
|
|
|
def __init__(self, line=None):
|
|
"""Initialize the class."""
|
|
self.sid = ""
|
|
self.residues = None
|
|
self.sccs = ""
|
|
self.sunid = ""
|
|
self.hierarchy = {}
|
|
if line:
|
|
self._process(line)
|
|
|
|
def _process(self, line):
|
|
line = line.rstrip() # no trailing whitespace
|
|
columns = line.split("\t") # separate the tab-delineated cols
|
|
if len(columns) != 6:
|
|
raise ValueError(f"I don't understand the format of {line}")
|
|
|
|
self.sid, pdbid, residues, self.sccs, self.sunid, hierarchy = columns
|
|
self.residues = Residues.Residues(residues)
|
|
self.residues.pdbid = pdbid
|
|
self.sunid = int(self.sunid)
|
|
|
|
for ht in hierarchy.split(","):
|
|
key, value = ht.split("=")
|
|
self.hierarchy[key] = int(value)
|
|
|
|
def __str__(self):
|
|
"""Represent the SCOP classification record as a tab-separated string."""
|
|
s = []
|
|
s.append(self.sid)
|
|
s += str(self.residues).split(" ")
|
|
s.append(self.sccs)
|
|
s.append(self.sunid)
|
|
|
|
s.append(
|
|
",".join(
|
|
"=".join((key, str(value))) for key, value in self.hierarchy.items()
|
|
)
|
|
)
|
|
|
|
return "\t".join(map(str, s)) + "\n"
|
|
|
|
|
|
def parse(handle):
|
|
"""Iterate over a CLA file as Cla records for each line.
|
|
|
|
Arguments:
|
|
- handle - file-like object.
|
|
|
|
"""
|
|
for line in handle:
|
|
if line.startswith("#"):
|
|
continue
|
|
yield Record(line)
|
|
|
|
|
|
class Index(dict):
|
|
"""A CLA file indexed by SCOP identifiers for rapid random access."""
|
|
|
|
def __init__(self, filename):
|
|
"""Create CLA index.
|
|
|
|
Arguments:
|
|
- filename - The file to index
|
|
|
|
"""
|
|
dict.__init__(self)
|
|
self.filename = filename
|
|
with open(self.filename) as f:
|
|
position = 0
|
|
while True:
|
|
line = f.readline()
|
|
if not line:
|
|
break
|
|
if line.startswith("#"):
|
|
continue
|
|
record = Record(line)
|
|
key = record.sid
|
|
if key is not None:
|
|
self[key] = position
|
|
position = f.tell()
|
|
|
|
def __getitem__(self, key):
|
|
"""Return an item from the indexed file."""
|
|
position = dict.__getitem__(self, key)
|
|
|
|
with open(self.filename) as f:
|
|
f.seek(position)
|
|
line = f.readline()
|
|
record = Record(line)
|
|
return record
|