Logo Search packages:      
Sourcecode: python-biopython version File versions  Download package

# Copyright 2001 by Gavin E. Crooks.  All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license.  Please see the LICENSE file that should have been included
# as part of this package.

""" Handle the SCOP DEScription file.

The file format is described in the scop
"release notes.":http://scop.berkeley.edu/release-notes-1.55.html 
The latest DES file can be found
"elsewhere at SCOP.":http://scop.mrc-lmb.cam.ac.uk/scop/parse/
"Release 1.55":http://scop.berkeley.edu/parse/des.cla.scop.txt_1.55 (July 2001)

00018 class Record(object):
    """Holds information for one node in the SCOP hierarchy.

    sunid       -- SCOP unique identifiers

    nodetype    -- One of 'cl' (class), 'cf' (fold), 'sf' (superfamily),
                   'fa' (family), 'dm' (protein), 'sp' (species),
                   'px' (domain). Additional node types may be added.

    sccs        -- SCOP concise classification strings. e.g. b.1.2.1

    name        -- The SCOP ID (sid) for domains (e.g. d1anu1),
                   currently empty for other node types

    description --  e.g. "All beta proteins","Fibronectin type III", 
    def __init__(self, line=None):
        self.sunid = ''
        self.nodetype = ''
        self.sccs = ''
        self.name = ''
        self.description =''
        if line:
00044     def _process(self, line):
        """Parses DES records.
        Records consist of 5 tab deliminated fields,
        sunid, node type, sccs, node name, node description.
        #For example ::
        #21953   px      b.1.2.1 d1dan.1 1dan T:,U:91-106
        #48724   cl      b       -       All beta proteins
        #48725   cf      b.1     -       Immunoglobulin-like beta-sandwich
        #49265   sf      b.1.2   -       Fibronectin type III
        #49266   fa      b.1.2.1 -       Fibronectin type III

        line = line.rstrip()  # no trailing whitespace
        columns = line.split("\t")  # separate the tab-delineated cols
        if len(columns) != 5:
            raise ValueError("I don't understand the format of %s" % line)
        sunid, self.nodetype, self.sccs, self.name, self.description = columns
        if self.name=='-': self.name =''
        self.sunid = int(sunid)

    def __str__(self):
        s = []
        if self.name:
        return "\t".join(map(str,s)) + "\n"

def parse(handle):
    """Iterates over a DES file, returning a Des record for each line
    in the file.

        handle -- file-like object
    for line in handle:
        if line.startswith('#'):
        yield Record(line)

Generated by  Doxygen 1.6.0   Back to index