Source code for parsers.cnver

# Parser for CNVer output CNV calls.

import re
import os

import cnv_struct
import parsers

# This file is part of CNVAnalysisToolkit.
# 
# CNVAnalysisToolkit is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# 
# CNVAnalysisToolkit is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# You should have received a copy of the GNU General Public License
# along with CNVAnalysisToolkit.  If not, see <http://www.gnu.org/licenses/>.

__author__ = "Marc-Andre Legault (StatGen)"
__copyright__ = "Copyright (C) 2013 StatGen"
__license__ = "GNU General Public License v3 (GPL-3)"

class Parser(parsers.ParentParser):
    """Creates the CNV dictionary for a given family for calls from the CNVer algorithm.
    
    Medvedev, P., Fiume, M., Smith, T., Brudno, M. (2010). Detecting copy number variation with mated short reads, `Genome Research`, **20**:1613-1622. 

    """
    def __init__(self, family_root):
        super(Parser, self).__init__(family_root)

    def get_cnvs(self):
        # cnvs = { "twin1": {1: [cnvs_for_chr1, ],
        #                    2: [cnvs_for_chr2, ],
        #                           ...
        #                   }
        #           "twin2": ... }

        for sample in self.paths:
            self.cnvs[sample] = {}

            for i in xrange(1, 23):
                self.cnvs[sample][i] = []

                chr_file = os.path.join(
                                            self.family_root,
                                            self.paths[sample],
                                            "calls",
                                            "chr{}.cnvs".format(i)
                                       )

                cols = ["chr", "start", "end", "cnv_type", "doc"]

                with open(chr_file) as f:
                    for line in f:
                        line = line.rstrip("\r\n")
                        fields = dict(zip(cols, line.split("\t")))
                        pos = "{chr}:{start}-{end}".format(**fields)

                        doc = None
                        try:
                            doc = float(fields["doc"])
                        except Exception as e:
                            print ("An error occured while trying to parse "
                                   "the following line: ")
                            print line
                            print
                            print ("From the file:")
                            print f
                            print
                            raise e
                            
                        cnv_builder = {
                                        "pos": pos,
                                        "type": fields["cnv_type"],
                                        "algo": "cnver",
                                        "doc": doc,
                                        "source": sample
                                      }

                        cnv = cnv_struct.cnv(**cnv_builder)
                        self.cnvs[sample][i].append(cnv)

        return self.cnvs