view commons/core/parsing/CoordsParser.py @ 64:783e6ed4eb66

Minor bug correction. Added casts to str in Galaxy XML files. Also closed the writer in the Python script "changeTagName."
author m-zytnicki
date Mon, 19 Oct 2015 14:16:44 +0200
parents 769e306b7933
children
line wrap: on
line source

#
# Copyright INRA-URGI 2009-2010
# 
# This software is governed by the CeCILL license under French law and
# abiding by the rules of distribution of free software. You can use,
# modify and/ or redistribute the software under the terms of the CeCILL
# license as circulated by CEA, CNRS and INRIA at the following URL
# "http://www.cecill.info".
# 
# As a counterpart to the access to the source code and rights to copy,
# modify and redistribute granted by the license, users are provided only
# with a limited warranty and the software's author, the holder of the
# economic rights, and the successive licensors have only limited
# liability.
# 
# In this respect, the user's attention is drawn to the risks associated
# with loading, using, modifying and/or developing or reproducing the
# software by the user in light of its specific status of free software,
# that may mean that it is complicated to manipulate, and that also
# therefore means that it is reserved for developers and experienced
# professionals having in-depth computer knowledge. Users are therefore
# encouraged to load and test the software's suitability as regards their
# requirements in conditions enabling the security of their systems and/or
# data to be ensured and, more generally, to use and operate it in the
# same conditions as regards security.
# 
# The fact that you are presently reading this means that you have had
# knowledge of the CeCILL license and that you accept its terms.
#
import re
import sys
from SMART.Java.Python.structure.Mapping import Mapping
from commons.core.parsing.MapperParser import MapperParser
from SMART.Java.Python.structure.SubMapping import SubMapping
from SMART.Java.Python.misc import Utils

class CoordsParser(MapperParser):
    """A class that parses the .coords output of Nucmer"""

    def __init__(self, fileName, verbosity = 0):
        self._lineParseRe = re.compile(r"^\s*(?P<tStart>\d+)\s+(?P<tEnd>\d+)\s+\|\s+(?P<qStart>\d+)\s+(?P<qEnd>\d+)\s+\|\s+(?P<tLength>\d+)\s+(?P<qLength>\d+)\s+\|\s+(?P<identity>\d+\.?\d*)\s+\|\s+(?P<tName>[\w\|\:\-]+)\s+(?P<qName>.*)\s*$")
        self._lineParseRe2 = re.compile(r"^\s*(?P<tStart>\d+)\s+(?P<tEnd>\d+)\s+(?P<qStart>\d+)\s+(?P<qEnd>\d+)\s+(?P<tLength>\d+)\s+(?P<qLength>\d+)\s+(?P<identity>\d+\.?\d*)\s+(?P<rlen>\d+\.?\d*)\s+(?P<qlen>\d+\.?\d*)\s+(?P<rcov>\d+\.?\d*)\s+(?P<qcov>\d+\.?\d*)\s+(?P<rframe>[-]?\d+\.?\d*)\s+(?P<qframe>[-]?\d+\.?\d*)\s+(?P<tName>[\w\|\:\-]+)\s+(?P<qName>.*)\s*$")
        self._lineParseRe3 = re.compile(r"^\s*(?P<tStart>\d+)\s+(?P<tEnd>\d+)\s+\|\s+(?P<qStart>\d+)\s+(?P<qEnd>\d+)\s+\|\s+(?P<tLength>\d+)\s+(?P<qLength>\d+)\s+\|\s+(?P<identity>\d+\.?\d*)\s+(?P<sim>\d+\.?\d*)\s+(?P<stp>\d+\.?\d*)\s+\|\s+(?P<rframe>[-]?\d+\.?\d*)\s+(?P<qframe>[-]?\d+\.?\d*)\s+(?P<tName>[\w\|\:\-]+)\s+(?P<qName>.*)\s*$")
        self._lineParseRe4 = re.compile(r"^\s*(?P<tStart>\d+)\s+(?P<tEnd>\d+)\s+(?P<qStart>\d+)\s+(?P<qEnd>\d+)\s+(?P<tLength>\d+)\s+(?P<qLength>\d+)\s+(?P<identity>\d+\.?\d*)\s+(?P<sim>\d+\.?\d*)\s+(?P<stp>\d+\.?\d*)\s+(?P<rlen>\d+\.?\d*)\s+(?P<qlen>\d+\.?\d*)\s+(?P<rcov>\d+\.?\d*)\s+(?P<qcov>\d+\.?\d*)\s+(?P<rframe>[-]?\d+\.?\d*)\s+(?P<qframe>[-]?\d+\.?\d*)\s+(?P<tName>[\w\|\:\-]+)\s+(?P<qName>.*)\s*$")
        self.lineType = 1
        MapperParser.__init__(self, fileName, verbosity)
        
    def getFileFormats():
        return ["coords"]
    getFileFormats = staticmethod(getFileFormats)

    def skipFirstLines(self):    
        while True: 
            line = self.handle.readline()
            self.currentLineNb += 1
            if line == "":
                break
            if "=====" in line:
                break
            if "[S1]\t[E1]\t[S2]\t[E2]\t[LEN 1]\t[LEN 2]\t[% IDY]\t[LEN R]\t[LEN Q]\t[COV R]\t[COV Q]\t[FRM]\t[TAGS]" in line:
                self.lineType = 2
                break
            if "[S1]     [E1]  |     [S2]     [E2]  |  [LEN 1]  [LEN 2]  |  [% IDY]  [% SIM]  [% STP]  | [FRM]  [TAGS]" in line:
                self.lineType = 3
           
            if "[% IDY]\t[% SIM]\t[% STP]" in line and "[LEN Q]"in line:
                self.lineType = 4 
                break     
        
    def parseLine(self, line):
        
        if self.lineType == 1 : 
            m = self._lineParseRe.search(line)
        elif self.lineType == 2:
            m = self._lineParseRe2.search(line)
        elif self.lineType == 3:
            m = self._lineParseRe3.search(line)
        elif self.lineType == 4:
            m = self._lineParseRe4.search(line)
        if m == None:
            sys.exit("\nLine %d '%s' does not have a NucMer format" % (self.currentLineNb, line))
  
        mapping = Mapping()
        
        subMapping = SubMapping()
        subMapping.queryInterval.setName(m.group("qName"))
        subMapping.queryInterval.setStart(min(int(m.group("qStart")), int(m.group("qEnd"))))
        subMapping.queryInterval.setEnd(max(int(m.group("qStart")), int(m.group("qEnd"))))
        subMapping.queryInterval.setSize(int(m.group("qLength")))
        subMapping.queryInterval.setDirection(int(m.group("qEnd")) - int(m.group("qStart")))
        
        subMapping.targetInterval.setChromosome(m.group("tName"))
        subMapping.targetInterval.setStart(min(int(m.group("tStart")), int(m.group("tEnd"))))
        subMapping.targetInterval.setEnd(max(int(m.group("tStart")), int(m.group("tEnd"))))
        subMapping.targetInterval.setSize(int(m.group("tLength")))
        subMapping.targetInterval.setDirection(int(m.group("tEnd")) - int(m.group("tStart")))
       
        subMapping.setDirection(int(m.group("qEnd")) - int(m.group("qStart")))
        subMapping.setSize(min(int(m.group("qLength")), int(m.group("tLength"))))
        subMapping.setIdentity(float(m.group("identity")))
        
        mapping.addSubMapping(subMapping)
        mapping.targetInterval.setStart(min(int(m.group("tStart")), int(m.group("tEnd"))))
        mapping.targetInterval.setEnd(max(int(m.group("tStart")), int(m.group("tEnd"))))
        mapping.targetInterval.setSize(int(m.group("tLength")))
        mapping.targetInterval.setChromosome(m.group("tName"))
         
        mapping.queryInterval.setStart(min(int(m.group("qStart")), int(m.group("qEnd"))))
        mapping.queryInterval.setEnd(max(int(m.group("qStart")), int(m.group("qEnd"))))
        mapping.queryInterval.setSize(int(m.group("qLength")))
        mapping.queryInterval.setName(m.group("qName"))
        mapping.setDirection(int(m.group("qEnd")) - int(m.group("qStart")))
        mapping.setSize(min(int(m.group("qLength")), int(m.group("tLength"))))
        mapping.setIdentity(float(m.group("identity")))
        mapping.setTagValue("feature", "match")
        mapping.setTagValue("Target", "%s %d %d" % (m.group("qName"), int(m.group("qStart")), int(m.group("qEnd"))))
                    
        if self.lineType ==2 or self.lineType ==4:
            mapping.setTagValue("target_pident", float(m.group("identity")))
            mapping.setTagValue("target_pcover", float(m.group("qcov")))
            mapping.setTagValue("target_length", int(m.group("qlen")))
            
        
# Specific to Mark Work. Commented lines because of possible slowdown.                 
#        for line in self.handle:
#            string1 = line.strip()
#            self.currentLineNb += 1
#            break
#        for line in self.handle:
#            string2 = line.strip()
#            self.currentLineNb += 1
#            break
#        print(len(string1),len(string2))
#        mapping.setNbMismatches(Utils.getHammingDistance(string1, string2))
        mapping.setNbGaps(0)

        return mapping