def __init__(self, orthofinderWorkingDir_list, speciesToUse, nSpAll, qAddSpeciesToIDs, idExtractor = util.FirstWordExtractor):
self.speciesIDsEx = util.FullAccession(files.FileHandler.GetSpeciesIDsFN())
self._Spec_SeqIDs = None
self._extractor = idExtractor
self.seqIDsEx = None
self.ogs_all = None
self.iOgs4 = 0
self.speciesToUse = speciesToUse # list of ints
self.seqsInfo = util.GetSeqsInfo(orthofinderWorkingDir_list, self.speciesToUse, nSpAll)
self.id_to_og = None
self.qAddSpeciesToIDs = qAddSpeciesToIDs
def SequenceDict(self):
if self.seqIDsEx == None:
try:
self.seqIDsEx = self._extractor(self.seqIDsFN)
except RuntimeError as error:
print(error.message)
if error.message.startswith("ERROR"):
util.Fail()
else:
print("Tried to use only the first part of the accession in order to list the sequences in each orthogroup\nmore concisely but these were not unique. The full accession line will be used instead.\n")
self.seqIDsEx = util.FullAccession(self.seqIDsFN)
return self.seqIDsEx.GetIDToNameDict()
def __init__(self, orthofinderWorkingDir, speciesToUse, nSpAll, clustersFilename_pairs, idExtractor = util.FirstWordExtractor, pickleDir=None):
self.workingDirOF = orthofinderWorkingDir
self.seqIDsFN = orthofinderWorkingDir + "SequenceIDs.txt"
self.speciesIDsFN = orthofinderWorkingDir + "SpeciesIDs.txt"
self.speciesIDsEx = util.FullAccession(self.speciesIDsFN)
self._Spec_SeqIDs = None
self._extractor = idExtractor
self.clustersFN = clustersFilename_pairs
self.seqIDsEx = None
self.ogs_all = None
self.iOgs4 = 0
self.speciesToUse = speciesToUse
self.seqsInfo = util.GetSeqsInfo(orthofinderWorkingDir, self.speciesToUse, nSpAll)
self.fileInfo = util.FileInfo(workingDir = orthofinderWorkingDir, graphFilename="", separatePickleDir=pickleDir)
self.id_to_og = None
def GetSpeciesDict(self):
d = util.FullAccession(self.GetSpeciesIDsFN()).GetIDToNameDict()
return {k: v.rsplit(".", 1)[0] for k, v in d.items()}