def addTranslateIDInIBDCheckResultJob(self, workflow=None, plinkIBDCheckOutputFile=None, pop_country_id_ls_str=None, \
pop_site_id_ls_str=None, popHeader=None,\
readGroupFile=None, parentJobLs=None, sampleIDHeader='sampleID',\
transferOutput=False):
"""
2012.10.24
moved from popgen/CompareAlleleFrequencyOfTwoPopulationFromOneVCFFolder.py
2012.10.15
"""
job = None
if plinkIBDCheckOutputFile:
pop_country_id_set = set(getListOutOfStr(pop_country_id_ls_str))
pop_site_id_set = set(getListOutOfStr(pop_site_id_ls_str))
if 447 in pop_site_id_set or 135 in pop_country_id_set: #either site = VRC or country = USA
commonPrefix = os.path.splitext(plinkIBDCheckOutputFile.name)[0]
outputFile = File('%s_%s_withReadGroup.tsv'%(commonPrefix, popHeader))
extraArgumentList = [" --readGroupFname", readGroupFile, "--readGroupHeader %s"%(sampleIDHeader), \
'--replaceColumnHeaderLs IID1,IID2']
job = self.addAbstractMatrixFileWalkerJob(workflow=workflow, executable=self.ReplaceIndividualIDInMatrixFileWithReadGroup, \
inputFileList=None, inputFile=plinkIBDCheckOutputFile, outputFile=outputFile, \
outputFnamePrefix=None, whichColumn=None, whichColumnHeader=sampleIDHeader, \
minNoOfTotal=0,\
samplingRate=1.0, \
parentJob=None, parentJobLs=parentJobLs, \
extraDependentInputLs=[readGroupFile], \
extraArgumentList=extraArgumentList, transferOutput=transferOutput, job_max_memory=1000,\
sshDBTunnel=self.needSSHDBTunnel, \
objectWithDBArguments=self,)
return job
def __init__(self, **keywords):
"""
2011-7-11
"""
AbstractVariationWorkflow.__init__(self, **keywords)
if getattr(self, 'result_id_ls', None):
self.result_id_ls = getListOutOfStr(self.result_id_ls,
data_type=int)
self.result_id_ls.sort()
else:
self.result_id_ls = []
if getattr(self, 'analysis_method_id_ls', None):
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.analysis_method_id_ls.sort()
else:
self.analysis_method_id_ls = []
if getattr(self, 'phenotype_method_id_ls', None):
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.phenotype_method_id_ls.sort()
else:
self.phenotype_method_id_ls = []
def __init__(self, **keywords):
"""
2012.6.5
to replace MpiAssociation.py
"""
AbstractVariationWorkflow.__init__(self, **keywords)
if getattr(self, 'call_method_id_ls', None):
self.call_method_id_ls = getListOutOfStr(self.call_method_id_ls,
data_type=int)
self.call_method_id_ls.sort()
else:
self.call_method_id_ls = []
if getattr(self, 'analysis_method_id_ls', None):
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.analysis_method_id_ls.sort()
else:
self.analysis_method_id_ls = []
if getattr(self, 'phenotype_method_id_ls', None):
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.phenotype_method_id_ls.sort()
else:
self.phenotype_method_id_ls = []
def __init__(self, **keywords):
"""
2008-11-10
"""
ProcessOptions.process_function_arguments(
keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self
)
if self.phenotype_method_id_ls:
self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
self.which_PC_index_ls = getListOutOfStr(self.which_PC_index_ls, data_type=int)
self.run_whole_matrix = {
1: self._kruskal_wallis_whole_matrix,
2: self.LM_whole_matrix,
3: self.Emma_whole_matrix,
4: self.LM_with_PCs_whole_matrix,
5: self.LM_with_PCs_whole_matrix,
6: self.LM_with_PCs_whole_matrix,
7: self.Emma_whole_matrixForNoNAGenotypeMatrix,
8: self.EMMAX,
}
self.output_results = {
1: self.output_kw_results,
2: self.output_lm_results,
3: self.output_lm_results,
7: self.output_emma_results,
}
def __init__(self, **keywords): """ 2009-1-5 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords): """ 2008-08-20 """ TopSNPTest.__init__(self, **keywords) self.list_type_id_ls = getListOutOfStr(self.list_type_id_ls, data_type=int) self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords): """ 2008-04-08 """ from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.analysis_method_id_ls: self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) if self.phenotype_method_id_ls: self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2008-08-20
"""
TopSNPTest.__init__(self, **keywords)
self.list_type_id_ls = getListOutOfStr(self.list_type_id_ls,
data_type=int)
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords): """ 2008-11-19 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls, data_type=int) self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) if self.output_dir and not os.path.isdir(self.output_dir): os.makedirs(self.output_dir)
def __init__(self, **keywords):
"""
2008-11-19
"""
AbstractVariationMappe.__init__(self, **keywords)
self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls,
data_type=int)
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
if self.output_dir and not os.path.isdir(self.output_dir):
os.makedirs(self.output_dir)
def __init__(self, **keywords):
RunGADA.__init__(self, **keywords)
self.aAlpha_ls = getListOutOfStr(self.aAlpha_ls, data_type=float)
self.TBackElim_ls = getListOutOfStr(self.TBackElim_ls, data_type=float)
self.MinSegLen_ls = getListOutOfStr(self.MinSegLen_ls, data_type=int)
# 2010-5-30
self.communicator = MPI.world.duplicate()
MPIwrapper.__init__(self,
self.communicator,
debug=self.debug,
report=self.report)
def __init__(self, **keywords):
"""
2008-11-10
"""
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.cofactors = getListOutOfStr(self.cofactors, data_type=str)
self.cofactor_phenotype_id_ls = getListOutOfStr(
self.cofactor_phenotype_id_ls, data_type=int)
def __init__(self, **keywords): """ 2012.2.8 """ AbstractNGSWorkflow.__init__(self, **keywords) if self.isq_id_ls: self.isq_id_ls = getListOutOfStr(self.isq_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2008-07-05
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, \
error_doc=self.__doc__, class_to_have_attr=self)
self.getIntensityFuncDict = {
1: self.getQCIntensityLs,
2: self.getIntensityLsFromOutputGivenProbeSubset,
3: self.getAllIntensityFromArray
}
self.xlim = getListOutOfStr(self.xlim, data_type=float)
self.array_id_ls = getListOutOfStr(self.array_id_ls, int)
def __init__(self, **keywords): """ 2008-04-08 """ from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.array_id_ls: self.array_id_ls = getListOutOfStr(self.array_id_ls, data_type=str)
def __init__(self, **keywords):
"""
2011-7-11
"""
AbstractVervetWorkflow.__init__(self, **keywords)
if self.ind_seq_id_ls:
self.ind_seq_id_ls = getListOutOfStr(self.ind_seq_id_ls, data_type=int)
def __init__(self, **keywords): """ 2008-05-11 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.ecotype_id_ls: self.ecotype_id_ls = getListOutOfStr(self.ecotype_id_ls, data_type=str) #str because ecotype ids in SNPData are not converted to integers
def __init__(self, **keywords):
"""
2010-3-8
add argument min_score, phenotype_id_ls
2009-2-16
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls,
data_type=int)
def __init__(self, **keywords):
"""
2008-10-20
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.results_method_id_ls = getListOutOfStr(self.results_method_id_ls,
data_type=int)
self.list_type_id_ls = getListOutOfStr(self.list_type_id_ls,
data_type=int)
if self.output_dir and not os.path.isdir(self.output_dir):
os.makedirs(self.output_dir)
def __init__(self, **keywords):
"""
2008-08-27
inherit from TopSNPTest
"""
TopSNPTest.__init__(self, **keywords)
if self.phenotype_method_id_ls:
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2012.2.28
"""
AbstractVariationWorkflow.__init__(self, **keywords)
self.inputFolder = os.path.abspath(self.inputFolder)
if getattr(self, 'analysis_method_id_ls', None):
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.analysis_method_id_ls.sort()
else:
self.analysis_method_id_ls = []
if getattr(self, 'phenotype_method_id_ls', None):
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.phenotype_method_id_ls.sort()
else:
self.phenotype_method_id_ls = []
def __init__(self, inputFnameLs, **keywords):
"""
"""
AbstractVariationMapper.__init__(self, inputFnameLs, **keywords)
if self.list_type_id_list:
self.list_type_id_list = getListOutOfStr(self.list_type_id_list,
data_type=int)
else:
self.list_type_id_list = []
self.result_id_peak_type_id_ls = getListOutOfStr(
self.result_id_peak_type_id_ls, data_type=str)
result_id_peak_type_id_ls = []
for result_id_peak_type_id in self.result_id_peak_type_id_ls:
result_id_peak_type_id = result_id_peak_type_id.split(':')
result_id_peak_type_id = map(int, result_id_peak_type_id)
result_id_peak_type_id_ls.append(result_id_peak_type_id)
self.result_id_peak_type_id_ls = result_id_peak_type_id_ls
def __init__(self, **keywords): """ 2008-11-25 change option phenotype_index_ls to phenotype_method_id_ls to pick phenotypes. phenotype_method_id is more intuitive. """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.phenotype_method_id_ls is not None: self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
def __init__(self, inputFnameLs, **keywords):
"""
"""
AssociationPeak2AssociationLocus.__init__(self, inputFnameLs,
**keywords)
self.call_method_id_ls = getListOutOfStr(self.call_method_id_ls,
data_type=int)
self.analysis_method_id_ls = getListOutOfStr(
self.analysis_method_id_ls, data_type=int)
self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls,
data_type=int)
self.phenotype_id_ls.sort()
self.result_peak_type_id_ls = getListOutOfStr(
self.result_peak_type_id_ls, data_type=int)
self.phenotype_id_set = set(self.phenotype_id_ls)
self.call_method_id_set = set(self.call_method_id_ls)
self.analysis_method_id_set = set(self.analysis_method_id_ls)
def __init__(self, inputFnameLs=None, **keywords): """ """ AbstractVariationMapper.__init__(self, inputFnameLs=inputFnameLs, **keywords) AbstractPlot.__init__(self, inputFnameLs=inputFnameLs, **keywords) if self.list_type_id_list: self.list_type_id_list = getListOutOfStr(self.list_type_id_list, data_type=int) else: self.list_type_id_list = []
def __init__(self, **keywords): """ 2008-07-01 chop off most functions, inherit from QC_250k 2008-04-20 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.call_info_id_ls: self.call_info_id_ls = getListOutOfStr(self.call_info_id_ls, data_type=int) self.QCMethod_class = QCMethod
def __init__(self, **keywords): """ 2012.3.29 default to stage out final output. Argument stageOutFinalOutput morphs into notStageOutFinalOutput. 2011-7-11 """ ShortRead2AlignmentWorkflow.__init__(self, **keywords) if self.ind_seq_id_ls: self.ind_seq_id_ls = getListOutOfStr(self.ind_seq_id_ls, data_type=int)
def __init__(self, **keywords): """ 2011-7-11 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) if self.ind_seq_id_ls: self.ind_seq_id_ls = getListOutOfStr(self.ind_seq_id_ls, data_type=int) self.vervetSrcPath = self.vervetSrcPath%self.home_path
def __init__(self, **keywords):
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.jumpStep is None:
self.jumpStep = self.blockSize / 4
if self.minNoOfProbesPerBlock is None:
self.minNoOfProbesPerBlock = self.blockSize * self.blockSize / 6
self.array_id_ls = getListOutOfStr(self.array_id_ls, data_type=int)
self.x_range = getListOutOfStr(self.x_range, data_type=int)
self.y_range = getListOutOfStr(self.y_range, data_type=int)
self.communicator = MPI.world.duplicate()
MPIwrapper.__init__(self,
self.communicator,
debug=self.debug,
report=self.report)
def __init__(self, **keywords): """ 2011-7-11 """ self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) #record it as string self.trio_set_str = self.trio_id if self.trio_id: self.trio_id = getListOutOfStr(self.trio_id, data_type=str) self.allNumberPattern = re.compile(r'^\d+')
def __init__(self, inputLs, **keywords):
"""
2012.2.28
"""
AbstractVariationWorkflow.__init__(self, **keywords)
if getattr(self, 'phenotype_method_id_ls', None):
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.phenotype_method_id_ls.sort()
else:
self.phenotype_method_id_ls = []
self.call_analysis_peak_type_id_list = getListOutOfStr(
self.call_analysis_peak_type_id_list, data_type=str)
call_analysis_peak_type_id_list = []
for call_analysis_peak_type_id in self.call_analysis_peak_type_id_list:
call_analysis_peak_type_id = call_analysis_peak_type_id.split(':')
call_analysis_peak_type_id = map(int, call_analysis_peak_type_id)
call_analysis_peak_type_id_list.append(call_analysis_peak_type_id)
self.call_analysis_peak_type_id_list = call_analysis_peak_type_id_list
def __init__(self, **keywords): """ 2008-07-24 split results_id_ls if it exists, to accomodate MpiGeneListRankTest which removed this option 2008-07-10 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls, data_type=int) if self.output_dir and not os.path.isdir(self.output_dir): os.makedirs(self.output_dir)
def __init__(self, **keywords):
"""
2008-12-05
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.which_array_id_ls = getListOutOfStr(self.which_array_id_ls,
data_type=int)
def __init__(self, **keywords):
"""
2008-05-11
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.ecotype_id_ls:
self.ecotype_id_ls = getListOutOfStr(
self.ecotype_id_ls, data_type=str
) #str because ecotype ids in SNPData are not converted to integers
def __init__(self, **keywords): """ 2008-09-29 add option min_LD_to_output and min_MAF """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) if self.individualSequenceIDList: self.individualSequenceIDList = getListOutOfStr(self.individualSequenceIDList, data_type=int) # 2010-5-30 #self.communicator = MPI.world.duplicate() self.communicator = MPI.COMM_WORLD MPI4pywrapper.__init__(self, self.communicator, debug=self.debug, report=self.report)
def __init__(self, **keywords):
"""
2008-11-25
change option phenotype_index_ls to phenotype_method_id_ls to pick phenotypes. phenotype_method_id is more intuitive.
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.phenotype_method_id_ls is not None:
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2008-07-01 chop off most functions, inherit from QC_250k
2008-04-20
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.call_info_id_ls:
self.call_info_id_ls = getListOutOfStr(self.call_info_id_ls,
data_type=int)
self.QCMethod_class = QCMethod
def __init__(self, **keywords):
"""
2011-7-11
"""
parentClass.__init__(self, **keywords)
if self.alnId2targetDepth:
alnId2targetDepthLs = getListOutOfStr(self.alnId2targetDepth, data_type=str)
self.alnId2targetDepth = {}
for alnIdTargetDepth in alnId2targetDepthLs:
alnIdTargetDepth = alnIdTargetDepth.split(':')
alnIdTargetDepth = map(int, alnIdTargetDepth)
alnId, targetDepth = alnIdTargetDepth
self.alnId2targetDepth[alnId] = targetDepth
else:
self.alnId2targetDepth = {}
def __init__(self, **keywords):
"""
2008-07-24
split results_id_ls if it exists, to accomodate MpiGeneListRankTest which removed this option
2008-07-10
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.phenotype_id_ls = getListOutOfStr(self.phenotype_id_ls,
data_type=int)
if self.output_dir and not os.path.isdir(self.output_dir):
os.makedirs(self.output_dir)
def filterTableRowByPhenotypeVector(self, tableObject=None, phenotypeIDList=None): """ 2013.2.19 modify the tableObject and gets rid of phenotypes in (overlap_phenotype_ls_in_str, input1_only_phenotype_ls_in_str, input2_only_phenotype_ls_in_str) that are not in phenotypeIDList """ if phenotypeIDList: phenotypeIDSet = set(phenotypeIDList) else: #return it without modifying return tableObject phenotypeRelatedAttributeNameList = [['total_phenotype_ls_in_str', 'no_of_total_phenotypes', 'fraction_of_total_phenotypes'],\ ['overlap_phenotype_ls_in_str', 'no_of_overlap_phenotypes', 'fraction_of_overlap_phenotypes'],\ ['input1_only_phenotype_ls_in_str', 'no_of_input1_only_phenotypes', 'fraction_of_input1_only_phenotypes'], \ ['input2_only_phenotype_ls_in_str', 'no_of_input2_only_phenotypes', 'fraction_of_input2_only_phenotypes']] no_of_total_phenotypes = None #no of total significant phenotypes for phenotypeRelatedAttributeName in phenotypeRelatedAttributeNameList: phenotypeListAttributeName = phenotypeRelatedAttributeName[0] dependentAttributeNameList = phenotypeRelatedAttributeName[1:] phenotypeListAttributeValue = getattr(tableObject, phenotypeListAttributeName, None) givenPhenotypeIDList = getListOutOfStr(phenotypeListAttributeValue) modified_phenotypeIDList = [] for phenotype_id in givenPhenotypeIDList: if phenotype_id in phenotypeIDSet: modified_phenotypeIDList.append(phenotype_id) #modify the list attribute modified_phenotypeIDListInStr = utils.getSuccinctStrOutOfList(modified_phenotypeIDList) setattr(tableObject, phenotypeListAttributeName, modified_phenotypeIDListInStr) #modify the #phenotypes & phenotypeFraction attributes noOfPhenotypeAttributeName, phenotypeFractionAttributeName = dependentAttributeNameList[:2] noOfPhenotypes = len(modified_phenotypeIDList) #calculate fraction of phenotypes if noOfPhenotypeAttributeName=='no_of_total_phenotypes': # this fraction is #significant-phenotypes/#all-phenotypes-in-association no_of_total_phenotypes = noOfPhenotypes oldNoOfPhenotypes = getattr(tableObject, noOfPhenotypeAttributeName, None) oldPhenotypeFraction = getattr(tableObject, phenotypeFractionAttributeName, None) phenotypeFraction = noOfPhenotypes/float(oldNoOfPhenotypes/oldPhenotypeFraction) elif no_of_total_phenotypes is not None and no_of_total_phenotypes>0: phenotypeFraction = noOfPhenotypes/float(no_of_total_phenotypes) else: phenotypeFraction = None setattr(tableObject, noOfPhenotypeAttributeName, noOfPhenotypes) setattr(tableObject, phenotypeFractionAttributeName, phenotypeFraction) return tableObject
def __init__(self, **keywords): """ 2008-12-05 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) processing_bits_ls = [1,1,1,1,1] for i in range(len(self.processing_bits)): processing_bits_ls[i] = int(self.processing_bits[i]) #now pass all values self.quantile_normalization,\ self.need_to_subtract_ref,\ self.subtract_column_median,\ self.subtract_row_median,\ self.split_genome_into_chromosomes = processing_bits_ls self.reference_arrays = getListOutOfStr(self.reference_arrays, data_type=int)
def __init__(self, **keywords):
"""
2008-12-05
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
processing_bits_ls = [1, 1, 1, 1, 1]
for i in range(len(self.processing_bits)):
processing_bits_ls[i] = int(self.processing_bits[i])
#now pass all values
self.quantile_normalization,\
self.need_to_subtract_ref,\
self.subtract_column_median,\
self.subtract_row_median,\
self.split_genome_into_chromosomes = processing_bits_ls
self.reference_arrays = getListOutOfStr(self.reference_arrays,
data_type=int)
def __init__(self, **keywords):
RunGADA.__init__(self, **keywords)
self.aAlpha_ls = getListOutOfStr(self.aAlpha_ls, data_type=float)
self.TBackElim_ls = getListOutOfStr(self.TBackElim_ls, data_type=float)
self.MinSegLen_ls = getListOutOfStr(self.MinSegLen_ls, data_type=int)
def type(cls, id=None, TypeClass=model.Stock_250kDB.CandidateGeneTopSNPTestRMType, \
template='/display_top_snp_test_rm_type.html', \
phenotype_id_ls_str = '1-7,39-61,80-82,9-13,32-38,65-74', \
list_type_id_ls_str = '3,6,8,28,51,64,65,68,71,76,129,24,29,30,130,131',\
analysis_method_id_ls_str = '1,5,6,7',\
figure_type=1, call_method_id=17):
"""
2009-10-13
allow user to specify phenotype_id_ls_str and list_type_id_ls_str in URL
add figure_type argument:
1: candidate vs non-candidate ratio (in db beforehand)
2: 2D matrix-plot of pvalue for enrichment statistic. row is cutoff. column is distance between gene and SNP.
add call_method_id argument
add argument analysis_method_id_ls_str
2008-10-30
generalized so that DisplayResultsGene could call it
"""
ResultsMethod = model.Stock_250kDB.ResultsMethod
if id is None:
id = request.params.get('id', '1')
phenotype_id_ls_str = request.params.get('phenotype_id_ls_str', phenotype_id_ls_str) # 2009-10-13
list_type_id_ls_str = request.params.get('list_type_id_ls_str', list_type_id_ls_str) # 2009-10-13
analysis_method_id_ls_str = request.params.get('analysis_method_id_ls_str', analysis_method_id_ls_str) # 2009-10-13
c.figure_type = request.params.get('figure_type', figure_type) # 2009-10-13
call_method_id = request.params.get('call_method_id', call_method_id) # 2009-10-13
phenotype_id_ls = getListOutOfStr(phenotype_id_ls_str, data_type=str)
list_type_id_ls = getListOutOfStr(list_type_id_ls_str, data_type=str)
analysis_method_id_ls = getListOutOfStr(analysis_method_id_ls_str, data_type=int)
#extra_tables = ' %s c '%(CandidateGeneTopSNPTestRM.table.name)
extra_condition = 'p.id in (%s)'%(','.join(phenotype_id_ls))
c.phenotype_info = hc.getPhenotypeInfo(extra_condition=extra_condition, extra_tables=None)
#extra_condition = 's.type_id =%s'%id
extra_condition = 'p.id in (%s)'%(','.join(list_type_id_ls))
c.list_info = hc.getListTypeInfo(extra_condition=extra_condition)
data_matrix = []
no_of_rows = len(c.list_info.list_type_id_ls)
no_of_cols = len(c.phenotype_info.phenotype_method_id_ls)
for i in range(no_of_rows):
data_matrix.append([None]*no_of_cols)
c.type = TypeClass.get(id)
#2008-10-29 a faster way to come up the data_matrix but data is not guaranteed inside
rows = ResultsMethod.query.filter(ResultsMethod.phenotype_method_id.in_(map(int, phenotype_id_ls))).\
filter(ResultsMethod.analysis_method_id.in_(analysis_method_id_ls)).\
filter_by(call_method_id=call_method_id).\
order_by(ResultsMethod.analysis_method_id)
counter = 0
for row in rows:
col_index = c.phenotype_info.phenotype_method_id2index.get(row.phenotype_method_id)
if col_index is None:
continue
for list_type_id, row_index in c.list_info.list_type_id2index.iteritems():
if list_type_id>0:
if data_matrix[row_index][col_index] is None:
data_matrix[row_index][col_index] = []
data_matrix[row_index][col_index].append((row.id, row.analysis_method.short_name))
counter +=1
"""
rows = CandidateGeneTopSNPTestRM.query.filter_by(type_id=id)
for row in rows:
row_index = c.list_info.list_type_id2index[row.list_type_id]
col_index = c.phenotype_info.phenotype_method_id2index[row.result.phenotype_method_id]
if data_matrix[row_index][col_index] is None:
data_matrix[row_index][col_index] = Set()
data_matrix[row_index][col_index].add(row.results_id)
counter +=1
"""
c.counter = counter
c.data_matrix = data_matrix
return render(template)
def __init__(self, inputFnameLs, **keywords):
"""
"""
AbstractVariationMapper.__init__(self, inputFnameLs, **keywords)
self.peak_id_ls = getListOutOfStr(self.peak_id_ls, data_type=int)
self.peak_id_ls.sort()
def __init__(self, inputFnameLs=None, **keywords): """ """ SelectRowsWithinCoverageRange.__init__(self, inputFnameLs=inputFnameLs, **keywords) #self.connectDB() called within its __init__() self.replaceColumnHeaderLs = getListOutOfStr(self.replaceColumnHeaderLs, data_type=str)
def __init__(self, **keywords): GeneListRankTest.__init__(self, **keywords) self.list_type_id_ls = getListOutOfStr(self.list_type_id_ls, data_type=int) self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords): GeneListRankTest.__init__(self, **keywords) self.list_type_id_ls = getListOutOfStr(self.list_type_id_ls, data_type=int) self.analysis_method_id_ls = getListOutOfStr(self.analysis_method_id_ls, data_type=int) self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
