def main():
mutationmatrix = '/Users/jlu96/maf/new/PRAD_broad/PRAD_broad-som.m2'
patientFile = None #'/Users/jlu96/maf/new/PRAD_broad/shared_patients.plst'
geneFile = None #'/Users/jlu96/conte/jlu/REQUIREDFILES_OnlyLoss2/COSMICGenes_OnlyLoss.txt'
load_directory = '/Users/jlu96/conte/jlu/Analyses/CooccurImprovement/LoadMatrices'
minFreq = 0
num_permutations = 20
binary_perm_method = False
Q = 100
write_matrices = True
matrixdirectory = '/Users/jlu96/conte/jlu/Analyses/CooccurImprovement/LoadMatrices'
#'/Users/jlu96/conte/jlu/Analyses/CooccurImprovement/SARC_broad-som-jl-' + ('matrix' if binary_perm_method else 'network')
outmutexfile = matrixdirectory + '/mutex' + str(num_permutations) + str(time.time()) + '.tsv'
outcooccurfile = matrixdirectory + '/cooccur' + str(num_permutations) + str(time.time()) + '.tsv'
outseedsfile = matrixdirectory + '/seeds' + str(time.time()) + '.tsv'
if not os.path.exists(os.path.dirname(matrixdirectory)):
os.makedirs(os.path.dirname(matrixdirectory))
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mex.load_mutation_data(mutationmatrix, patientFile, geneFile, minFreq)
print "numGenes ", numGenes, " and numCases ", numCases
for patient in patients:
if not patientToGenes[patient]:
patientToGenes.pop(patient)
print patient, "popped"
# Generate Permutation Matrices
pm = PermutationMatrices(geneToCases, patientToGenes, num_permutations, Q=Q, matrixdirectory=matrixdirectory,
binary_perm_method=binary_perm_method, write_matrices=write_matrices, load_directory=load_directory,
geneFile=geneFile, patientFile=patientFile, minFreq=minFreq)
# Make list of pairs from highly mutated genes
test_genes = [gene for gene in genes if len(geneToCases[gene]) > 5]
# for test_gene in test_genes:
# print test_gene
genepairs = met.getgenepairs(geneToCases, test_genes)
print "Number of pairs to test ", len(genepairs)
# CALCULATE MUTEX
# Create a list of ConditionFunctions that you must later initialize...
ConditionFunctions = range(len(genepairs))
mutex_set_condition_function_list = []
# Generate set_condition_function_list
for i in range(len(genepairs)):
genepair = genepairs[i]
condition_dict = {}
condition_dict['Genes'] = tuple(genepair)
condition_dict['Overlap'] = len(set.intersection(*[geneToCases[gene] for gene in condition_dict['Genes']]))
condition_dict['Mutex'] = True
ConditionFunctions[i] = Condition([condition_dict])
if [condition_dict] != ConditionFunctions[i].conditions:
print condition_dict, ConditionFunctions[i].conditions
mutex_set_condition_function_list.append((genepair, ConditionFunctions[i]))
print "Finished mutex condition function list"
t= time.time()
# Calculate pvalues for mutual exclusivity
pair_to_mutex = {}
pair_to_mutex_network_pvalue = pm.set_to_pvalue(mutex_set_condition_function_list)
print "mutex pair network pvalues finished in ", time.time() - t
for genepair in genepairs:
pair_to_mutex[genepair] = mex.analyze_mutex_set_new(numCases, geneToCases, patientToGenes, genepair)
pair_to_mutex[genepair]['NetworkProbability'] = pair_to_mutex_network_pvalue[genepair]
# Write to output
with open(outmutexfile, 'w') as csvfile:
fieldnames = pair_to_mutex[genepairs[0]].keys()
writer = csv.DictWriter(csvfile, delimiter='\t', fieldnames=fieldnames)
writer.writeheader()
for genepair in pair_to_mutex:
writer.writerow(pair_to_mutex[genepair])
# CALCULATE COOCCUR
cooccur_set_condition_function_list = []
# Generate set_condition_function_list
for genepair in genepairs:
ConditionFunction = Condition(None)
condition_dict = {}
condition_dict['Genes'] = tuple(genepair)
condition_dict['Overlap'] = len(set.intersection(*[geneToCases[gene] for gene in condition_dict['Genes']]))
condition_dict['Mutex'] = False
ConditionFunction.set_params([condition_dict])
cooccur_set_condition_function_list.append((genepair, ConditionFunction))
t= time.time()
# Calculate pvalues for mutual exclusivity
pair_to_cooccur = {}
pair_to_cooccur_network_pvalue = pm.set_to_pvalue(cooccur_set_condition_function_list)
print "cooccur pair network pvalues finished in ", time.time() - t
for genepair in genepairs:
pair_to_cooccur[genepair] = mex.analyze_cooccur_set_new(numCases, geneToCases, patientToGenes, genepair)
pair_to_cooccur[genepair]['NetworkProbability'] = pair_to_cooccur_network_pvalue[genepair]
# Write to output
with open(outcooccurfile, 'w') as csvfile:
fieldnames = pair_to_cooccur[genepairs[0]].keys()
writer = csv.DictWriter(csvfile, delimiter='\t', fieldnames=fieldnames)
writer.writeheader()
for genepair in pair_to_cooccur:
writer.writerow(pair_to_cooccur[genepair])
# Write seeds to output
with open(outseedsfile, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter='\t')
for seed in pm.seeds:
writer.writerow([seed])
def main():
mutationmatrix = '/Users/jlu96/maf/new/OV_broad/OV_broad-cna-jl.m2'
patientFile = '/Users/jlu96/maf/new/OV_broad/shared_patients.plst'
cpairfile = '/Users/jlu96/conte/jlu/Analyses/CooccurImprovement/LorenzoModel/Binomial/OV_broad-cna-jl-cpairs-min_cohort.txt'
partitionfile = '/Users/jlu96/maf/new/OV_broad/OV_broad-cna-jl.ppf'
load_partitions = True
do_min_cohort = True
geneFile = None
minFreq = 0
test_minFreq = 100
compute_mutex = True
include_cohort_info = False
num_cohorts_list = [1,3, 5, 7]
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mex.load_mutation_data(mutationmatrix, patientFile, geneFile, minFreq)
print "number of genes is ", numGenes
if do_min_cohort:
cohort_dict, clusterToProp, min_cohort = partition.load_patient_cohorts(partitionfile, patientToGenes)
min_cohort_genes = set.union(*(patientToGenes[p] for p in min_cohort))
print "getting pairs"
genepairs = met.getgenepairs(geneToCases, min_cohort_genes, test_minFreq=test_minFreq)
print "Number of pairs ", len(genepairs)
print "Normal cooccur test"
t = time.time()
cpairsdict, cgenedict = met.cooccurpairs(numCases, geneToCases, patientToGenes, genepairs, compute_mutex=compute_mutex)
print "Normal cooccur done in ", time.time() - t
print "Beginning cohorts"
t = time.time()
cpairsdict = add_BinomP_min_cohort_all_pairs(cpairsdict, geneToCases, patientToGenes, cohort_dict, min_cohort)
print "Cohorts done in ", time.time() - t
else:
genepairs = met.getgenepairs(geneToCases, genes, test_minFreq=test_minFreq)
print "Number of pairs ", len(genepairs)
print "Normal cooccur test"
cpairsdict, cgenedict = met.cooccurpairs(numCases, geneToCases, patientToGenes, genepairs, compute_mutex=compute_mutex)
# print "Add binomial probability"
# cpairsdict = add_BinomP_all_pairs(cpairsdict, geneToCases, patientToGenes)
# undo
print "Beginning cohorts"
if load_partitions:
cohort_dict = partition.load_patient_cohorts(partitionfile)
cpairsdict = add_BinomP_cohorts_all_pairs(cpairsdict, geneToCases, patientToGenes, cohort_dict)
else:
for num_cohorts in num_cohorts_list:
# get cohorts
cohort_dict = generate_patient_cohorts(patientToGenes, num_cohorts)
cpairsdict = add_BinomP_cohorts_all_pairs(cpairsdict, geneToCases, patientToGenes, cohort_dict)
if include_cohort_info:
cpairsdict = add_cohorts_all_pairs(cpairsdict, geneToCases, patientToGenes, cohort_dict)
print "Writing to file..."
met.writeanydict(cpairsdict, cpairfile)
def main():
mutationmatrix = '/Users/jlu96/maf/new/OV_broad/OV_broad-cna-jl.m2'
patientFile = '/Users/jlu96/maf/new/OV_broad/shared_patients.plst'
cpairfile = '/Users/jlu96/conte/jlu/Analyses/CooccurImprovement/LorenzoModel/Binomial/OV_broad-cna-jl-cpairs-min_cohort.txt'
partitionfile = '/Users/jlu96/maf/new/OV_broad/OV_broad-cna-jl.ppf'
load_partitions = True
do_min_cohort = True
geneFile = None
minFreq = 0
test_minFreq = 100
compute_mutex = True
include_cohort_info = False
num_cohorts_list = [1, 3, 5, 7]
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mex.load_mutation_data(
mutationmatrix, patientFile, geneFile, minFreq)
print "number of genes is ", numGenes
if do_min_cohort:
cohort_dict, clusterToProp, min_cohort = partition.load_patient_cohorts(
partitionfile, patientToGenes)
min_cohort_genes = set.union(*(patientToGenes[p] for p in min_cohort))
print "getting pairs"
genepairs = met.getgenepairs(geneToCases,
min_cohort_genes,
test_minFreq=test_minFreq)
print "Number of pairs ", len(genepairs)
print "Normal cooccur test"
t = time.time()
cpairsdict, cgenedict = met.cooccurpairs(numCases,
geneToCases,
patientToGenes,
genepairs,
compute_mutex=compute_mutex)
print "Normal cooccur done in ", time.time() - t
print "Beginning cohorts"
t = time.time()
cpairsdict = add_BinomP_min_cohort_all_pairs(cpairsdict, geneToCases,
patientToGenes,
cohort_dict, min_cohort)
print "Cohorts done in ", time.time() - t
else:
genepairs = met.getgenepairs(geneToCases,
genes,
test_minFreq=test_minFreq)
print "Number of pairs ", len(genepairs)
print "Normal cooccur test"
cpairsdict, cgenedict = met.cooccurpairs(numCases,
geneToCases,
patientToGenes,
genepairs,
compute_mutex=compute_mutex)
# print "Add binomial probability"
# cpairsdict = add_BinomP_all_pairs(cpairsdict, geneToCases, patientToGenes)
# undo
print "Beginning cohorts"
if load_partitions:
cohort_dict = partition.load_patient_cohorts(partitionfile)
cpairsdict = add_BinomP_cohorts_all_pairs(cpairsdict, geneToCases,
patientToGenes,
cohort_dict)
else:
for num_cohorts in num_cohorts_list:
# get cohorts
cohort_dict = generate_patient_cohorts(patientToGenes,
num_cohorts)
cpairsdict = add_BinomP_cohorts_all_pairs(
cpairsdict, geneToCases, patientToGenes, cohort_dict)
if include_cohort_info:
cpairsdict = add_cohorts_all_pairs(cpairsdict, geneToCases,
patientToGenes,
cohort_dict)
print "Writing to file..."
met.writeanydict(cpairsdict, cpairfile)
