def run(args):
mdictfile = args.mdictfile
cdictfile = args.cdictfile
mprob = args.mprob
cprob = args.cprob
cooccur_distance_threshold = args.cooccur_distance_threshold
bin_distance_threshold = args.bin_distance_threshold
mutationmatrix = args.mutation_matrix
newmutationmatrix = args.newmutationmatrix
file_prefix = args.output_prefix
if not file_prefix:
file_prefix = newmutationmatrix
geneFile = args.gene_file
patientFile = args.patient_file
gene_blacklist = args.gene_blacklist_file
patient_blacklist = args.patient_blacklist_file
minFreq = args.min_freq
minCooccur = args.min_cooccur
min_cooccurrence_ratio = args.min_cooccurrence_ratio
top_percentile = args.top_percentile
top_number = args.top_number
parallel_compute_number = args.parallel_compute_number
filter_cooccur_same_segment = args.filter_cooccur_same_segment
fcss_cratiothresh = args.fcss_cratiothresh
fcss_mutfreqdiffthresh = args.fcss_mutfreqdiffthresh
fcss_mutfreqdiffratiothresh = args.fcss_mutfreqdiffratiothresh
fcss_coveragethresh = args.fcss_coveragethresh
fcss_probabilitythresh = args.fcss_probabilitythresh
gene_segment_file = args.gene_segment_file
load_gene_segments = args.load_gene_segments
is_gene2seg = args.is_gene2seg
gene_bin_entries_file = args.gene_bin_entries_file
no_throw_out_extras = args.no_throw_out_extras
segment_info_file = args.segment_info_file
if not gene_bin_entries_file:
gene_bin_entries_file = file_prefix + '_binnedgenes.tsv'
if not segment_info_file:
segment_info_file = file_prefix + '_SEGMENTINFO.tsv'
#-----------------------------------------------------
mutations = mex.remove_blacklists(gene_blacklist, patient_blacklist,
*mex.load_mutation_data(mutationmatrix, patientFile, geneFile, minFreq))
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mutations
print 'Filtered Mutation data: %s genes x %s patients' % (numGenes, numCases)
# Load segment info
if load_gene_segments:
# extra_genes is the genes not found in the segment file.
# If throw_out_extras is False, extra_genes will be empty.
geneToBin, extra_genes = load_gene_to_bin(gene_segment_file, geneToCases, no_throw_out_extras=no_throw_out_extras, is_gene2seg=is_gene2seg)
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mex.remove_extra_genes(extra_genes, numGenes, numCases, genes, patients, geneToCases, patientToGenes)
else:
print "Beginning bin genes by co-occurring pairs. "
genepairs = getgenepairs(geneToCases, genes, closer_than_distance=bin_distance_threshold)
print "Pairs retrieved. Calculating cooccurring pairs to make bins."
cpairsdict, cgenedict = met.complete_cooccurpairs(numCases, geneToCases, patientToGenes, genepairs, fcss_probabilitythresh, minCooccur,
cooccur_distance_threshold, fcss_cratiothresh, parallel_compute_number,
filter_cooccur_same_segment, fcss_cratiothresh, fcss_mutfreqdiffratiothresh,
fcss_coveragethresh, fcss_probabilitythresh)
print "Cooccurring pairs calculated."
geneToBin = get_gene_bins_cooccur_same_segment(cpairsdict, geneToCases, fcss_cratiothresh, fcss_mutfreqdiffthresh,
fcss_mutfreqdiffratiothresh, fcss_coveragethresh, fcss_probabilitythresh, bin_distance_threshold=bin_distance_threshold)
# Write these new bins out
new_bins = convert_genes_to_bins(genes, geneToBin)
write_segment_infos(new_bins, filename=segment_info_file)
print "New SEGMENTINFO written to ", segment_info_file
write_gene_positions(new_bins)
print "New segment positions appended to gene_positions.txt"
# Update to the new mutation matrix.
geneToBinSet, bin_setToBin = bin_sets_from_geneToBin(genes, geneToBin)
newGeneToCases, newPatientToGenes = update_geneToCases_patientToGenes(geneToCases, patientToGenes, bin_setToBin, at_least_half=True)
gene_bin_entries = get_gene_bin_entries(geneToCases, newGeneToCases, geneToBinSet, bin_setToBin)
if gene_bin_entries_file:
met.writeanydict(gene_bin_entries, gene_bin_entries_file)
print "Gene bin entries written to ", gene_bin_entries_file
# Write the new mutation matrix out.
writemutationmatrix(newPatientToGenes, filename=newmutationmatrix)
def run(args):
mdictfile = args.mdictfile
cdictfile = args.cdictfile
mprob = args.mprob
cprob = args.cprob
cooccur_distance_threshold = args.cooccur_distance_threshold
bin_distance_threshold = args.bin_distance_threshold
mutationmatrix = args.mutation_matrix
newmutationmatrix = args.newmutationmatrix
file_prefix = args.output_prefix
if not file_prefix:
file_prefix = newmutationmatrix
geneFile = args.gene_file
patientFile = args.patient_file
gene_blacklist = args.gene_blacklist_file
patient_blacklist = args.patient_blacklist_file
minFreq = args.min_freq
minCooccur = args.min_cooccur
min_cooccurrence_ratio = args.min_cooccurrence_ratio
top_percentile = args.top_percentile
top_number = args.top_number
parallel_compute_number = args.parallel_compute_number
filter_cooccur_same_segment = args.filter_cooccur_same_segment
fcss_cratiothresh = args.fcss_cratiothresh
fcss_mutfreqdiffthresh = args.fcss_mutfreqdiffthresh
fcss_mutfreqdiffratiothresh = args.fcss_mutfreqdiffratiothresh
fcss_coveragethresh = args.fcss_coveragethresh
fcss_probabilitythresh = args.fcss_probabilitythresh
gene_segment_file = args.gene_segment_file
load_gene_segments = args.load_gene_segments
is_gene2seg = args.is_gene2seg
gene_bin_entries_file = args.gene_bin_entries_file
no_throw_out_extras = args.no_throw_out_extras
segment_info_file = args.segment_info_file
if not gene_bin_entries_file:
gene_bin_entries_file = file_prefix + '_binnedgenes.tsv'
if not segment_info_file:
segment_info_file = file_prefix + '_SEGMENTINFO.tsv'
#-----------------------------------------------------
mutations = mex.remove_blacklists(
gene_blacklist, patient_blacklist,
*mex.load_mutation_data(mutationmatrix, patientFile, geneFile,
minFreq))
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mutations
print 'Filtered Mutation data: %s genes x %s patients' % (numGenes,
numCases)
# Load segment info
if load_gene_segments:
# extra_genes is the genes not found in the segment file.
# If throw_out_extras is False, extra_genes will be empty.
geneToBin, extra_genes = load_gene_to_bin(
gene_segment_file,
geneToCases,
no_throw_out_extras=no_throw_out_extras,
is_gene2seg=is_gene2seg)
numGenes, numCases, genes, patients, geneToCases, patientToGenes = mex.remove_extra_genes(
extra_genes, numGenes, numCases, genes, patients, geneToCases,
patientToGenes)
else:
print "Beginning bin genes by co-occurring pairs. "
genepairs = getgenepairs(geneToCases,
genes,
closer_than_distance=bin_distance_threshold)
print "Pairs retrieved. Calculating cooccurring pairs to make bins."
cpairsdict, cgenedict = met.complete_cooccurpairs(
numCases, geneToCases, patientToGenes, genepairs,
fcss_probabilitythresh, minCooccur, cooccur_distance_threshold,
fcss_cratiothresh, parallel_compute_number,
filter_cooccur_same_segment, fcss_cratiothresh,
fcss_mutfreqdiffratiothresh, fcss_coveragethresh,
fcss_probabilitythresh)
print "Cooccurring pairs calculated."
geneToBin = get_gene_bins_cooccur_same_segment(
cpairsdict,
geneToCases,
fcss_cratiothresh,
fcss_mutfreqdiffthresh,
fcss_mutfreqdiffratiothresh,
fcss_coveragethresh,
fcss_probabilitythresh,
bin_distance_threshold=bin_distance_threshold)
# Write these new bins out
new_bins = convert_genes_to_bins(genes, geneToBin)
write_segment_infos(new_bins, filename=segment_info_file)
print "New SEGMENTINFO written to ", segment_info_file
write_gene_positions(new_bins)
print "New segment positions appended to gene_positions.txt"
# Update to the new mutation matrix.
geneToBinSet, bin_setToBin = bin_sets_from_geneToBin(genes, geneToBin)
newGeneToCases, newPatientToGenes = update_geneToCases_patientToGenes(
geneToCases, patientToGenes, bin_setToBin, at_least_half=True)
gene_bin_entries = get_gene_bin_entries(geneToCases, newGeneToCases,
geneToBinSet, bin_setToBin)
if gene_bin_entries_file:
met.writeanydict(gene_bin_entries, gene_bin_entries_file)
print "Gene bin entries written to ", gene_bin_entries_file
# Write the new mutation matrix out.
writemutationmatrix(newPatientToGenes, filename=newmutationmatrix)
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)
