def estimateEnrichmentOfTFBS(infiles, outfile):
'''
Estimate the significance of trnascription factors that are
associated with a foreground set of intervals vs a background set
'''
E.info("Running Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
# required files
match_table = "match_result"
# we don't know which order the foreground and backgorund
# will come in
background = [infile for infile in infiles if
re.search("background", infile)][0]
foreground = [infile for infile in infiles if
re.search("foreground", infile)][0]
# run significance testing
PipelineTFM.testSignificanceOfMatrices(background,
foreground,
PARAMS["database"],
match_table,
outfile)
E.info("Completed Fisher's exact test for "
"TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
Estimate the significance of trnascription factors that are
associated with a foreground set of intervals vs a background set
'''
E.info("Running Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
# required files
match_table = "match_result"
# we don't know which order the foreground and backgorund
# will come in
background = [
infile for infile in infiles
if re.search("background", infile)
][0]
foreground = [
infile for infile in infiles
if re.search("foreground", infile)
][0]
# run significance testing
PipelineTFM.testSignificanceOfMatrices(background, foreground,
PARAMS["database"],
match_table, outfile)
E.info("Completed Fisher's exact test for "
"TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
Estimate the significance of transcription factors that are associated
with a foreground set of intervals vs a background set matched for
sequence composition.
'''
E.info("Running Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
# required files
match_table = "match_result"
# we don't know which order the foreground and background will come in
background = [infile for infile in infiles if
re.search("background", infile)][0]
foreground = ["%s.foreground.tsv" %
re.match(".+/(.+)\.foreground\.gc\.tsv",
infile).groups()[0]
for infile in infiles if re.search("foreground",
infile)][0]
# run significance testing
PipelineTFM.testSignificanceOfMatrices(background,
foreground,
PARAMS["database"],
match_table,
outfile,
PARAMS["genesets_header"])
E.info("Completed Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
estimate the significance of trnascription factors that are associated with
a foreground set of intervals vs a background set matched for CpG content
'''
# required files
match_table = "match_result"
# we don't know which order the foreground and backgorund will come in
background = [
infile for infile in infiles if re.search("background", infile)][0]
foreground = ["%s.foreground.tsv" % re.match(".+/(.+)\.foreground\.gc\.tsv", infile).groups()[0]
for infile in infiles if re.search("foreground", infile)][0]
# run significance testing
PipelineTransfacMatch.testSignificanceOfMatrices(
background, foreground, PARAMS["database"], match_table, outfile)
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
estimate the significance of trnascription factors that are associated with
a foreground set of intervals vs a background set
'''
# required files
match_table = "match_result"
#we don't know which order the foreground and backgorund will come in
background = [
infile for infile in infiles if re.search("background", infile)
][0]
foreground = [
infile for infile in infiles if re.search("foreground", infile)
][0]
# run significance testing
PipelineTransfacMatch.testSignificanceOfMatrices(
background, foreground, PARAMS["database"], match_table, outfile)
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
Estimate the significance of transcription factors that are
associated with a foreground set of intervals vs a background
set matched for sequence composition.
'''
E.info("Running Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
# required files
match_table = "match_result"
# we don't know which order the foreground and background
# will come in
background = [
infile for infile in infiles
if re.search("background", infile)
][0]
foreground = [
"%s.foreground.tsv" %
re.match(".+/(.+)\.foreground\.gc\.tsv", infile).groups()[0]
for infile in infiles if re.search("foreground", infile)
][0]
# run significance testing
# MM: added in directionality into FET - might only be looking for
# enrichment OR depletion so don't want to hammer those p-value
# too hard
pval_direct = PARAMS['fisher_direction']
PipelineTFM.testSignificanceOfMatrices(background, foreground,
PARAMS["database"],
match_table, outfile,
PARAMS["genesets_header"],
pval_direct)
E.info("Completed Fisher's exact test for "
"TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
def estimateEnrichmentOfTFBS(infiles, outfile):
'''
Estimate the significance of transcription factors that are
associated with a foreground set of intervals vs a background
set matched for sequence composition.
'''
E.info("Running Fisher's exact test for TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
# required files
match_table = "match_result"
# we don't know which order the foreground and background
# will come in
background = [infile for infile in infiles if
re.search("background", infile)][0]
foreground = ["%s.foreground.tsv" %
re.match(".+/(.+)\.foreground\.gc\.tsv",
infile).groups()[0]
for infile in infiles if re.search("foreground",
infile)][0]
# run significance testing
# MM: added in directionality into FET - might only be looking for
# enrichment OR depletion so don't want to hammer those p-value
# too hard
pval_direct = PARAMS['fisher_direction']
PipelineTFM.testSignificanceOfMatrices(background,
foreground,
PARAMS["database"],
match_table,
outfile,
PARAMS["genesets_header"],
pval_direct)
E.info("Completed Fisher's exact test for "
"TF enrichment between %s" %
" & ".join([os.path.basename(x) for x in infiles]))
