def merge_calls_across_SD(calls, pipeline, max_distance_to_merge=50, min_sd_percent=0.5):
out_calls = [] #pd.DataFrame(columns=list(calls.calls.columns) + ["merge_count"])
chrom_probes = {chrom: pd.DataFrame(p.r.h5file.root.probes._f_getChild("probes_chr%d" % chrom).read()) for chrom in range(1,24)}
for sampleID in set(calls.calls["sampleID"]):
print sampleID
sample_calls = CallTable(calls.calls[calls.calls["sampleID"] == sampleID])
for chrom in set(sample_calls.calls.chromosome):
chr_probes = chrom_probes[chrom]
calls_to_merge = sample_calls.filter(lambda x: x["chromosome"] == chrom).calls.sort("start")
if len(calls_to_merge) <= 1:
# no calls to merge
out_calls.append(calls_to_merge.ix[calls_to_merge.index[0]])#, ignore_index=True)
else:
# for each call, first check it is within the max_distance_to_merge
# then check if the SD content between them is more than the min_sd_percent
first_call = calls_to_merge.ix[calls_to_merge.index[0]]
# start iterating on the second call
for ix, second_call in calls_to_merge.ix[calls_to_merge.index[1:]].iterrows():
delta = second_call["start_exon"] - first_call["stop_exon"]
if (second_call["state"] == first_call["state"]) and (delta < max_distance_to_merge):
gap_sd_count = chr_probes.ix[xrange(first_call["stop_exon"],second_call["start_exon"])].isSegDup.sum()
gap_sd_percent = float(gap_sd_count)/delta
if gap_sd_percent >= min_sd_percent:
merged = merge_calls(first_call, second_call)
first_call = merged.copy()
else:
out_calls.append(first_call)#, ignore_index=True)
first_call = second_call
else:
# too far apart, do not merge
out_calls.append(first_call)#, ignore_index=True)
first_call = second_call
#if not last_call_was_merged:
out_calls.append(second_call)#, ignore_index=True)
out_calls = pd.DataFrame(out_calls)
return CallTable(out_calls)
import argparse
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--infile", "-i", action="store", required=True)
parser.add_argument("--cohort", action="store", required=True)
parser.add_argument("--esp_infile", action="store", required=True)
parser.add_argument("--outfile", "-o", action="store", required=True)
parser.add_argument("--gamma", type=float, action="store", required=False, default=0.9)
parser.add_argument("--cophenetic_cutoff", type=float, action="store", required=False, default=0.85)
args = parser.parse_args()
assert args.gamma <= 1, "Gamma must be <= 1.00"
assert args.cophenetic_cutoff <= 1, "Cophenetic cutoffs must be <= 1.00"
calls = CallTable(args.infile)
esp_calls = CallTable(args.esp_infile)
calls.calls["cohort"] = args.cohort
esp_calls.calls["cohort"] = "ESP"
calls.appendCalls(esp_calls)
calls = calls.clusterCallsByCohort(gamma=args.gamma, cohort_field="cohort", cophenetic_cutoff=args.cophenetic_cutoff)
#clean up calls table
del calls.calls["cnvrID_ESP"]
calls = CallTable(calls.calls.rename(columns={'cnvr_frequency_HSCR': 'cnvr_frequency', 'cnvrID_HSCR': 'cnvrID'}))
# filter for original cohort and save
calls.filter(lambda x: x["cohort"] == args.cohort).save(args.outfile)
OtherDupFilter = CallFilterTemplate(p,
"/net/eichler/vol8/home/nkrumm/REFERENCE_INFO/3copiesin27of34.bed",
name="Dup_overlap",
filter_type="overlap",
func=lambda x: x < 0.5)
GeneAnnotation = CallFilterTemplate(p,
"/net/eichler/vol8/home/nkrumm/REFERENCE_INFO/hg19.refGene.bed",
name="RefSeq",
filter_type="name")
def signalFilter(x):
if x["num_probes"] <= 2:
return np.abs(x["median_svdzrpkm"]) >= 1.5
elif x["num_probes"] <= 5:
return np.abs(x["median_svdzrpkm"]) >= 1
else:
return np.abs(x["median_svdzrpkm"]) >= 0.5
calls = CallTable(args.call_file)
calls = calls.filter(signalFilter)\
.filter(lambda x: x["probability"] > 0.99)\
.filter(SDFilter)\
.filter(PPGFilter)\
.filter(OtherDupFilter)\
.annotate(SDCount)\
.annotate(PPG_probe_count)
calls.save(args.outfile)
parser = argparse.ArgumentParser()
parser.add_argument("--conifer_file", action="store", required=True)
parser.add_argument("--call_file", action="store", required=True)
parser.add_argument("--out_dir", action="store", required=True)
parser.add_argument("--min_freq", type=int, action="store", required=False, default=0)
parser.add_argument("--max_freq", type=int, action="store", required=False, default=30)
parser.add_argument("--cnvrID", type=int, nargs="*", action="store", required=False, default=None)
parser.add_argument("--cohort", action="store", required=False, default = "SSC")
args = parser.parse_args()
INHERITED_CODES = ['fa_to_both', 'fa_to_pro', 'fa_to_sib', 'mo_to_both', 'mo_to_pro', 'mo_to_sib']
calls = CallTable(args.call_file)
del calls.calls["cnvrID"]# = calls.calls["cnvrID_%s" % args.cohort]
if isinstance(args.cnvrID, list):
calls = calls.filter(lambda x: x["cnvrID_%s" % args.cohort] in args.cnvrID)
calls = calls.filter(lambda x: (x["cnvr_frequency_%s" % args.cohort] >= args.min_freq) & (x["cnvr_frequency_%s" % args.cohort] < args.max_freq))
calls.calls["familyID"] = map(lambda x: x.split(".")[:-1], calls.calls["sampleID"])
offspring_calls = calls.filter(lambda x: x["sampleID"].endswith(("p1","s1","s2","s3")))
parent_calls = calls.filter(lambda x: x["sampleID"].endswith(("mo","fa")))
sibling_calls = calls.filter(lambda x: x["sampleID"].endswith(("s1", "s2", "s3")))
plotters = {}
colors = {"fa": "b", "mo": "b", "sib": "g", "pro": "r"}
for rel, codes in zip(["pro", "sib", "mo", "fa"], [["p1", "p2"], ["s1", "s2", "s3"], ["mo"], ["fa"]]):
# create a plotter for each family member
plotters[rel] = ConiferPlotter(args.conifer_file)
# add the calls from that group
t=ConiferPlotTrack(plotters[rel], data_in = calls.filter(lambda x: x["sampleID"].split(".")[1] in codes),
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--conifer_file", action="store", required=True)
parser.add_argument("--call_file", action="store", required=True)
parser.add_argument("--outfile", "-o", action="store", required=True)
parser.add_argument("--threshold", default=0.99)
parser.add_argument("--sample_size", default=None)
args = parser.parse_args()
p = ConiferPipeline(args.conifer_file)
calls = CallTable(args.call_file)
calls.calls["familyID"] = map(lambda x: x.split('.')[0], calls.calls["sampleID"])
new_calls = CallTable()
offspring_calls = calls.filter(lambda x: x["sampleID"].endswith(("p", "s", "p1"))).calls
#offspring_calls = calls.filter(lambda x: x["sampleID"][6] in ["p","s"]).calls
parent_calls = calls.filter(lambda x: x["sampleID"].endswith(("m", "f", "mo", "fa"))).calls
#parent_calls = calls.filter(lambda x: x["sampleID"][6] in ["m","f"]).calls
if args.sample_size:
sample_size = int(args.sample_size)
else:
sample_size = len(p.samples)
print sample_size
total_calls = len(offspring_calls)
cnt = 0
for ix, c in offspring_calls.iterrows():
# first check if parents already have calls:
cnt += 1
if cnt % 100 == 0:
p,
"/net/eichler/vol8/home/nkrumm/REFERENCE_INFO/3copiesin27of34.bed",
name="Dup_overlap",
filter_type="overlap",
func=lambda x: x < 0.5)
GeneAnnotation = CallFilterTemplate(
p,
"/net/eichler/vol8/home/nkrumm/REFERENCE_INFO/hg19.refGene.bed",
name="RefSeq",
filter_type="name")
def signalFilter(x):
if x["num_probes"] <= 2:
return np.abs(x["median_svdzrpkm"]) >= 1.5
elif x["num_probes"] <= 5:
return np.abs(x["median_svdzrpkm"]) >= 1
else:
return np.abs(x["median_svdzrpkm"]) >= 0.5
calls = CallTable(args.call_file)
calls = calls.filter(signalFilter)\
.filter(lambda x: x["probability"] > 0.99)\
.filter(SDFilter)\
.filter(PPGFilter)\
.filter(OtherDupFilter)\
.annotate(SDCount)\
.annotate(PPG_probe_count)
calls.save(args.outfile)