def main():
parser = argparse.ArgumentParser(
description="Calculate Baseline Tolerance partial statistics per feature")
cmd = DefaultCommandHelper(parser)
parser.add_argument("scores_path", metavar="SCORES_PATH",
help="The scores file")
parser.add_argument("predictors", metavar="PREDICTORS",
help="Comma separated list of predictors")
parser.add_argument("out_path", metavar="OUTPUT_PATH",
help="Output file.")
cmd.add_transform_args()
args, logger = cmd.parse_args("blt-partial")
predictors = [p.strip() for p in args.predictors.split(",") if len(p.strip()) > 0]
num_predictors = len(predictors)
if len(predictors) == 0:
logger.error("At least one predictor is needed")
exit(-1)
logger.info("Selected predictors: {}".format(", ".join(predictors)))
transforms = cmd.get_transforms()
stats = {}
lost_snvs = 0
scores_path = args.scores_path
logger.info("Reading scores from {} ...".format(
os.path.basename(scores_path) if scores_path != "-" else "standard input"))
with tsv.open(scores_path) as sf:
for line_num, line in enumerate(sf):
fields = line.rstrip("\n").split("\t")
chrom, pos, ref, alt, feature = fields[:5]
if len(feature) == 0:
lost_snvs += 1
continue
scores = fields[5:]
if len(scores) != num_predictors:
line_error(logger, scores_path, line_num, "Number of score columns does not match the number of predictors")
try:
scores = [float(v) if len(v) > 0 else None for v in scores]
except:
line_error(logger, scores_path, line_num, "Scores should be real numbers: {}".format(scores))
if feature not in stats:
stats[feature] = tuple([[0, 0.0, 0.0] for p in predictors])
feature_stats = stats[feature]
for i, score in enumerate(scores):
if score is not None:
predictor = predictors[i]
if predictor in transforms:
for name, func in transforms[predictor]:
try:
score = func(score)
except:
logger.error("Error transforming the {} score {} with {}".format(predictor, score, name))
exit(-1)
feature_stats[i][0] += 1
feature_stats[i][1] += score
feature_stats[i][2] += score * score
logger.info("Saving results into {} ...".format(
os.path.basename(args.out_path) if args.out_path != "-" else "standard output"))
with tsv.open(args.out_path, "w") as of:
tsv.write_line(of, "FEATURE", *predictors)
for feature in sorted(stats.keys()):
sb = [feature]
feature_stats = stats[feature]
for i in range(num_predictors):
sb += ["/".join([repr(v) for v in feature_stats[i]])]
tsv.write_line(of, *sb)
logger.info("Number of SNV's = {}, lost SNV's = {}, number of features = {}".format(line_num, lost_snvs, len(stats)))
return 0
def main():
parser = argparse.ArgumentParser(
description="Calculate TransFIC cutoffs")
cmd = DefaultCommandHelper(parser)
parser.add_argument("ranges_path", metavar="RANGES_PATH",
help="JSON file generated with pred-list containing predictors stats. Only min and max are used.")
parser.add_argument("scores_path", metavar="SCORES_PATH",
help="The dataset with scores for non recurrent and highly recurrent. ID column should be NON/HIGH for non-rec/highly-rec datasets.")
parser.add_argument("-o", dest="out_path", metavar="OUT_PATH",
help="The file where cutoffs will be saved. Use - for standard output.")
cmd.add_selected_predictors_args()
parser.add_argument("-P", "--precision", dest="precision", metavar="PRECISION", type=int, default=3,
help="Distribution precision")
cmd.add_transform_args()
args, logger = cmd.parse_args("cutoffs")
if args.out_path is None:
prefix = os.path.splitext(os.path.basename(args.scores_path))[0]
if prefix.endswith("-scores"):
prefix = prefix[:-7]
args.out_path = os.path.join(os.getcwd(), "{}-cutoffs.json".format(prefix))
try:
logger.info("Loading ranges from {} ...".format(os.path.basename(args.ranges_path)))
with open(args.ranges_path) as f:
pred_stats = json.load(f)
predictor_range = {}
for pid, pstats in pred_stats.items():
predictor_range[pid] = (pstats["min"], pstats["max"])
transforms = cmd.get_transforms()
logger.info("Reading datasets {} ...".format(args.scores_path if args.scores_path != "-" else "from standard input"))
with tsv.open(args.scores_path) as f:
# Select predictors from the available predictors in the dataset or user selection
column_names, column_indices = tsv.header(f)
excluded_columns = set(COORD_COLUMNS) | set(["ID"])
available_predictors = [c for c in column_names if c not in excluded_columns]
predictors = cmd.get_selected_predictors(available_predictors)
# Initialize statistics
step = 1.0 / 10**args.precision
stats = dict()
state = dict(
predictors = predictors,
stats = stats,
transforms=dict([(p, [e for e, _ in t]) for p, t in transforms.items()]),
precision = args.precision,
step = step)
for predictor in predictors:
rmin, rmax = predictor_range[predictor] if predictor in predictor_range else (0.0, 1.0)
dim = rmax - rmin
size = int(dim / step) + 1
values = [(x * step) + rmin for x in xrange(size)]
stats[predictor] = dict(
rmin = rmin,
rmax = rmax,
dim = dim,
values = values,
size = size,
vmin = None,
vmax = None,
dp = [0] * size,
dn = [0] * size,
cdp = [0] * size,
cdn = [0] * size,
cump = 0,
cumn = 0,
cutoff = None,
cutoff_index = None)
counts = load_events(f, column_indices, predictors, transforms, stats, logger)
logger.info(" {}".format(", ".join(["{}={}".format(n, c) for n, c in counts.items()])))
logger.info("Calculating cumulative distribution ...")
for predictor in predictors:
predictor_stats = stats[predictor]
dp, dn, cdp, cdn = [predictor_stats[k] for k in ["dp", "dn", "cdp", "cdn"]]
cump = 0
cumn = 0
i = len(dp) - 1
while i >= 0:
#cdp[i] = dp[i] + cump
cump += dp[i]
cdp[i] = cump
cdn[i] = dn[i] + cumn
cumn += dn[i]
i -= 1
predictor_stats["cump"] = cump
predictor_stats["cumn"] = cumn
logger.info(" {}: cump={}, cumn={}".format(predictor, cump, cumn))
logger.info("Calculating cutoffs ...")
for predictor in predictors:
predictor_stats = stats[predictor]
values, size, vmin, vmax, cump, cumn, cdp, cdn = [predictor_stats[k] for k in [
"values", "size", "vmin", "vmax", "cump", "cumn", "cdp", "cdn"]]
cutoff_low_mid_index = -1
i = 0
while (i < size) and (cdp[i] / float(cump) >= 0.95):
cutoff_low_mid_index = i
i += 1
cutoff_low_mid = values[cutoff_low_mid_index]
predictor_stats["cutoff_low_mid"] = cutoff_low_mid
predictor_stats["cutoff_low_mid_index"] = cutoff_low_mid_index
cutoff_mid_high_index = -1
i = 0
while (i < size) and (cdn[i] / float(cumn) >= 0.20):
cutoff_mid_high_index = i
i += 1
cutoff_mid_high = values[cutoff_mid_high_index]
predictor_stats["cutoff_mid_high"] = cutoff_mid_high
predictor_stats["cutoff_mid_high_index"] = cutoff_mid_high_index
logger.info(" {}: cutoffs: vmin={}, low_mid={}, mid_high={}, vmax={}".format(predictor, vmin, cutoff_low_mid, cutoff_mid_high, vmax))
logger.info("Saving state ...")
out_path = args.out_path
save_weights(out_path, state)
except:
cmd.handle_error()
return 0