def stats(self, fg_fa, bg_fa, logger=None):
try:
stats = {}
fg_result = self.pwm_scan_all(fg_fa,
cutoff=0.0,
nreport=1,
scan_rc=True)
bg_result = self.pwm_scan_all(bg_fa,
cutoff=0.0,
nreport=1,
scan_rc=True)
pos = []
for x in fg_result.values():
if len(x):
pos.append(x[0][1])
else:
pos.append(-100)
neg = []
for x in bg_result.values():
if len(x):
neg.append(x[0][1])
else:
neg.append(-100)
stats["mncp"] = MNCP(pos, neg)
stats["roc_auc"] = ROC_AUC(pos, neg)
x, y = max_enrichment(pos, neg)
stats["maxenr"] = x
stats["scoreatmaxenr"] = y
stats["fraction"] = fraction_fdr(pos, neg)
stats["score_fdr"] = score_at_fdr(pos, neg)
stats["enr_fdr"] = enr_at_fdr(pos, neg)
stats["cutoff_fdr"] = (stats["score_fdr"] - self.pwm_min_score()
) / (self.pwm_max_score() -
self.pwm_min_score())
pos = [x[0][0] for x in fg_result.values() if len(x)]
p = ks_pvalue(pos, max(pos))
stats["ks"] = p
if p > 0:
stats["ks_sig"] = -log(p) / log(10)
else:
stats["ks_sig"] = "Inf"
return stats
except Exception as e:
#e = sys.exc_info()[0]
msg = "Error calculating stats of {0}, error {1}".format(
self.id, str(e))
if logger:
logger.error(msg)
else:
print msg
raise
def stats(self, fg_fa, bg_fa, logger=None):
from gimmemotifs.rocmetrics import MNCP, ROC_AUC, max_enrichment, fraction_fdr, score_at_fdr, enr_at_fdr
from gimmemotifs.fasta import Fasta
from gimmemotifs.utils import ks_pvalue
from numpy import array, std
from math import log
try:
stats = {}
fg_result = self.pwm_scan_all(fg_fa, cutoff=0.0, nreport=1, scan_rc=True)
bg_result = self.pwm_scan_all(bg_fa, cutoff=0.0, nreport=1, scan_rc=True)
pos = []
for x in fg_result.values():
if len(x):
pos.append(x[0][1])
else:
pos.append(-100)
neg = []
for x in bg_result.values():
if len(x):
neg.append(x[0][1])
else:
neg.append(-100)
stats["mncp"] = MNCP(pos, neg)
stats["roc_auc"] = ROC_AUC(pos, neg)
x, y = max_enrichment(pos, neg)
stats["maxenr"] = x
stats["scoreatmaxenr"] = y
stats["fraction"] = fraction_fdr(pos, neg)
stats["score_fdr"] = score_at_fdr(pos, neg)
stats["enr_fdr"] = enr_at_fdr(pos, neg)
stats["cutoff_fdr"] = (stats["score_fdr"] - self.pwm_min_score()) / (
self.pwm_max_score() - self.pwm_min_score()
)
pos = [x[0][0] for x in fg_result.values() if len(x)]
p = ks_pvalue(pos, max(pos))
stats["ks"] = p
if p > 0:
stats["ks_sig"] = -log(p) / log(10)
else:
stats["ks_sig"] = "Inf"
return stats
except Exception as e:
raise
# e = sys.exc_info()[0]
msg = "Error calculating stats of {0}, error {1}".format(self.id, str(e))
if logger:
logger.error(msg)
else:
print msg
def roc(args):
""" Calculate ROC_AUC and other metrics and optionally plot ROC curve.
"""
pwmfile = args.pwmfile
fg_file = args.sample
bg_file = args.background
outputfile = args.outfile
# Default extension for image
if outputfile and not outputfile.endswith(".png"):
outputfile += ".png"
motifs = read_motifs(open(pwmfile), fmt="pwm")
s = Scanner()
s.set_motifs(pwmfile)
ids = []
if args.ids:
ids = args.ids.split(",")
else:
ids = [m.id for m in motifs]
fg_total = dict([(m.id, []) for m in motifs])
for scores in s.best_score(fg_file):
for motif,score in zip(motifs, scores):
fg_total[motif.id].append(score)
bg_total = dict([(m.id, []) for m in motifs])
for scores in s.best_score(bg_file):
for motif,score in zip(motifs, scores):
bg_total[motif.id].append(score)
plot_x = []
plot_y = []
# Print the metrics
print "Motif\tROC AUC\tMNCP\tEnr. at 5% FDR\tMax enr.\tRecall at 10% FDR"
for motif_id in ids:
fg_vals = fg_total[motif_id]
bg_vals = bg_total[motif_id]
(x, y) = ROC_values(fg_vals, bg_vals)
plot_x.append(x)
plot_y.append(y)
auc = ROC_AUC(fg_vals, bg_vals)
mncp = MNCP(fg_vals, bg_vals)
enr_fdr = enr_at_fdr(fg_vals, bg_vals)
max_enr,score = max_enrichment(fg_vals, bg_vals)
recall = recall_at_fdr(fg_vals, bg_vals, 0.1)
print "%s\t%0.3f\t%03f\t%0.2f\t%0.2f\t%0.4f" % (
motif_id, auc, mncp, enr_fdr, max_enr, recall)
# Plot the ROC curve
if outputfile:
roc_plot(outputfile, plot_x, plot_y, ids=ids)
def roc(args):
""" Calculate ROC_AUC and other metrics and optionally plot ROC curve.
"""
pwmfile = args.pwmfile
fg_file = args.sample
bg_file = args.background
outputfile = args.outfile
# Default extension for image
if outputfile and not outputfile.endswith(".png"):
outputfile += ".png"
motifs = read_motifs(open(pwmfile), fmt="pwm")
s = Scanner()
s.set_motifs(pwmfile)
ids = []
if args.ids:
ids = args.ids.split(",")
else:
ids = [m.id for m in motifs]
fg_total = dict([(m.id, []) for m in motifs])
for scores in s.best_score(fg_file):
for motif, score in zip(motifs, scores):
fg_total[motif.id].append(score)
bg_total = dict([(m.id, []) for m in motifs])
for scores in s.best_score(bg_file):
for motif, score in zip(motifs, scores):
bg_total[motif.id].append(score)
plot_x = []
plot_y = []
# Print the metrics
print "Motif\tROC AUC\tMNCP\tEnr. at 5% FDR\tMax enr."
for motif_id in ids:
fg_vals = fg_total[motif_id]
bg_vals = bg_total[motif_id]
(x, y) = ROC_values(fg_vals, bg_vals)
plot_x.append(x)
plot_y.append(y)
auc = ROC_AUC(fg_vals, bg_vals)
mncp = MNCP(fg_vals, bg_vals)
enr_fdr = enr_at_fdr(fg_vals, bg_vals)
max_enr, score = max_enrichment(fg_vals, bg_vals)
print "%s\t%0.3f\t%03f\t%0.2f\t%0.2f" % (motif_id, auc, mncp, enr_fdr,
max_enr)
# Plot the ROC curve
if outputfile:
roc_plot(outputfile, plot_x, plot_y, ids=ids)
def roc(args):
""" Calculate ROC_AUC and other metrics and optionally plot ROC curve.
"""
pwmfile = args.pwmfile
fg_file = args.sample
bg_file = args.background
outputfile = args.outfile
# Default extension for image
if outputfile and not outputfile.endswith(".png"):
outputfile += ".png"
motifs = dict([(x.id, x) for x in pwmfile_to_motifs(pwmfile)])
ids = []
if args.ids:
ids = args.ids.split(",")
else:
ids = motifs.keys()
fg_total = {}
result = scan(fg_file, [motifs[x] for x in ids], 0.0, 1)
for key,m in result.items():
fg_total[key.id.split("\t")[0]] = [matches[0][1] for matches in m.values()]
bg_total = {}
result = scan(bg_file, [motifs[x] for x in ids], 0.0, 1)
for key,m in result.items():
bg_total[key.id.split("\t")[0]] = [matches[0][1] for matches in m.values()]
plot_x = []
plot_y = []
# Print the metrics
print "Motif\tROC AUC\tMNCP\tEnr. at 5% FDR\tMax enr."
for id in ids:
fg_vals = fg_total[id]
bg_vals = bg_total[id]
(x, y) = ROC_values(fg_vals, bg_vals)
plot_x.append(x)
plot_y.append(y)
auc = ROC_AUC(fg_vals, bg_vals)
mncp = MNCP(fg_vals, bg_vals)
enr_fdr = enr_at_fdr(fg_vals, bg_vals)
max_enr,score = max_enrichment(fg_vals, bg_vals)
print "%s\t%0.3f\t%03f\t%0.2f\t%0.2f" % (id, auc, mncp, enr_fdr, max_enr)
# Plot the ROC curve
if outputfile:
roc_plot(outputfile, plot_x, plot_y, ids=ids)
