def create_roc_plots(pwmfile, fgfa, background, outdir):
"""Make ROC plots for all motifs."""
motifs = read_motifs(pwmfile, fmt="pwm", as_dict=True)
ncpus = int(MotifConfig().get_default_params()['ncpus'])
pool = Pool(processes=ncpus)
jobs = {}
for bg,fname in background.items():
for m_id, m in motifs.items():
k = "{}_{}".format(str(m), bg)
jobs[k] = pool.apply_async(
get_roc_values,
(motifs[m_id], fgfa, fname,)
)
imgdir = os.path.join(outdir, "images")
if not os.path.exists(imgdir):
os.mkdir(imgdir)
roc_img_file = os.path.join(outdir, "images", "{}_roc.{}.png")
for motif in motifs.values():
for bg in background:
k = "{}_{}".format(str(motif), bg)
error, x, y = jobs[k].get()
if error:
logger.error("Error in thread: %s", error)
logger.error("Motif: %s", motif)
sys.exit(1)
roc_plot(roc_img_file.format(motif.id, bg), x, y)
def create_roc_plots(pfmfile, fgfa, background, outdir, genome):
"""Make ROC plots for all motifs."""
motifs = read_motifs(pfmfile, fmt="pwm", as_dict=True)
ncpus = int(MotifConfig().get_default_params()["ncpus"])
pool = Pool(processes=ncpus)
jobs = {}
for bg, fname in background.items():
for m_id, m in motifs.items():
k = "{}_{}".format(str(m), bg)
jobs[k] = pool.apply_async(get_roc_values,
(motifs[m_id], fgfa, fname, genome))
imgdir = os.path.join(outdir, "images")
if not os.path.exists(imgdir):
os.mkdir(imgdir)
roc_img_file = os.path.join(outdir, "images", "{}_roc.{}.png")
for motif in motifs.values():
for bg in background:
k = "{}_{}".format(str(motif), bg)
error, x, y = jobs[k].get()
if error:
logger.error("Error in thread: %s", error)
logger.error("Motif: %s", motif)
sys.exit(1)
roc_plot(roc_img_file.format(motif.id, bg), x, y)
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)
def create_roc_plots(self, pwm_file, fg_fasta, bg_fasta, name):
motifs = dict([(m.id, m) for m in read_motifs(open(pwm_file), fmt="pwm")])
jobs = {}
for id,m in motifs.items():
jobs[id] = self.job_server().apply_async(get_roc_values, (motifs[id],fg_fasta,bg_fasta,))
roc_img_file = os.path.join(self.imgdir, "%s_%s_roc.png")
for id in motifs.keys():
error, x, y = jobs[id].get()
if error:
self.logger.error("Error in thread: %s", error)
sys.exit(1)
roc_plot(roc_img_file % (id,name), x, y)
def create_roc_plots(self, pwm_file, fg_fasta, bg_fasta, name):
motifs = dict([(m.id, m)
for m in read_motifs(open(pwm_file), fmt="pwm")])
jobs = {}
for id, m in motifs.items():
jobs[id] = self.job_server().apply_async(get_roc_values, (
motifs[id],
fg_fasta,
bg_fasta,
))
roc_img_file = os.path.join(self.imgdir, "%s_%s_roc.png")
for id in motifs.keys():
error, x, y = jobs[id].get()
if error:
self.logger.error("Error in thread: %s", error)
sys.exit(1)
roc_plot(roc_img_file % (id, name), x, y)
def roc(args):
""" Calculate ROC_AUC and other metrics and optionally plot ROC curve."""
outputfile = args.outfile
# Default extension for image
if outputfile and not outputfile.endswith(".png"):
outputfile += ".png"
motifs = read_motifs(open(args.pwmfile), fmt="pwm")
ids = []
if args.ids:
ids = args.ids.split(",")
else:
ids = [m.id for m in motifs]
motifs = [m for m in motifs if (m.id in ids)]
stats = [
"phyper_at_fpr",
"roc_auc",
"enr_at_fpr",
"max_enrichment",
"recall_at_fdr",
"roc_values",
"matches_at_fpr",
]
motif_stats = calc_stats(motifs,
args.sample,
args.background,
genome=args.genome,
stats=stats)
plot_x = []
plot_y = []
legend = []
f_out = sys.stdout
if args.outdir:
if not os.path.exists(args.outdir):
os.makedirs(args.outdir)
f_out = open(args.outdir + "/gimme.roc.report.txt", "w")
# Print the metrics
f_out.write(
"Motif\t# matches\t# matches background\tP-value\tlog10 P-value\tROC AUC\tEnr. at 1% FPR\tRecall at 10% FDR\n"
)
for motif in motifs:
if outputfile:
x, y = motif_stats[str(motif)]["roc_values"]
plot_x.append(x)
plot_y.append(y)
legend.append(motif.id)
log_pvalue = np.inf
if motif_stats[str(motif)]["phyper_at_fpr"] > 0:
log_pvalue = -np.log10(motif_stats[str(motif)]["phyper_at_fpr"])
f_out.write(
"{}\t{:d}\t{:d}\t{:.2e}\t{:.3f}\t{:.3f}\t{:.2f}\t{:0.4f}\n".format(
motif.id,
motif_stats[str(motif)]["matches_at_fpr"][0],
motif_stats[str(motif)]["matches_at_fpr"][1],
motif_stats[str(motif)]["phyper_at_fpr"],
log_pvalue,
motif_stats[str(motif)]["roc_auc"],
motif_stats[str(motif)]["enr_at_fpr"],
motif_stats[str(motif)]["recall_at_fdr"],
))
f_out.close()
if args.outdir:
html_report(
args.outdir,
args.outdir + "/gimme.roc.report.txt",
args.pwmfile,
0.01,
)
# Plot the ROC curve
if outputfile:
roc_plot(outputfile, plot_x, plot_y, ids=legend)
def roc(args):
""" Calculate ROC_AUC and other metrics and optionally plot ROC curve."""
outputfile = args.outfile
# Default extension for image
if outputfile and not outputfile.endswith(".png"):
outputfile += ".png"
motifs = read_motifs(args.pwmfile, fmt="pwm")
ids = []
if args.ids:
ids = args.ids.split(",")
else:
ids = [m.id for m in motifs]
motifs = [m for m in motifs if (m.id in ids)]
stats = [
"phyper_at_fpr",
"roc_auc",
"pr_auc",
"enr_at_fpr",
"recall_at_fdr",
"roc_values",
"matches_at_fpr",
]
plot_x = []
plot_y = []
legend = []
f_out = sys.stdout
if args.outdir:
if not os.path.exists(args.outdir):
os.makedirs(args.outdir)
f_out = open(args.outdir + "/gimme.roc.report.txt", "w")
# Print the metrics
f_out.write("Motif\t# matches\t# matches background\tP-value\tlog10 P-value\tROC AUC\tPR AUC\tEnr. at 1% FPR\tRecall at 10% FDR\n")
for motif_stats in calc_stats_iterator(motifs, args.sample, args.background,
genome=args.genome, stats=stats, ncpus=args.ncpus):
for motif in motifs:
if str(motif) in motif_stats:
if outputfile:
x, y = motif_stats[str(motif)]["roc_values"]
plot_x.append(x)
plot_y.append(y)
legend.append(motif.id)
log_pvalue = np.inf
if motif_stats[str(motif)]["phyper_at_fpr"] > 0:
log_pvalue = -np.log10(motif_stats[str(motif)]["phyper_at_fpr"])
f_out.write("{}\t{:d}\t{:d}\t{:.2e}\t{:.3f}\t{:.3f}\t{:.3f}\t{:.2f}\t{:0.4f}\n".format(
motif.id,
motif_stats[str(motif)]["matches_at_fpr"][0],
motif_stats[str(motif)]["matches_at_fpr"][1],
motif_stats[str(motif)]["phyper_at_fpr"],
log_pvalue,
motif_stats[str(motif)]["roc_auc"],
motif_stats[str(motif)]["pr_auc"],
motif_stats[str(motif)]["enr_at_fpr"],
motif_stats[str(motif)]["recall_at_fdr"],
))
f_out.close()
if args.outdir:
html_report(
args.outdir,
args.outdir + "/gimme.roc.report.txt",
args.pwmfile,
0.01,
)
# Plot the ROC curve
if outputfile:
roc_plot(outputfile, plot_x, plot_y, ids=legend)
