def loadGLAM2SCAN(infile, outfile):
'''parse mast file and load into database.
Parse several motif runs and add them to the same
table.
'''
tmpfile = tempfile.NamedTemporaryFile(delete=False)
tmpfile.write(
"motif\tid\tnmatches\tscore\tscores\tncontrols\tmax_controls\n")
lines = iotools.open_file(infile).readlines()
chunks = [x for x in range(len(lines)) if lines[x].startswith("::")]
chunks.append(len(lines))
for chunk in range(len(chunks) - 1):
# use real file, as parser can not deal with a
# list of lines
try:
motif = re.match(":: motif = (\S+) ::",
lines[chunks[chunk]]).groups()[0]
except AttributeError:
raise ValueError("parsing error in line '%s'" %
lines[chunks[chunk]])
if chunks[chunk] + 1 == chunks[chunk + 1]:
L.warn("no results for motif %s - ignored" % motif)
continue
tmpfile2 = tempfile.NamedTemporaryFile(delete=False)
tmpfile2.write("".join(lines[chunks[chunk] + 1:chunks[chunk + 1]]))
tmpfile2.close()
glam = Glam2Scan.parse(iotools.open_file(tmpfile2.name, "r"))
os.unlink(tmpfile2.name)
# collect control data
full_matches = collections.defaultdict(list)
controls = collections.defaultdict(list)
for match in glam.matches:
m = match.id.split("_")
track, id = m[:2]
if len(m) == 2:
full_matches[id].append(match)
else:
controls[id].append(match.score)
for id, matches in full_matches.items():
nmatches = len(matches)
scores = [x.score for x in matches]
score = max(scores)
# move to genomic coordinates
# contig, start, end = re.match( "(\S+):(\d+)..(\d+)", match.id).groups()
# start, end = int(start), int(end)
# match.start += start
# match.end += start
contig = ""
if id not in controls:
P.warn("no controls for %s - increase evalue?" % id)
c = controls[id]
if len(c) == 0:
mmax = ""
else:
mmax = max(c)
tmpfile.write("\t".join(
map(str, (motif, id, nmatches, score,
",".join(map(str, scores)), len(c), mmax))) + "\n")
tmpfile.close()
P.load(tmpfile.name,
outfile,
options="--add-index=id "
"--add-index=motif "
"--add-index=id,motif "
"--allow-empty-file "
"--map=base_qualities:text")
os.unlink(tmpfile.name)
def loadMAST(infile, outfile):
'''parse mast file and load into database.
Parse several motif runs and add them to the same
table.
Add columns for the control data as well.
'''
tablename = P.to_table(outfile)
tmpfile = P.get_temp_file(".")
tmpfile.write(MAST.Match().header + "\tmotif\tcontig"
"\tl_evalue\tl_pvalue\tl_nmatches\tl_length\tl_start\tl_end"
"\tr_evalue\tr_pvalue\tr_nmatches\tr_length\tr_start\tr_end"
"\tmin_evalue\tmin_pvalue\tmax_nmatches" + "\n")
lines = iotools.open_file(infile).readlines()
chunks = [x for x in range(len(lines)) if lines[x].startswith("::")]
chunks.append(len(lines))
def readChunk(lines, chunk):
# use real file, as MAST parser can not deal with a
# list of lines
tmpfile2 = P.get_temp_file(".")
try:
motif, part = re.match(":: motif = (\S+) - (\S+) ::",
lines[chunks[chunk]]).groups()
except AttributeError:
raise ValueError("parsing error in line '%s'" %
lines[chunks[chunk]])
E.info("reading %s - %s" % (motif, part))
tmpfile2.write("".join(lines[chunks[chunk] + 1:chunks[chunk + 1]]))
tmpfile2.close()
mast = MAST.parse(iotools.open_file(tmpfile2.name, "r"))
os.unlink(tmpfile2.name)
return motif, part, mast
def splitId(s, mode):
'''split background match id
has three parts: track _ id _ pos
track might contain '_'.
'''
d = match.id.split("_")
if mode == "bg":
return "_".join(d[:-2]), d[-2], d[-1]
elif mode == "fg":
return "_".join(d[:-1]), d[-1]
for chunk in range(0, len(chunks) - 1, 2):
motif_fg, part, mast_fg = readChunk(lines, chunk)
assert part == "foreground"
motif_bg, part, mast_bg = readChunk(lines, chunk + 1)
assert part == "background"
assert motif_fg == motif_bg
# index control data
controls = collections.defaultdict(dict)
for match in mast_bg.matches:
track, id, pos = splitId(match.id, "bg")
controls[id][pos] = (match.evalue, match.pvalue, match.nmotifs,
match.length, match.start, match.end)
for match in mast_fg.matches:
# remove track and pos
track, match.id = splitId(match.id, "fg")
# move to genomic coordinates
contig, start, end = re.match("(\S+):(\d+)..(\d+)",
match.description).groups()
if match.nmotifs > 0:
start, end = int(start), int(end)
match.start += start
match.end += start
match.positions = [x + start for x in match.positions]
id = match.id
if id not in controls:
P.warn("no controls for %s - increase MAST evalue" % id)
if "l" not in controls[id]:
controls[id]["l"] = (float(P.get_params()["mast_evalue"]), 1,
0, 0, 0, 0)
if "r" not in controls[id]:
controls[id]["r"] = (float(P.get_params()["mast_evalue"]), 1,
0, 0, 0, 0)
min_evalue = min(controls[id]["l"][0], controls[id]["r"][0])
min_pvalue = min(controls[id]["l"][1], controls[id]["r"][1])
max_nmatches = max(controls[id]["l"][2], controls[id]["r"][2])
tmpfile.write(
str(match) + "\t%s\t%s\t%s\t%s\t%s\t%s\t%s" % (
motif_fg,
contig,
"\t".join(map(str, controls[id]["l"])),
"\t".join(map(str, controls[id]["r"])),
str(min_evalue),
str(min_pvalue),
str(max_nmatches),
) + "\n")
tmpfile.close()
P.load(tmpfile.name,
outfile,
options="--add-index=id "
"--add-index=motif "
"--add-index=id,motif "
"--allow-empty-file "
"--map=base_qualities:text")
os.unlink(tmpfile.name)
def printTracks(infile, outfile):
P.warn("\n\n\n\nprinting tracks:")
for track in EXPERIMENTS:
print("\t")
print(track)