def loadBioProspector(infile, outfile): '''load results from bioprospector.''' target_path = os.path.join( os.path.abspath(PARAMS["exportdir"]), "bioprospector") try: os.makedirs(target_path) except OSError: pass track = infile[:-len(".bioprospector")] results = Bioprospector.parse(IOTools.openFile(infile, "r")) tmpfile = P.getTempFile() tmpfile.write("id\tmotif\tstart\tend\tstrand\tarrangement\n") for x, motifs in enumerate(results): outname = os.path.join(target_path, "%s_%02i.png" % (track, x)) Bioprospector.build_logo([y.sequence for y in motifs.matches], outname) for match in motifs.matches: distance = abs( match.start + match.width1 - (match.end - match.width2)) if match.strand in ("+-", "-+"): arrangement = "ER" elif match.strand in ("++", "--"): arrangement = "DR" else: arrangement = "SM" distance = 0 arrangement += "%i" % distance strand = match.strand[0] id = re.sub(".*_", "", match.id) tmpfile.write("%s\t%i\t%i\t%i\t%s\t%s\n" % (id, x, match.start, match.end, strand, arrangement)) 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 loadBioProspector(infile, outfile): '''load results from bioprospector.''' tablename = outfile[:-len(".load")] target_path = os.path.join(os.path.abspath(PARAMS["exportdir"]), "bioprospector") try: os.makedirs(target_path) except OSError: pass track = infile[:-len(".bioprospector")] results = Bioprospector.parse(IOTools.openFile(infile, "r")) tmpfile = P.getTempFile() tmpfile.write("id\tmotif\tstart\tend\tstrand\tarrangement\n") for x, motifs in enumerate(results): outname = os.path.join(target_path, "%s_%02i.png" % (track, x)) Bioprospector.build_logo([y.sequence for y in motifs.matches], outname) for match in motifs.matches: distance = abs(match.start + match.width1 - (match.end - match.width2)) if match.strand in ("+-", "-+"): arrangement = "ER" elif match.strand in ("++", "--"): arrangement = "DR" else: arrangement = "SM" distance = 0 arrangement += "%i" % distance strand = match.strand[0] id = re.sub(".*_", "", match.id) tmpfile.write("%s\t%i\t%i\t%i\t%s\t%s\n" % (id, x, match.start, match.end, strand, arrangement)) tmpfile.close() tmpfilename = tmpfile.name statement = ''' python %(scriptsdir)s/csv2db.py %(csv2db_options)s \ --allow-empty \ -b sqlite \ --index=id \ --index=motif \ --index=id,motif \ --table=%(tablename)s \ < %(tmpfilename)s > %(outfile)s ''' P.run()
def loadBioProspector(infile, outfile): '''load results from bioprospector.''' tablename = outfile[:-len(".load")] target_path = os.path.join( os.path.abspath(PARAMS["exportdir"]), "bioprospector") try: os.makedirs(target_path) except OSError: pass track = infile[:-len(".bioprospector")] results = Bioprospector.parse(IOTools.openFile(infile, "r")) tmpfile = P.getTempFile() tmpfile.write("id\tmotif\tstart\tend\tstrand\tarrangement\n") for x, motifs in enumerate(results): outname = os.path.join(target_path, "%s_%02i.png" % (track, x)) Bioprospector.build_logo([y.sequence for y in motifs.matches], outname) for match in motifs.matches: distance = abs( match.start + match.width1 - (match.end - match.width2)) if match.strand in ("+-", "-+"): arrangement = "ER" elif match.strand in ("++", "--"): arrangement = "DR" else: arrangement = "SM" distance = 0 arrangement += "%i" % distance strand = match.strand[0] id = re.sub(".*_", "", match.id) tmpfile.write("%s\t%i\t%i\t%i\t%s\t%s\n" % (id, x, match.start, match.end, strand, arrangement)) tmpfile.close() tmpfilename = tmpfile.name statement = ''' python %(scriptsdir)s/csv2db.py %(csv2db_options)s \ --allow-empty \ -b sqlite \ --index=id \ --index=motif \ --index=id,motif \ --table=%(tablename)s \ < %(tmpfilename)s > %(outfile)s ''' P.run()