def readGenomesFromFile(multi_files_fname, genome_dir, genome_dicts, column_index=1, load_fxn=biofile.firstField, species=None, outstream=None): if outstream is None: outstream = util.OutStreams() # Format for species_map = {} for line in file(multi_files_fname,'r').readlines(): if line[0] != '#' and not line.strip() == '': # skip comments and blank lines flds = line.strip().split() #print flds, column_index species_map[flds[0]] = flds[column_index] if species is None: species = species_map.keys() else: assert set(species).intersection(set(species_map.keys())) == set(species), "Not all specified species found in mapping file" for spec in species: genome_file = os.path.join(os.path.expanduser(genome_dir), species_map[spec]) if not os.path.isfile(genome_file): outstream.write("# Cannot find file %s\n" % genome_file) genome = biofile.readFASTADict(genome_file, load_fxn) genome_dicts[spec] = genome outstream.write("# species=%s, genome file=%s has %d entries, example ID=%s\n" % (spec, genome_file, len(genome.keys()), genome.keys()[0])) return species_map
# Required arguments parser.add_argument(dest="orthodb_id", type=str, help="OrthoDB ID") # Optional arguments parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") parser.add_argument("--fasta-out", dest="fasta_out_fname", default=None, help="output FASTA filename") #parser.add_argument("-o", "--out-dir", dest="out_dir", default='', help="output file directory") options = parser.parse_args() info_outs = util.OutStreams() #data_outs = util.OutStreams() fasta_outs = util.OutStreams() # Start up output if not options.out_fname is None: outf = file(options.out_fname, 'w') info_outs.addStream(outf) else: # By default, write to stdout info_outs.addStream(sys.stdout) if not options.fasta_out_fname is None: outf = file(options.fasta_out_fname, 'w') fasta_outs.addStream(outf) else: # By default, write to stdout
pos = n-1 return pval_list[pos] if __name__=='__main__': parser = argparse.ArgumentParser(description="Compute P-values for entropy") # Required arguments parser.add_argument(dest="in_fname", help="input filename") parser.add_argument(dest="in_distribution_fname_pattern", help="input distribution filename pattern") # Optional arguments parser.add_argument("-a", "--adjust", dest="adjust", action='store_true', default=False, help="adjust P-values") parser.add_argument("-l", "--lower", dest="min_window_size", default=5, help="minimum window size") parser.add_argument("-u", "--upper", dest="max_window_size", default=300, help="maximum window size") parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") options = parser.parse_args() info_outs = util.OutStreams(sys.stdout) data_outs = util.OutStreams() # Start up output if not options.out_fname is None: outf = file(options.out_fname,'w') data_outs.addStream(outf) else: # By default, write to stdout data_outs.addStream(sys.stdout) # Write out parameters data_outs.write("# Run started {}\n".format(util.timestamp(timeformat="%a %b %d %H:%M:%S %Y"))) data_outs.write("# Parameters:\n") optdict = vars(options) for (k,v) in optdict.items():
help="random-number generator seed") parser.add_argument("-p", "--optimize", dest="optimize", action="store_true", default=False, help="optimize the codons?") options = parser.parse_args() # Fetch sequence seq = options.sequence random.seed(options.seed) # Start up output info_outs = util.OutStreams([sys.stdout]) data_outs = util.OutStreams() multi_outs = util.OutStreams([info_outs, data_outs]) if not options.out_fname is None: outf = file(options.out_fname, 'w') data_outs.addStream(outf) else: data_outs.addStream(sys.stdout) # Read sequences from a FASTA file? fname = os.path.expanduser(seq) if os.path.isfile(fname): (headers, seq_list) = biofile.readFASTA(fname) seqs = zip(headers, seq_list) info_outs.write("# Read {0:d} sequences from {1}\n".format( len(seqs), fname))
action="store_true", default=False, help="generate short species IDs (e.g. S.cerevisiae) for each sequence?" ) parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") parser.add_argument("--fasta-out", dest="fasta_out_fname", default=None, help="FASTA output filename") options = parser.parse_args() info_outs = util.OutStreams(sys.stdout) data_outs = util.OutStreams() # Start up output if not options.out_fname is None: outf = open(options.out_fname, 'w') data_outs.addStream(outf) else: # By default, write to stdout data_outs.addStream(sys.stdout) # Write out parameters data_outs.write("# Run started {}\n".format(util.timestamp())) data_outs.write("# Command: {}\n".format(' '.join(sys.argv))) data_outs.write("# Parameters:\n") optdict = vars(options)
if prot_align[i] == '-': out_align += "-" else: out_align += prot[j] j += 1 return out_align if __name__=='__main__': parser = argparse.ArgumentParser(description="Muscle alignment") parser.add_argument("in_fname", help="input filename") parser.add_argument("-p", "--path", dest="muscle_path", default=const_default_muscle_exepath, help="path to Muscle binary") parser.add_argument("-t", "--translate", dest="translate", action="store_true", default=False, help="translate the input sequences?") parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") options = parser.parse_args() outs = util.OutStreams() if not options.out_fname is None: fname = os.path.expanduser(options.out_fname) #print fname outf = open(fname,'w') outs.addStream(outf) else: outs.addStream(sys.stdout) (headers, seqs) = biofile.readFASTA(open(options.in_fname,'r')) seqs_to_align = seqs if options.translate: seqs_to_align = [translate.translate(s) for s in seqs] alseqs = alignSequences(seqs_to_align, exepath=options.muscle_path) #print alseqs if options.translate:
dest="normalize_ratio_by_orf", default=None, help="ORF to use for normalization across runs") parser.add_argument( "--ratio-sig", dest="ratio_significance_field", default="ratio_hl_normalized", help="field to use for ratio significance calculations") parser.add_argument("--abundance", dest="abundance_field", default="intensity", help="field to use for abundance calculations") options = parser.parse_args() # Set up some output info_outs = util.OutStreams(sys.stdout) orf_dict = None if not options.database_fname is None: orf_dict = biofile.readFASTADict(options.database_fname) evidences = [] if not options.in_fname is None: #print "# Loading..." # Read more experiments from master file inf = file(os.path.expanduser(options.in_fname), 'r') dlr = util.DelimitedLineReader(inf, header=True) while not dlr.atEnd(): flds = dlr.nextDict() if os.path.isfile(os.path.expanduser(flds['filename'])): ed = mq.EvidenceDescriptor()
action='store_true', default=False, help="execute debugging code?") parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") parser.add_argument("--isolate-out", dest="isolate_out_fname", default=None, help="output filename") options = parser.parse_args() info_outs = util.OutStreams(sys.stdout) data_outs = util.OutStreams() isolate_outs = util.OutStreams() params_outs = util.OutStreams([data_outs]) motif_outs = None # Start up output if not options.out_fname is None: outf = file(options.out_fname, 'w') data_outs.addStream(outf) else: # By default, write to stdout if options.isolate_out_fname is None: data_outs.addStream(sys.stdout) if not options.isolate_out_fname is None: isolate_outf = file(options.isolate_out_fname, 'w')
# Optional arguments parser.add_argument( "--resolution-ml", dest="resolution_ml", default=0.005, help= "output resolution, in mL: average output over elution-volume ranges no larger than this number" ) parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename") options = parser.parse_args() info_outs = util.OutStreams(sys.stdout) data_outs = util.OutStreams() # Start up output if not options.out_fname is None: outf = open(options.out_fname, 'w') data_outs.addStream(outf) else: # By default, write to stdout data_outs.addStream(sys.stdout) # Create the instance using default options if os.path.isdir(options.in_fname): basedir = options.in_fname for in_fname in os.listdir(options.in_fname): full_fname = os.path.join(basedir, in_fname)