taxonomy_key = "real_taxonomy" biom = Biom( generated_by="grinder", matrix_type="sparse" ) # Set observations count for sample_name in args.samples: biom.add_sample( sample_name ) fh_abund = open( args.samples[sample_name] ) for line in fh_abund: # Content format: "# rank<TAB>seq_id<TAB>rel_abund_perc" if not line.startswith('#'): fields = line.strip().split() try: biom.add_observation( fields[1] ) except: # already exist pass biom.change_count( fields[1], sample_name, int(float(fields[2])*100000000000000) )################## depend de la precision grinder fh_abund.close() # Set taxonomy metadata fh_classif = FastaIO( args.affiliation ) for record in fh_classif: try: metadata = biom.get_observation_metadata( record.id ) if metadata is None or not metadata.has_key( taxonomy_key ): taxonomy = getCleanedTaxonomy(record.description) biom.add_metadata( record.id, taxonomy_key, taxonomy, "observation" ) except ValueError: # is not in BIOM pass fh_classif.close() # Write BIOM
taxonomy_key = "real_taxonomy" biom = Biom(generated_by="grinder", matrix_type="sparse") # Set observations count for sample_name in args.samples: biom.add_sample(sample_name) fh_abund = open(args.samples[sample_name]) for line in fh_abund: # Content format: "# rank<TAB>seq_id<TAB>rel_abund_perc" if not line.startswith('#'): fields = line.strip().split() try: biom.add_observation(fields[1]) except: # already exist pass biom.change_count( fields[1], sample_name, int(float(fields[2]) * 100000000000000 )) ################## depend de la precision grinder fh_abund.close() # Set taxonomy metadata fh_classif = FastaIO(args.affiliation) for record in fh_classif: try: metadata = biom.get_observation_metadata(record.id) if metadata is None or not metadata.has_key(taxonomy_key): taxonomy = getCleanedTaxonomy(record.description) biom.add_metadata(record.id, taxonomy_key, taxonomy, "observation") except ValueError: # is not in BIOM pass fh_classif.close()