# Run seqenv # cluster.otu_uparse.seqenv.threshold = 1.0 cluster.otu_uparse.seqenv.N = 5000 cluster.otu_uparse.seqenv.run() # Run seqenv via SLURM # cluster.run(steps=[{'otu_uparse.seqenv.run': {}}]) cluster.run_slurm(steps=[{'otu_uparse.seqenv.run': {}}], time="04:00:00") # Check some matrix multiplications # otu_vs_envo = cluster.otu_uparse.seqenv.base_dir + "centers_N1000_blast_F_ENVO_OTUs_labels.csv" otu_vs_envo = pandas.io.parsers.read_csv(otu_vs_envo, sep=',', index_col=0, encoding='utf-8') otu_vs_samples = cluster.otu_uparse.seqenv.base_dir + "abundances.csv" otu_vs_samples = pandas.io.parsers.read_csv(otu_vs_samples, sep=',', index_col=0, encoding='utf-8') otu_vs_samples = otu_vs_samples.loc[otu_vs_envo.index] otu_vs_samples = otu_vs_samples.transpose() result_us = otu_vs_samples.dot(otu_vs_envo) result_them = cluster.otu_uparse.seqenv.base_dir + "centers_N1000_blast_F_ENVO_samples_labels.csv" result_them = pandas.io.parsers.read_csv(result_them, sep=',', index_col=0, encoding='utf-8') result_them.sum(axis=1) cluster.otu_uparse.taxonomy_silva.otu_table ############################################################################### # Print SRA information # for s in cluster: s.sra.upload_to_sra() from illumitag.helper.sra import MakeSpreadsheet make_tsv = MakeSpreadsheet(cluster) make_tsv.write_bio_tsv() make_tsv.write_sra_tsv()
############################################################################### # Get vars # samples_pyro = [s for s in illumitag.pyrosamples if s.run_num==9999] samples = [s.mate for s in samples_pyro] cluster = illumitag.clustering.Cluster(samples, 'soda_model_lakes') # Upload raw samples for SRA # pool = illumitag.runs[3][7] pool.create_raw_samples() for s in samples: s.sra.upload_to_sra() for s in samples_pyro: s.sra.upload_to_sra() # Create BioSamples # from illumitag.helper.sra import MakeSpreadsheet make_tsv = MakeSpreadsheet(cluster) make_tsv.write_bio_tsv() # Submit to SRA # make_tsv.write_sra_tsv() # The pyro samples # cluster_pyro = illumitag.clustering.Cluster(samples_pyro, 'soda_model_lakes_pyro') make_tsv_pyro = MakeSpreadsheet(cluster_pyro) make_tsv_pyro.platform = "LS454" make_tsv_pyro.instrument_model = "454 GS FLX Titanium" make_tsv_pyro.forward_read_length = "500" make_tsv_pyro.reverse_read_length = "500" make_tsv_pyro.forward_filetype = "sff" make_tsv_pyro.reverse_filetype = "sff" make_tsv_pyro.write_sra_tsv()