def run_all(gbfile, groupfile, transfile, tagFiles): # does this filter out replicates that appear in every tag? annodb, al, dna = analyze.read_genbank_annots(gbfile) snps = analyze.read_tag_files(tagFiles) gsd = analyze.map_snps(snps, al, dna) # Count nonsyn vs. syn. sites for each gene site_counts = genes_sites_dict(annodb) # Count nonsyn vs. syn. snps for each gene snp_counts = analyze.get_gene_na_ns(gsd) genes = annodb.keys() functional_groups = load_func_assoc(groupfile, transfile) #binomial_tests(snp_counts, site_counts) #main(site_counts, snp_counts, genes, functional_groups, test_func=binomial_test) for name, test_func in [("Fisher test", fisher_test), ("Binomial Test", binomial_test)]: print name run_tests(site_counts, snp_counts, genes, functional_groups, test_func=test_func) print
def pathways_cmd(gbfile, groupfile, transfile, tagFiles): pathway_dict = load_func_assoc(groupfile, transfile) for k, v in pathway_dict.items(): pathway_dict[k] = v[1] # only keep the gene list annodb, al, dna = analyze.read_genbank_annots(gbfile) snps = analyze.read_tag_files(tagFiles) results = analyze.analyze_nonsyn_groups(pathway_dict, snps, annodb, al, dna) for k, v in results: print "%s,%s,%s" % (k, v, " ".join(pathway_dict[v]))
def pathways_cmd(gbfile, groupfile, transfile, tagFiles): pathway_dict = load_func_assoc(groupfile, transfile) for k,v in pathway_dict.items(): pathway_dict[k] = v[1] # only keep the gene list annodb, al, dna = analyze.read_genbank_annots(gbfile) snps = analyze.read_tag_files(tagFiles) results = analyze.analyze_nonsyn_groups(pathway_dict, snps, annodb, al, dna) for k, v in results: print "%s,%s,%s" % (k, v, " ".join(pathway_dict[v]))
def phenoseq_top_genes(gbfile, tagFiles): annodb, al, dna = analyze.read_genbank_annots(gbfile) snps = analyze.read_tag_files(tagFiles) results = analyze.analyze_nonsyn(snps, annodb, al, dna) return results