def test_SystemSerializer_str(self): model_name = 'foo' model_location = ModelLocation( path=os.path.join(self.cfg.models_dir(), model_name)) model_A = Model("foo/A", 10) model_B = Model("foo/B", 10) c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG", self.profile_factory) gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B) c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG", self.profile_factory) gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B) c_gene_flgB = CoreGene(model_location, "flgB", self.profile_factory) c_gene_tadZ = CoreGene(model_location, "tadZ", self.profile_factory) gene_tadZ = ModelGene(c_gene_tadZ, model_B) c_gene_sctn = CoreGene(model_location, "sctN", self.profile_factory) gene_sctn = ModelGene(c_gene_sctn, model_A) gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn) gene_sctn.add_exchangeable(gene_sctn_hom) c_gene_sctj = CoreGene(model_location, "sctJ", self.profile_factory) gene_sctj = ModelGene(c_gene_sctj, model_A) gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj) gene_sctj.add_exchangeable(gene_sctj_an) c_gene_gspd = CoreGene(model_location, "gspD", self.profile_factory) gene_gspd = ModelGene(c_gene_gspd, model_A) gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd) gene_gspd.add_exchangeable(gene_gspd_an) c_gene_abc = CoreGene(model_location, "abc", self.profile_factory) gene_abc = ModelGene(c_gene_abc, model_A) gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc) gene_abc.add_exchangeable(gene_abc_ho) model_A.add_mandatory_gene(gene_sctn) model_A.add_mandatory_gene(gene_sctj) model_A.add_accessory_gene(gene_gspd) model_A.add_forbidden_gene(gene_abc) model_B.add_mandatory_gene(gene_sctn_flg) model_B.add_mandatory_gene(gene_sctj_flg) model_B.add_accessory_gene(gene_gspd) model_B.add_accessory_gene(gene_tadZ) h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) model_A._min_mandatory_genes_required = 2 model_A._min_genes_required = 2 c1 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_A, self.hit_weights) c2 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY) ], model_A, self.hit_weights) model_B._min_mandatory_genes_required = 1 model_B._min_genes_required = 2 c3 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_B, self.hit_weights) sys_A = System(model_A, [c1, c2], self.cfg.redundancy_penalty()) sys_A.id = "sys_id_A" sys_B = System(model_B, [c3], self.cfg.redundancy_penalty()) sys_B.id = "sys_id_B" hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B]) system_serializer = TxtSystemSerializer() sys_str = f"""system id = {sys_A.id} model = foo/A replicon = replicon_id clusters = [('hit_sctj', 'sctJ', 1), ('hit_sctn', 'sctN', 1), ('hit_gspd', 'gspD', 1)], [('hit_sctj', 'sctJ', 1), ('hit_sctn', 'sctN', 1)] occ = 2 wholeness = 1.000 loci nb = 2 score = 1.500 mandatory genes: \t- sctN: 2 (sctN, sctN) \t- sctJ: 2 (sctJ, sctJ) accessory genes: \t- gspD: 1 (gspD [sys_id_B]) neutral genes: """ self.assertEqual( sys_str, system_serializer.serialize(sys_A, hit_multi_sys_tracker))
def test_SolutionSerializer_tsv(self): model_name = 'foo' model_location = ModelLocation( path=os.path.join(self.cfg.models_dir(), model_name)) model_A = Model("foo/A", 10) model_B = Model("foo/B", 10) c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG", self.profile_factory) gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B) c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG", self.profile_factory) gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B) c_gene_flgB = CoreGene(model_location, "flgB", self.profile_factory) gene_flgB = ModelGene(c_gene_flgB, model_B) c_gene_tadZ = CoreGene(model_location, "tadZ", self.profile_factory) gene_tadZ = ModelGene(c_gene_tadZ, model_B) c_gene_sctn = CoreGene(model_location, "sctN", self.profile_factory) gene_sctn = ModelGene(c_gene_sctn, model_A) gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn) gene_sctn.add_exchangeable(gene_sctn_hom) c_gene_sctj = CoreGene(model_location, "sctJ", self.profile_factory) gene_sctj = ModelGene(c_gene_sctj, model_A) gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj) gene_sctj.add_exchangeable(gene_sctj_an) c_gene_gspd = CoreGene(model_location, "gspD", self.profile_factory) gene_gspd = ModelGene(c_gene_gspd, model_A) gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd) gene_gspd.add_exchangeable(gene_gspd_an) c_gene_abc = CoreGene(model_location, "abc", self.profile_factory) gene_abc = ModelGene(c_gene_abc, model_A) gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc) gene_abc.add_exchangeable(gene_abc_ho) model_A.add_mandatory_gene(gene_sctn) model_A.add_mandatory_gene(gene_sctj) model_A.add_accessory_gene(gene_gspd) model_A.add_forbidden_gene(gene_abc) model_B.add_mandatory_gene(gene_sctn_flg) model_B.add_mandatory_gene(gene_sctj_flg) model_B.add_accessory_gene(gene_flgB) model_B.add_accessory_gene(gene_tadZ) h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_flgB = Hit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) model_A._min_mandatory_genes_required = 2 model_A._min_genes_required = 2 c1 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_A, self.hit_weights) c2 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY) ], model_A, self.hit_weights) model_B._min_mandatory_genes_required = 1 model_B._min_genes_required = 2 c3 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY) ], model_B, self.hit_weights) sys_A = System(model_A, [c1, c2], self.cfg.redundancy_penalty()) sys_A.id = "sys_id_A" sys_B = System(model_B, [c3], self.cfg.redundancy_penalty()) sys_B.id = "sys_id_B" sol = [sys_A, sys_B] sol_id = '12' hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B]) system_serializer = TsvSolutionSerializer() sol_tsv = '\t'.join([ sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'gspD', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'sctJ_FLG', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_tadZ', 'tadZ', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'tadZ', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_flgB', 'flgB', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'flgB', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += "\n" ser = system_serializer.serialize(sol, sol_id, hit_multi_sys_tracker) self.assertEqual(ser, sol_tsv)
def test_solutions_to_tsv(self): args = argparse.Namespace() args.sequence_db = self.find_data("base", "test_1.fasta") args.db_type = 'gembase' args.models_dir = self.find_data('models') cfg = Config(MacsyDefaults(), args) model_name = 'foo' models_location = ModelLocation( path=os.path.join(args.models_dir, model_name)) # we need to reset the ProfileFactory # because it's a like a singleton # so other tests are influenced by ProfileFactory and it's configuration # for instance search_genes get profile without hmmer_exe profile_factory = ProfileFactory(cfg) model_A = Model("foo/A", 10) model_B = Model("foo/B", 10) model_C = Model("foo/C", 10) c_gene_sctn_flg = CoreGene(models_location, "sctN_FLG", profile_factory) gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B) c_gene_sctj_flg = CoreGene(models_location, "sctJ_FLG", profile_factory) gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B) c_gene_flgB = CoreGene(models_location, "flgB", profile_factory) gene_flgB = ModelGene(c_gene_flgB, model_B) c_gene_tadZ = CoreGene(models_location, "tadZ", profile_factory) gene_tadZ = ModelGene(c_gene_tadZ, model_B) c_gene_sctn = CoreGene(models_location, "sctN", profile_factory) gene_sctn = ModelGene(c_gene_sctn, model_A) gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn) gene_sctn.add_exchangeable(gene_sctn_hom) c_gene_sctj = CoreGene(models_location, "sctJ", profile_factory) gene_sctj = ModelGene(c_gene_sctj, model_A) gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj) gene_sctj.add_exchangeable(gene_sctj_an) c_gene_gspd = CoreGene(models_location, "gspD", profile_factory) gene_gspd = ModelGene(c_gene_gspd, model_A) gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd) gene_gspd.add_exchangeable(gene_gspd_an) c_gene_abc = CoreGene(models_location, "abc", profile_factory) gene_abc = ModelGene(c_gene_abc, model_A) gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc) gene_abc.add_exchangeable(gene_abc_ho) model_A.add_mandatory_gene(gene_sctn) model_A.add_mandatory_gene(gene_sctj) model_A.add_accessory_gene(gene_gspd) model_A.add_forbidden_gene(gene_abc) model_B.add_mandatory_gene(gene_sctn_flg) model_B.add_mandatory_gene(gene_sctj_flg) model_B.add_accessory_gene(gene_flgB) model_B.add_accessory_gene(gene_tadZ) model_C.add_mandatory_gene(gene_sctn_flg) model_C.add_mandatory_gene(gene_sctj_flg) model_C.add_mandatory_gene(gene_flgB) model_C.add_accessory_gene(gene_tadZ) model_C.add_accessory_gene(gene_gspd) h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_flgB = Hit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) model_A._min_mandatory_genes_required = 2 model_A._min_genes_required = 2 hit_weights = HitWeight(**cfg.hit_weights()) c1 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_A, hit_weights) c2 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY) ], model_A, hit_weights) model_B._min_mandatory_genes_required = 1 model_B._min_genes_required = 2 c3 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY) ], model_B, hit_weights) model_C._min_mandatory_genes_required = 1 model_C._min_genes_required = 2 c4 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_flgB, gene_flgB, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_C, hit_weights) sys_A = System(model_A, [c1, c2], cfg.redundancy_penalty()) sys_A.id = "sys_id_A" sys_B = System(model_B, [c3], cfg.redundancy_penalty()) sys_B.id = "sys_id_B" sys_C = System(model_C, [c4], cfg.redundancy_penalty()) sys_C.id = "sys_id_C" sol_1 = [sys_A, sys_B] sol_2 = [sys_A, sys_C] sol_id_1 = '1' sol_id_2 = '2' sol_tsv = f"""# macsyfinder {macsypy.__version__} # {' '.join(sys.argv)} # Systems found: """ sol_tsv += "\t".join([ "sol_id", "replicon", "hit_id", "gene_name", "hit_pos", "model_fqn", "sys_id", "sys_loci", "sys_wholeness", "sys_score", "sys_occ", "hit_gene_ref", "hit_status", "hit_seq_len", "hit_i_eval", "hit_score", "hit_profile_cov", "hit_seq_cov", "hit_begin_match", "hit_end_match", "used_in" ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'gspD', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'sctJ_FLG', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_tadZ', 'tadZ', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'tadZ', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_1, 'replicon_id', 'hit_flgB', 'flgB', '1', 'foo/B', 'sys_id_B', '1', '0.750', '2.000', '1', 'flgB', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'gspD', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A', 'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '' ]) sol_tsv += "\n" sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '1', 'foo/C', 'sys_id_C', '1', '0.800', '3.000', '1', 'sctJ_FLG', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_tadZ', 'tadZ', '1', 'foo/C', 'sys_id_C', '1', '0.800', '3.000', '1', 'tadZ', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_flgB', 'flgB', '1', 'foo/C', 'sys_id_C', '1', '0.800', '3.000', '1', 'flgB', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id_2, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/C', 'sys_id_C', '1', '0.800', '3.000', '1', 'gspD', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_A' ]) sol_tsv += "\n" sol_tsv += "\n" f_out = StringIO() hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B]) solutions_to_tsv([sol_1, sol_2], hit_multi_sys_tracker, f_out) self.assertMultiLineEqual(sol_tsv, f_out.getvalue())
def test_SolutionSerializer_tsv(self): model_name = 'foo' model_location = ModelLocation( path=os.path.join(self.cfg.models_dir()[0], model_name)) ########### # Model B # ########### model_B = Model("foo/B", 10) c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG", self.profile_factory) gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B) c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG", self.profile_factory) gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B) c_gene_flgB = CoreGene(model_location, "flgB", self.profile_factory) gene_flgB = ModelGene(c_gene_flgB, model_B) c_gene_tadZ = CoreGene(model_location, "tadZ", self.profile_factory) gene_tadZ = ModelGene(c_gene_tadZ, model_B) model_B.add_mandatory_gene(gene_sctn_flg) model_B.add_mandatory_gene(gene_sctj_flg) model_B.add_accessory_gene(gene_flgB) model_B.add_accessory_gene(gene_tadZ) ########### # Model A # ########### model_A = Model("foo/A", 10) c_gene_sctn = CoreGene(model_location, "sctN", self.profile_factory) gene_sctn = ModelGene(c_gene_sctn, model_A) gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn) gene_sctn.add_exchangeable(gene_sctn_hom) c_gene_sctj = CoreGene(model_location, "sctJ", self.profile_factory) gene_sctj = ModelGene(c_gene_sctj, model_A) gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj) gene_sctj.add_exchangeable(gene_sctj_an) c_gene_gspd = CoreGene(model_location, "gspD", self.profile_factory) gene_gspd = ModelGene(c_gene_gspd, model_A) gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd) gene_gspd.add_exchangeable(gene_gspd_an) c_gene_abc = CoreGene(model_location, "abc", self.profile_factory) gene_abc = ModelGene(c_gene_abc, model_A, loner=True) gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc) gene_abc.add_exchangeable(gene_abc_ho) model_A.add_mandatory_gene(gene_sctn) model_A.add_mandatory_gene(gene_sctj) model_A.add_accessory_gene(gene_gspd) model_A.add_accessory_gene(gene_abc) # CoreHit(gene, hit_id, hit_seq_length, replicon_name, position, i_eval, score, # profile_coverage, sequence_coverage, begin_match, end_match # pos score h_sctj = CoreHit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) mh_sctj = ModelHit(h_sctj, gene_sctj, GeneStatus.MANDATORY) h_sctn = CoreHit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 2, 1.0, 1.0, 1.0, 1.0, 10, 20) mh_sctn = ModelHit(h_sctn, gene_sctn, GeneStatus.MANDATORY) h_gspd = CoreHit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 3, 1.0, 1.0, 1.0, 1.0, 10, 20) mh_gspd = ModelHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) h_sctj_flg = CoreHit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 10, 1.0, 1.0, 1.0, 1.0, 10, 20) h_flgB = CoreHit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 11, 1.0, 1.0, 1.0, 1.0, 10, 20) h_abc = CoreHit(c_gene_abc, "hit_abc", 803, "replicon_id", 20, 1.0, 1.0, 1.0, 1.0, 10, 20) h_abc2 = CoreHit(c_gene_abc, "hit_abc2", 803, "replicon_id", 50, 1.0, 1.0, 1.0, 1.0, 10, 20) h_tadZ = CoreHit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 40, 1.0, 1.0, 1.0, 1.0, 10, 20) mh_sctj_flg = ModelHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY) mh_flgB = ModelHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY) mh_abc = ModelHit(h_abc, gene_abc, GeneStatus.ACCESSORY) mh_abc2 = ModelHit(h_abc2, gene_abc, GeneStatus.ACCESSORY) mh_tadZ = ModelHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY) model_A._min_mandatory_genes_required = 2 model_A._min_genes_required = 2 c1 = Cluster([mh_sctj, mh_sctn, mh_gspd], model_A, self.hit_weights) c2 = Cluster([mh_sctj, mh_sctn], model_A, self.hit_weights) c3 = Cluster([ Loner(h_abc, gene_ref=gene_abc, gene_status=GeneStatus.ACCESSORY, counterpart=[mh_abc2]) ], model_A, self.hit_weights) model_B._min_mandatory_genes_required = 1 model_B._min_genes_required = 2 c5 = Cluster([mh_sctj_flg, mh_tadZ, mh_flgB], model_B, self.hit_weights) sys_A = System(model_A, [c1, c2, c3], self.cfg.redundancy_penalty()) # score = 2.5, 2 , 0.35 = 4.85 - (2 * 1.5) = 1.85 sys_A.id = "sys_id_A" sys_B = System(model_B, [c5], self.cfg.redundancy_penalty()) # score = 2.0 sys_B.id = "sys_id_B" sol = Solution([sys_A, sys_B]) sol_id = '12' hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B]) sol_serializer = TsvSolutionSerializer() sol_tsv = '\t'.join([ sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '1', '1.000', '1.850', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctn', 'sctN', '2', 'foo/A', 'sys_id_A', '2', '1', '1.000', '1.850', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_gspd', 'gspD', '3', 'foo/A', 'sys_id_A', '2', '1', '1.000', '1.850', '2', 'gspD', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A', 'sys_id_A', '2', '2', '1.000', '1.850', '2', 'sctJ', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctn', 'sctN', '2', 'foo/A', 'sys_id_A', '2', '2', '1.000', '1.850', '2', 'sctN', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_abc', 'abc', '20', 'foo/A', 'sys_id_A', '2', '-1', '1.000', '1.850', '2', 'abc', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'hit_abc2', '' ]) sol_tsv += "\n" sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '10', 'foo/B', 'sys_id_B', '1', '1', '0.750', '2.000', '1', 'sctJ_FLG', 'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_flgB', 'flgB', '11', 'foo/B', 'sys_id_B', '1', '1', '0.750', '2.000', '1', 'flgB', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += '\t'.join([ sol_id, 'replicon_id', 'hit_tadZ', 'tadZ', '40', 'foo/B', 'sys_id_B', '1', '1', '0.750', '2.000', '1', 'tadZ', 'accessory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', '' ]) sol_tsv += "\n" sol_tsv += "\n" ser = sol_serializer.serialize(sol, sol_id, hit_multi_sys_tracker) self.maxDiff = None self.assertEqual(ser, sol_tsv)
def _build_systems(models, clusters, cfg): systems = {} # we need to tweek the replicon_id to have stable ressults # whatever the number of tests ran # or the tests order systems['A'] = System(models['A'], [clusters['c1'], clusters['c2']], cfg.redundancy_penalty()) # 5 hits systems['A'].id = "replicon_id_A" systems['B'] = System(models['B'], [clusters['c3']], cfg.redundancy_penalty()) # 3 hits systems['B'].id = "replicon_id_B" systems['C'] = System(models['C'], [clusters['c4']], cfg.redundancy_penalty()) # 4 hits systems['C'].id = "replicon_id_C" systems['D'] = System(models['D'], [clusters['c5']], cfg.redundancy_penalty()) # 2 hits systems['D'].id = "replicon_id_D" systems['E'] = System(models['E'], [clusters['c6']], cfg.redundancy_penalty()) # 1 hit systems['E'].id = "replicon_id_E" systems['F'] = System(models['F'], [clusters['c7']], cfg.redundancy_penalty()) # 1 hit systems['F'].id = "replicon_id_F" systems['G'] = System(models['G'], [clusters['c4']], cfg.redundancy_penalty()) # 4 hits systems['G'].id = "replicon_id_G" systems['H'] = System(models['H'], [clusters['c5']], cfg.redundancy_penalty()) # 2 hits systems['H'].id = "replicon_id_H" systems['I'] = System(models['I'], [clusters['c8']], cfg.redundancy_penalty()) # 2 hits systems['I'].id = "replicon_id_I" systems['J'] = System(models['J'], [clusters['c9']], cfg.redundancy_penalty()) # 2 hits systems['J'].id = "replicon_id_J" systems['K'] = System(models['K'], [clusters['c10']], cfg.redundancy_penalty()) # 2 hits systems['K'].id = "replicon_id_K" return systems
def _build_systems(cfg, profile_factory): model_name = 'foo' model_location = ModelLocation( path=os.path.join(cfg.models_dir(), model_name)) model_A = Model("foo/A", 10) model_B = Model("foo/B", 10) model_C = Model("foo/C", 10) model_D = Model("foo/D", 10) model_E = Model("foo/E", 10) model_F = Model("foo/F", 10) model_G = Model("foo/G", 10) model_H = Model("foo/H", 10) c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG", profile_factory) gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B) c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG", profile_factory) gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B) c_gene_flgB = CoreGene(model_location, "flgB", profile_factory) gene_flgB = ModelGene(c_gene_flgB, model_B) c_gene_tadZ = CoreGene(model_location, "tadZ", profile_factory) gene_tadZ = ModelGene(c_gene_tadZ, model_B) c_gene_sctn = CoreGene(model_location, "sctN", profile_factory) gene_sctn = ModelGene(c_gene_sctn, model_A) gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn) gene_sctn.add_exchangeable(gene_sctn_hom) c_gene_sctj = CoreGene(model_location, "sctJ", profile_factory) gene_sctj = ModelGene(c_gene_sctj, model_A) gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj) gene_sctj.add_exchangeable(gene_sctj_an) c_gene_gspd = CoreGene(model_location, "gspD", profile_factory) gene_gspd = ModelGene(c_gene_gspd, model_A) gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd) gene_gspd.add_exchangeable(gene_gspd_an) c_gene_abc = CoreGene(model_location, "abc", profile_factory) gene_abc = ModelGene(c_gene_abc, model_A) gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc) gene_abc.add_exchangeable(gene_abc_ho) model_A.add_mandatory_gene(gene_sctn) model_A.add_mandatory_gene(gene_sctj) model_A.add_accessory_gene(gene_gspd) model_A.add_forbidden_gene(gene_abc) model_B.add_mandatory_gene(gene_sctn_flg) model_B.add_mandatory_gene(gene_sctj_flg) model_B.add_accessory_gene(gene_flgB) model_B.add_accessory_gene(gene_tadZ) model_C.add_mandatory_gene(gene_sctn_flg) model_C.add_mandatory_gene(gene_sctj_flg) model_C.add_mandatory_gene(gene_flgB) model_C.add_accessory_gene(gene_tadZ) model_C.add_accessory_gene(gene_gspd) model_D.add_mandatory_gene(gene_abc) model_D.add_accessory_gene(gene_sctn) model_E.add_accessory_gene(gene_gspd) model_F.add_mandatory_gene(gene_abc) # idem as C model_G.add_mandatory_gene(gene_sctn_flg) model_G.add_mandatory_gene(gene_sctj_flg) model_G.add_mandatory_gene(gene_flgB) model_G.add_accessory_gene(gene_tadZ) model_G.add_accessory_gene(gene_gspd) # idem as D model_H.add_mandatory_gene(gene_abc) model_H.add_accessory_gene(gene_sctn) h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 2, 1.0, 1.0, 1.0, 1.0, 10, 20) h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 3, 1.0, 1.0, 1.0, 1.0, 10, 20) h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 4, 1.0, 1.0, 1.0, 1.0, 10, 20) h_flgB = Hit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 5, 1.0, 1.0, 1.0, 1.0, 10, 20) h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 6, 1.0, 1.0, 1.0, 1.0, 10, 20) h_abc = Hit(c_gene_abc, "hit_abc", 803, "replicon_id", 7, 1.0, 1.0, 1.0, 1.0, 10, 20) model_A._min_mandatory_genes_required = 2 model_A._min_genes_required = 2 hit_weights = HitWeight(**cfg.hit_weights()) c1 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_A, hit_weights) c2 = Cluster([ ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY) ], model_A, hit_weights) model_B._min_mandatory_genes_required = 1 model_B._min_genes_required = 2 c3 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY) ], model_B, hit_weights) model_C._min_mandatory_genes_required = 1 model_C._min_genes_required = 2 c4 = Cluster([ ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY), ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY), ValidHit(h_flgB, gene_flgB, GeneStatus.MANDATORY), ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY) ], model_C, hit_weights) model_D._min_mandatory_genes_required = 1 model_D._min_genes_required = 1 c5 = Cluster([ ValidHit(h_abc, gene_abc, GeneStatus.MANDATORY), ValidHit(h_sctn, gene_sctn, GeneStatus.ACCESSORY) ], model_D, hit_weights) model_E._min_mandatory_genes_required = 0 model_E._min_genes_required = 1 c6 = Cluster([ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)], model_E, hit_weights) model_F._min_mandatory_genes_required = 1 model_F._min_genes_required = 1 c7 = Cluster([ValidHit(h_abc, gene_abc, GeneStatus.MANDATORY)], model_F, hit_weights) systems = {} systems['A'] = System(model_A, [c1, c2], cfg.redundancy_penalty()) # 5 hits # we need to tweek the replicon_id to have stable ressults # whatever the number of tests ran # or the tests order systems['A'].id = "replicon_id_A" systems['B'] = System(model_B, [c3], cfg.redundancy_penalty()) # 3 hits systems['B'].id = "replicon_id_B" systems['C'] = System(model_C, [c4], cfg.redundancy_penalty()) # 4 hits systems['C'].id = "replicon_id_C" systems['D'] = System(model_D, [c5], cfg.redundancy_penalty()) # 2 hits systems['D'].id = "replicon_id_D" systems['E'] = System(model_E, [c6], cfg.redundancy_penalty()) # 1 hit systems['E'].id = "replicon_id_E" systems['F'] = System(model_F, [c7], cfg.redundancy_penalty()) # 1 hit systems['F'].id = "replicon_id_F" systems['G'] = System(model_G, [c4], cfg.redundancy_penalty()) # 4 hits systems['G'].id = "replicon_id_G" systems['H'] = System(model_H, [c5], cfg.redundancy_penalty()) # 2 hits systems['H'].id = "replicon_id_H" return systems