{ "pipeline_name": "bgc-compare (Native Architecture-Aware Biosynthetic Gene Cluster Engine vs. GECCO v0.11.0)", "external_tool_version": "GECCO v0.11.0 (pyrodigal 3.7.1, pyhmmer 0.12.3, full Pfam CRF)", "truth_database": "MIBiG 4.0 (mibig_json_4.0)", "domain_models": [ { "accession": "PF00109", "name": "ketoacyl-synt", "ga_bits": 20.8, "seed_sequences": 75, "model_length": 253, "accessory_weight": 0.8 }, { "accession": "PF02801", "name": "Ketoacyl-synt_C", "ga_bits": 20.8, "seed_sequences": 75, "model_length": 119, "accessory_weight": 0.3 }, { "accession": "PF00698", "name": "Acyl_transf_1", "ga_bits": 32.7, "seed_sequences": 8, "model_length": 320, "accessory_weight": 0.7 }, { "accession": "PF08659", "name": "KR", "ga_bits": 22.6, "seed_sequences": 42, "model_length": 180, "accessory_weight": 0.5 }, { "accession": "PF14765", "name": "PS-DH", "ga_bits": 23.7, "seed_sequences": 59, "model_length": 168, "accessory_weight": 0.6 }, { "accession": "PF00550", "name": "PP-binding", "ga_bits": 20.8, "seed_sequences": 150, "model_length": 67, "accessory_weight": 0.4 }, { "accession": "PF16197", "name": "KAsynt_C_assoc", "ga_bits": 33.0, "seed_sequences": 72, "model_length": 112, "accessory_weight": 0.3 }, { "accession": "PF00501", "name": "AMP-binding", "ga_bits": 29.9, "seed_sequences": 136, "model_length": 385, "accessory_weight": 0.6 }, { "accession": "PF00668", "name": "Condensation", "ga_bits": 30.6, "seed_sequences": 21, "model_length": 457, "accessory_weight": 1.0 }, { "accession": "PF00975", "name": "Thioesterase", "ga_bits": 26.4, "seed_sequences": 16, "model_length": 231, "accessory_weight": 0.4 }, { "accession": "PF13193", "name": "AMP-binding_C", "ga_bits": 24.5, "seed_sequences": 222, "model_length": 76, "accessory_weight": 0.2 }, { "accession": "PF00195", "name": "Chal_sti_synt_N", "ga_bits": 27.0, "seed_sequences": 5, "model_length": 225, "accessory_weight": 0.8 }, { "accession": "PF02797", "name": "Chal_sti_synt_C", "ga_bits": 27.0, "seed_sequences": 6, "model_length": 151, "accessory_weight": 0.8 }, { "accession": "PF03936", "name": "Terpene_synth_C", "ga_bits": 26.3, "seed_sequences": 181, "model_length": 241, "accessory_weight": 1.0 }, { "accession": "PF01397", "name": "Terpene_synth", "ga_bits": 37.6, "seed_sequences": 153, "model_length": 191, "accessory_weight": 1.0 }, { "accession": "PF13243", "name": "SQHop_cyclase_C", "ga_bits": 26.1, "seed_sequences": 12, "model_length": 319, "accessory_weight": 0.6 }, { "accession": "PF13249", "name": "SQHop_cyclase_N", "ga_bits": 26.2, "seed_sequences": 101, "model_length": 291, "accessory_weight": 0.6 }, { "accession": "PF00494", "name": "SQS_PSY", "ga_bits": 26.0, "seed_sequences": 78, "model_length": 266, "accessory_weight": 0.9 }, { "accession": "PF05147", "name": "LANC_like", "ga_bits": 23.2, "seed_sequences": 45, "model_length": 352, "accessory_weight": 1.0 }, { "accession": "PF04738", "name": "Lant_dehyd", "ga_bits": 28.0, "seed_sequences": 45, "model_length": 651, "accessory_weight": 1.0 }, { "accession": "PF04055", "name": "Radical_SAM", "ga_bits": 29.5, "seed_sequences": 479, "model_length": 167, "accessory_weight": 0.3 }, { "accession": "PF13186", "name": "SPASM", "ga_bits": 21.5, "seed_sequences": 136, "model_length": 69, "accessory_weight": 0.4 }, { "accession": "PF02624", "name": "YcaO", "ga_bits": 25.7, "seed_sequences": 181, "model_length": 325, "accessory_weight": 1.0 }, { "accession": "PF04183", "name": "IucA_IucC", "ga_bits": 25.0, "seed_sequences": 160, "model_length": 240, "accessory_weight": 1.0 }, { "accession": "PF06276", "name": "FhuF", "ga_bits": 25.2, "seed_sequences": 144, "model_length": 162, "accessory_weight": 0.4 }, { "accession": "PF00067", "name": "p450", "ga_bits": 22.8, "seed_sequences": 50, "model_length": 463, "accessory_weight": 0.35 }, { "accession": "PF01494", "name": "FAD_binding_3", "ga_bits": 22.0, "seed_sequences": 19, "model_length": 357, "accessory_weight": 0.35 }, { "accession": "PF08241", "name": "Methyltransf_11", "ga_bits": 21.2, "seed_sequences": 141, "model_length": 96, "accessory_weight": 0.25 }, { "accession": "PF00535", "name": "Glycos_transf_2", "ga_bits": 23.3, "seed_sequences": 131, "model_length": 170, "accessory_weight": 0.2 }, { "accession": "PF00155", "name": "Aminotran_1_2", "ga_bits": 19.7, "seed_sequences": 48, "model_length": 365, "accessory_weight": 0.2 }, { "accession": "PF01370", "name": "Epimerase", "ga_bits": 20.9, "seed_sequences": 96, "model_length": 241, "accessory_weight": 0.2 }, { "accession": "PF13489", "name": "Methyltransf_23", "ga_bits": 27.0, "seed_sequences": 40, "model_length": 166, "accessory_weight": 0.25 }, { "accession": "PF00201", "name": "UDPGT", "ga_bits": 19.5, "seed_sequences": 13, "model_length": 499, "accessory_weight": 0.3 }, { "accession": "PF01636", "name": "APH", "ga_bits": 23.2, "seed_sequences": 137, "model_length": 239, "accessory_weight": 0.1 } ], "genomes": [ { "genome_id": "AL645882.2", "organism": "Streptomyces coelicolor A3(2)", "kingdom": "Prokaryota", "regime_note": "BGC-rich actinomycete (15 MIBiG loci)", "genome_bp": 8667507, "genes_called_native": 7738, "native": { "tool": "native (rules v2)", "n_clusters": 12, "total_bp": 323863, "mibig_recall_any_overlap": 0.4666666666666667, "mibig_recall_half_covered": 0.4, "mibig_truth_hit": 7, "predicted_overlapping_mibig_frac": 0.5, "wall_ms": 34625 }, "native_rules_v1": { "tool": "native (rules v1)", "n_clusters": 12, "total_bp": 322280, "mibig_recall_any_overlap": 0.4666666666666667, "mibig_recall_half_covered": 0.4, "mibig_truth_hit": 7, "predicted_overlapping_mibig_frac": 0.5, "wall_ms": 34625 }, "gecco_default": { "tool": "GECCO v0.11.0 (-m 0.8)", "n_clusters": 46, "total_bp": 1053641, "mibig_recall_any_overlap": 0.9333333333333333, "mibig_recall_half_covered": 0.9333333333333333, "mibig_truth_hit": 14, "predicted_overlapping_mibig_frac": 0.2826086956521739, "wall_ms": 25600 }, "gecco_sensitive": { "tool": "GECCO v0.11.0 (-m 0.3)", "n_clusters": 73, "total_bp": 1719985, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 15, "predicted_overlapping_mibig_frac": 0.1917808219178082, "wall_ms": 0 }, "mibig_truth_loci": 15, "native_vs_gecco_bp_jaccard": 0.2876998149082955, "native_vs_gecco_matched_clusters": 12, "native_vs_gecco_cluster_jaccard": 0.2608695652173913, "domain_concordance": { "native_calls": 338, "gecco_calls": 520, "shared": 326, "jaccard": 0.6127819548872181, "family_count_pearson_r": 0.7777243766964882 }, "native_gene_call_ms": 26615, "native_domain_scan_ms": 8009, "native_cluster_call_ms": 1, "truth": [ { "mibig_id": "BGC0000325", "seq_id": "AL645882.2", "start": 510823, "end": 533448, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002127", "seq_id": "AL645882.2", "start": 1277478, "end": 1280491, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000910", "seq_id": "AL645882.2", "start": 2943456, "end": 2944875, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000940", "seq_id": "AL645882.2", "start": 3033355, "end": 3040682, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000315", "seq_id": "AL645882.2", "start": 3519449, "end": 3602320, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.6517279660198861, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000194", "seq_id": "AL645882.2", "start": 5513809, "end": 5535091, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.6117088756284358, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000660", "seq_id": "AL645882.2", "start": 5681016, "end": 5683483, "classes": "terpene", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001063", "seq_id": "AL645882.2", "start": 6432566, "end": 6464206, "classes": "NRPS/PKS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001181", "seq_id": "AL645882.2", "start": 6666219, "end": 6668399, "classes": "terpene", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000849", "seq_id": "AL645882.2", "start": 6890528, "end": 6892237, "classes": "other", "quality": "questionable", "native_cover_frac": 0.05263157894736842, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000038", "seq_id": "AL645882.2", "start": 6890528, "end": 6948414, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.8215661547497711, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000551", "seq_id": "AL645882.2", "start": 7419664, "end": 7426391, "classes": "ribosomal", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000663", "seq_id": "AL645882.2", "start": 7516017, "end": 7529773, "classes": "terpene", "quality": "questionable", "native_cover_frac": 0.9861888493130769, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002128", "seq_id": "AL645882.2", "start": 8279373, "end": 8288044, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.8723477859778598, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000324", "seq_id": "AL645882.2", "start": 8504461, "end": 8529581, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.8474583018191951, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 } ], "native_clusters": [ { "cluster_id": "AL645882.2_native_1", "seq_id": "AL645882.2", "start": 98190, "end": 127502, "gene_count": 10, "core_gene_count": 2, "classes": [ "PKS-I" ], "domains": [ "PF00109", "PF00698", "PF02801", "PF08659", "PF16197" ] }, { "cluster_id": "AL645882.2_native_2", "seq_id": "AL645882.2", "start": 251499, "end": 268263, "gene_count": 10, "core_gene_count": 2, "classes": [ "RiPP" ], "domains": [ "PF04738", "PF05147" ] }, { "cluster_id": "AL645882.2_native_3", "seq_id": "AL645882.2", "start": 3536679, "end": 3590688, "gene_count": 11, "core_gene_count": 3, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] }, { "cluster_id": "AL645882.2_native_4", "seq_id": "AL645882.2", "start": 5522073, "end": 5538287, "gene_count": 12, "core_gene_count": 2, "classes": [ "PKS-II" ], "domains": [ "PF00109", "PF00550", "PF02801", "PF08241", "PF13489" ] }, { "cluster_id": "AL645882.2_native_5", "seq_id": "AL645882.2", "start": 5782597, "end": 5796470, "gene_count": 10, "core_gene_count": 2, "classes": [ "PKS-II" ], "domains": [ "PF00109", "PF00550", "PF01494", "PF02801" ] }, { "cluster_id": "AL645882.2_native_6", "seq_id": "AL645882.2", "start": 6428010, "end": 6466206, "gene_count": 25, "core_gene_count": 2, "classes": [ "NRPS-like", "PKS-I" ], "domains": [ "PF00109", "PF00155", "PF00501", "PF00550", "PF00698", "PF00975", "PF01370", "PF02801", "PF08241", "PF13193", "PF13489", "PF16197" ] }, { "cluster_id": "AL645882.2_native_7", "seq_id": "AL645882.2", "start": 6841172, "end": 6856429, "gene_count": 10, "core_gene_count": 2, "classes": [ "Siderophore" ], "domains": [ "PF00155", "PF04183", "PF06276" ] }, { "cluster_id": "AL645882.2_native_8", "seq_id": "AL645882.2", "start": 6892148, "end": 6939705, "gene_count": 11, "core_gene_count": 3, "classes": [ "PKS-I" ], "domains": [ "PF00109", "PF00550", "PF00698", "PF02801", "PF08659", "PF14765", "PF16197" ] }, { "cluster_id": "AL645882.2_native_9", "seq_id": "AL645882.2", "start": 7094185, "end": 7121774, "gene_count": 10, "core_gene_count": 2, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF13193" ] }, { "cluster_id": "AL645882.2_native_10", "seq_id": "AL645882.2", "start": 7510283, "end": 7529583, "gene_count": 14, "core_gene_count": 1, "classes": [ "Terpene" ], "domains": [ "PF00494", "PF04055", "PF13243", "PF13249" ] }, { "cluster_id": "AL645882.2_native_11", "seq_id": "AL645882.2", "start": 7685305, "end": 7702728, "gene_count": 10, "core_gene_count": 2, "classes": [ "RiPP" ], "domains": [ "PF04738", "PF05147" ] }, { "cluster_id": "AL645882.2_native_12", "seq_id": "AL645882.2", "start": 8497392, "end": 8525749, "gene_count": 11, "core_gene_count": 3, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00067", "PF00501", "PF00550", "PF00975", "PF13193" ] } ], "gecco_default_clusters": [ { "seq_id": "AL645882.2", "start": 1144, "end": 42174, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 98463, "end": 128290, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 168705, "end": 189886, "label": "Terpene" }, { "seq_id": "AL645882.2", "start": 250805, "end": 267513, "label": "RiPP" }, { "seq_id": "AL645882.2", "start": 494260, "end": 544087, "label": "NRP" }, { "seq_id": "AL645882.2", "start": 738595, "end": 745763, "label": "RiPP" }, { "seq_id": "AL645882.2", "start": 1126535, "end": 1134012, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 1151870, "end": 1170556, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 1275235, "end": 1282540, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 1333824, "end": 1368913, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 1998468, "end": 2009392, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 2609897, "end": 2639559, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 2934114, "end": 2953604, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 3027514, "end": 3043370, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 3122937, "end": 3144042, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 3513024, "end": 3604107, "label": "NRP" }, { "seq_id": "AL645882.2", "start": 3880083, "end": 3885819, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 4001665, "end": 4028773, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 4242512, "end": 4258428, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 4615154, "end": 4635156, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 4895198, "end": 4899117, "label": "NRP" }, { "seq_id": "AL645882.2", "start": 5511271, "end": 5536287, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 5681016, "end": 5684465, "label": "Terpene" }, { "seq_id": "AL645882.2", "start": 5776630, "end": 5797479, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 6339501, "end": 6343258, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 6428862, "end": 6470874, "label": "NRP;Polyketide" }, { "seq_id": "AL645882.2", "start": 6541507, "end": 6551406, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 6553552, "end": 6563778, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 6831346, "end": 6878175, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 6889594, "end": 6949758, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 6991755, "end": 7012171, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 7106284, "end": 7132084, "label": "NRP" }, { "seq_id": "AL645882.2", "start": 7170144, "end": 7174841, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 7333403, "end": 7347440, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 7413412, "end": 7440215, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 7510408, "end": 7529773, "label": "Terpene" }, { "seq_id": "AL645882.2", "start": 7586410, "end": 7606241, "label": "Polyketide" }, { "seq_id": "AL645882.2", "start": 7631006, "end": 7663855, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 7675634, "end": 7707743, "label": "RiPP" }, { "seq_id": "AL645882.2", "start": 7988871, "end": 7998651, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 8193260, "end": 8209387, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 8254317, "end": 8269446, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 8276830, "end": 8286937, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 8491153, "end": 8551953, "label": "NRP" }, { "seq_id": "AL645882.2", "start": 8585463, "end": 8590784, "label": "Unknown" }, { "seq_id": "AL645882.2", "start": 8643240, "end": 8666364, "label": "Unknown" } ] }, { "genome_id": "CP000560.1", "organism": "Bacillus velezensis FZB42", "kingdom": "Prokaryota", "regime_note": "BGC-rich Firmicute (6 MIBiG loci)", "genome_bp": 3918589, "genes_called_native": 3741, "native": { "tool": "native (rules v2)", "n_clusters": 9, "total_bp": 418645, "mibig_recall_any_overlap": 0.6666666666666666, "mibig_recall_half_covered": 0.6666666666666666, "mibig_truth_hit": 4, "predicted_overlapping_mibig_frac": 0.4444444444444444, "wall_ms": 16166 }, "native_rules_v1": { "tool": "native (rules v1)", "n_clusters": 8, "total_bp": 404518, "mibig_recall_any_overlap": 0.6666666666666666, "mibig_recall_half_covered": 0.6666666666666666, "mibig_truth_hit": 4, "predicted_overlapping_mibig_frac": 0.5, "wall_ms": 16166 }, "gecco_default": { "tool": "GECCO v0.11.0 (-m 0.8)", "n_clusters": 10, "total_bp": 427910, "mibig_recall_any_overlap": 0.8333333333333334, "mibig_recall_half_covered": 0.8333333333333334, "mibig_truth_hit": 5, "predicted_overlapping_mibig_frac": 0.4, "wall_ms": 23100 }, "gecco_sensitive": { "tool": "GECCO v0.11.0 (-m 0.3)", "n_clusters": 12, "total_bp": 485600, "mibig_recall_any_overlap": 0.8333333333333334, "mibig_recall_half_covered": 0.8333333333333334, "mibig_truth_hit": 5, "predicted_overlapping_mibig_frac": 0.3333333333333333, "wall_ms": 0 }, "mibig_truth_loci": 6, "native_vs_gecco_bp_jaccard": 0.8253374444779853, "native_vs_gecco_matched_clusters": 7, "native_vs_gecco_cluster_jaccard": 0.5833333333333334, "domain_concordance": { "native_calls": 279, "gecco_calls": 378, "shared": 277, "jaccard": 0.7289473684210527, "family_count_pearson_r": 0.8993298661949224 }, "native_gene_call_ms": 6541, "native_domain_scan_ms": 9625, "native_cluster_call_ms": 0, "truth": [ { "mibig_id": "BGC0001090", "seq_id": "CP000560.1", "start": 1867976, "end": 1912622, "classes": "NRPS/PKS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001095", "seq_id": "CP000560.1", "start": 1921412, "end": 1970953, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.9427758265713939, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002641", "seq_id": "CP000560.1", "start": 2868415, "end": 2887865, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 0.9997429438075163, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001185", "seq_id": "CP000560.1", "start": 3021250, "end": 3032970, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000616", "seq_id": "CP000560.1", "start": 3044506, "end": 3048678, "classes": "ribosomal", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001184", "seq_id": "CP000560.1", "start": 3593877, "end": 3601174, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 0.0 } ], "native_clusters": [ { "cluster_id": "CP000560.1_native_1", "seq_id": "CP000560.1", "start": 337447, "end": 372781, "gene_count": 11, "core_gene_count": 3, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] }, { "cluster_id": "CP000560.1_native_2", "seq_id": "CP000560.1", "start": 1387644, "end": 1451113, "gene_count": 15, "core_gene_count": 6, "classes": [ "PKS-I" ], "domains": [ "PF00109", "PF00550", "PF00698", "PF02801", "PF08659", "PF14765", "PF16197" ] }, { "cluster_id": "CP000560.1_native_3", "seq_id": "CP000560.1", "start": 1698330, "end": 1776721, "gene_count": 17, "core_gene_count": 5, "classes": [ "PKS-I" ], "domains": [ "PF00067", "PF00109", "PF00501", "PF00550", "PF00668", "PF00698", "PF00975", "PF02801", "PF08659", "PF14765", "PF16197" ] }, { "cluster_id": "CP000560.1_native_4", "seq_id": "CP000560.1", "start": 1863725, "end": 1917144, "gene_count": 14, "core_gene_count": 3, "classes": [ "NRPS", "PKS-I" ], "domains": [ "PF00067", "PF00109", "PF00501", "PF00550", "PF00668", "PF00698", "PF00975", "PF02801", "PF04055", "PF08659", "PF13193", "PF16197" ] }, { "cluster_id": "CP000560.1_native_5", "seq_id": "CP000560.1", "start": 1924247, "end": 1976214, "gene_count": 13, "core_gene_count": 5, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] }, { "cluster_id": "CP000560.1_native_6", "seq_id": "CP000560.1", "start": 2273867, "end": 2349530, "gene_count": 17, "core_gene_count": 8, "classes": [ "NRPS-like", "PKS-I" ], "domains": [ "PF00067", "PF00109", "PF00501", "PF00550", "PF00698", "PF00975", "PF02801", "PF08659", "PF14765", "PF16197" ] }, { "cluster_id": "CP000560.1_native_7", "seq_id": "CP000560.1", "start": 2864396, "end": 2890915, "gene_count": 12, "core_gene_count": 3, "classes": [ "NRPS", "NRPS-like", "PKS-I" ], "domains": [ "PF00109", "PF00501", "PF00550", "PF00668", "PF02801", "PF04055", "PF13193", "PF16197" ] }, { "cluster_id": "CP000560.1_native_8", "seq_id": "CP000560.1", "start": 3015712, "end": 3036762, "gene_count": 11, "core_gene_count": 2, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF08659", "PF13193" ] }, { "cluster_id": "CP000560.1_native_9", "seq_id": "CP000560.1", "start": 3666307, "end": 3679131, "gene_count": 9, "core_gene_count": 1, "classes": [ "NRPS-like" ], "domains": [ "PF00501", "PF00550" ] } ], "gecco_default_clusters": [ { "seq_id": "CP000560.1", "start": 335466, "end": 375409, "label": "NRP" }, { "seq_id": "CP000560.1", "start": 719938, "end": 734849, "label": "RiPP" }, { "seq_id": "CP000560.1", "start": 1072854, "end": 1076924, "label": "Unknown" }, { "seq_id": "CP000560.1", "start": 1391841, "end": 1449113, "label": "Polyketide" }, { "seq_id": "CP000560.1", "start": 1700345, "end": 1776242, "label": "NRP;Polyketide" }, { "seq_id": "CP000560.1", "start": 1865725, "end": 1975020, "label": "NRP" }, { "seq_id": "CP000560.1", "start": 2275867, "end": 2351256, "label": "NRP;Polyketide" }, { "seq_id": "CP000560.1", "start": 2860627, "end": 2887860, "label": "NRP;Polyketide" }, { "seq_id": "CP000560.1", "start": 3019045, "end": 3033990, "label": "NRP" }, { "seq_id": "CP000560.1", "start": 3040537, "end": 3049482, "label": "Unknown" } ] }, { "genome_id": "AE004091.2", "organism": "Pseudomonas aeruginosa PAO1", "kingdom": "Prokaryota", "regime_note": "Proteobacterial pathogen (7 MIBiG loci)", "genome_bp": 6264404, "genes_called_native": 5681, "native": { "tool": "native (rules v2)", "n_clusters": 3, "total_bp": 94108, "mibig_recall_any_overlap": 0.16666666666666666, "mibig_recall_half_covered": 0.16666666666666666, "mibig_truth_hit": 1, "predicted_overlapping_mibig_frac": 0.3333333333333333, "wall_ms": 53352 }, "native_rules_v1": { "tool": "native (rules v1)", "n_clusters": 3, "total_bp": 94108, "mibig_recall_any_overlap": 0.16666666666666666, "mibig_recall_half_covered": 0.16666666666666666, "mibig_truth_hit": 1, "predicted_overlapping_mibig_frac": 0.3333333333333333, "wall_ms": 53352 }, "gecco_default": { "tool": "GECCO v0.11.0 (-m 0.8)", "n_clusters": 9, "total_bp": 235248, "mibig_recall_any_overlap": 0.3333333333333333, "mibig_recall_half_covered": 0.3333333333333333, "mibig_truth_hit": 2, "predicted_overlapping_mibig_frac": 0.2222222222222222, "wall_ms": 26700 }, "gecco_sensitive": { "tool": "GECCO v0.11.0 (-m 0.3)", "n_clusters": 18, "total_bp": 366596, "mibig_recall_any_overlap": 0.6666666666666666, "mibig_recall_half_covered": 0.5, "mibig_truth_hit": 4, "predicted_overlapping_mibig_frac": 0.2222222222222222, "wall_ms": 0 }, "mibig_truth_loci": 6, "native_vs_gecco_bp_jaccard": 0.36952625691819585, "native_vs_gecco_matched_clusters": 3, "native_vs_gecco_cluster_jaccard": 0.3333333333333333, "domain_concordance": { "native_calls": 196, "gecco_calls": 295, "shared": 187, "jaccard": 0.6151315789473685, "family_count_pearson_r": 0.7721389621919428 }, "native_gene_call_ms": 28166, "native_domain_scan_ms": 25186, "native_cluster_call_ms": 0, "truth": [ { "mibig_id": "BGC0000922", "seq_id": "AE004091.2", "start": 1073960, "end": 1087095, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000287", "seq_id": "AE004091.2", "start": 2532659, "end": 2545669, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002037", "seq_id": "AE004091.2", "start": 3729471, "end": 3746067, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002645", "seq_id": "AE004091.2", "start": 3930743, "end": 3936837, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 0.0 }, { "mibig_id": "BGC0000725", "seq_id": "AE004091.2", "start": 3962825, "end": 3979476, "classes": "saccharide", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 0.1377011770357915 }, { "mibig_id": "BGC0002489", "seq_id": "AE004091.2", "start": 5424761, "end": 5429842, "classes": "other", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.0, "gecco_sensitive_cover_frac": 0.0 } ], "native_clusters": [ { "cluster_id": "AE004091.2_native_1", "seq_id": "AE004091.2", "start": 2525743, "end": 2550530, "gene_count": 12, "core_gene_count": 2, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] }, { "cluster_id": "AE004091.2_native_2", "seq_id": "AE004091.2", "start": 2649307, "end": 2692127, "gene_count": 11, "core_gene_count": 3, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] }, { "cluster_id": "AE004091.2_native_3", "seq_id": "AE004091.2", "start": 4722639, "end": 4749137, "gene_count": 12, "core_gene_count": 3, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00501", "PF00550", "PF00975", "PF13193" ] } ], "gecco_default_clusters": [ { "seq_id": "AE004091.2", "start": 1059622, "end": 1069331, "label": "Unknown" }, { "seq_id": "AE004091.2", "start": 2060566, "end": 2084267, "label": "Unknown" }, { "seq_id": "AE004091.2", "start": 2482045, "end": 2485478, "label": "Unknown" }, { "seq_id": "AE004091.2", "start": 2530389, "end": 2552675, "label": "NRP" }, { "seq_id": "AE004091.2", "start": 2643306, "end": 2722738, "label": "NRP" }, { "seq_id": "AE004091.2", "start": 3723534, "end": 3749711, "label": "NRP" }, { "seq_id": "AE004091.2", "start": 3889139, "end": 3892055, "label": "Unknown" }, { "seq_id": "AE004091.2", "start": 4622812, "end": 4647811, "label": "Unknown" }, { "seq_id": "AE004091.2", "start": 4705956, "end": 4748542, "label": "NRP" } ] }, { "genome_id": "U00096.3", "organism": "Escherichia coli K-12 MG1655", "kingdom": "Prokaryota", "regime_note": "BGC-poor near-negative control (enterobactin only)", "genome_bp": 4641652, "genes_called_native": 4319, "native": { "tool": "native (rules v2)", "n_clusters": 1, "total_bp": 26541, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 1, "predicted_overlapping_mibig_frac": 1.0, "wall_ms": 36306 }, "native_rules_v1": { "tool": "native (rules v1)", "n_clusters": 0, "total_bp": 0, "mibig_recall_any_overlap": 0.0, "mibig_recall_half_covered": 0.0, "mibig_truth_hit": 0, "predicted_overlapping_mibig_frac": 0.0, "wall_ms": 36306 }, "gecco_default": { "tool": "GECCO v0.11.0 (-m 0.8)", "n_clusters": 2, "total_bp": 41513, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 1, "predicted_overlapping_mibig_frac": 0.5, "wall_ms": 29000 }, "gecco_sensitive": { "tool": "GECCO v0.11.0 (-m 0.3)", "n_clusters": 7, "total_bp": 120109, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 1, "predicted_overlapping_mibig_frac": 0.14285714285714285, "wall_ms": 0 }, "mibig_truth_loci": 1, "native_vs_gecco_bp_jaccard": 0.4237536350132848, "native_vs_gecco_matched_clusters": 1, "native_vs_gecco_cluster_jaccard": 0.5, "domain_concordance": { "native_calls": 103, "gecco_calls": 152, "shared": 99, "jaccard": 0.6346153846153846, "family_count_pearson_r": 0.8837045076343547 }, "native_gene_call_ms": 25805, "native_domain_scan_ms": 10501, "native_cluster_call_ms": 0, "truth": [ { "mibig_id": "BGC0002476", "seq_id": "U00096.3", "start": 619384, "end": 629713, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 1.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 } ], "native_clusters": [ { "cluster_id": "U00096.3_native_1", "seq_id": "U00096.3", "start": 607459, "end": 633999, "gene_count": 17, "core_gene_count": 2, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00501", "PF00550", "PF00668", "PF00975", "PF13193" ] } ], "gecco_default_clusters": [ { "seq_id": "U00096.3", "start": 609459, "end": 629713, "label": "NRP" }, { "seq_id": "U00096.3", "start": 3789047, "end": 3810304, "label": "Saccharide" } ] }, { "genome_id": "BN001302.1", "organism": "Aspergillus nidulans FGSC A4 chr II", "kingdom": "Eukaryota", "regime_note": "Out-of-regime: spliced fungal genes, bacterial gene callers", "genome_bp": 4011161, "genes_called_native": 5094, "native": { "tool": "native (rules v2)", "n_clusters": 4, "total_bp": 98261, "mibig_recall_any_overlap": 0.4, "mibig_recall_half_covered": 0.2, "mibig_truth_hit": 2, "predicted_overlapping_mibig_frac": 0.5, "wall_ms": 23221 }, "native_rules_v1": { "tool": "native (rules v1)", "n_clusters": 3, "total_bp": 83512, "mibig_recall_any_overlap": 0.4, "mibig_recall_half_covered": 0.2, "mibig_truth_hit": 2, "predicted_overlapping_mibig_frac": 0.6666666666666666, "wall_ms": 23221 }, "gecco_default": { "tool": "GECCO v0.11.0 (-m 0.8)", "n_clusters": 41, "total_bp": 1243866, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 5, "predicted_overlapping_mibig_frac": 0.0975609756097561, "wall_ms": 23000 }, "gecco_sensitive": { "tool": "GECCO v0.11.0 (-m 0.3)", "n_clusters": 45, "total_bp": 2250649, "mibig_recall_any_overlap": 1.0, "mibig_recall_half_covered": 1.0, "mibig_truth_hit": 5, "predicted_overlapping_mibig_frac": 0.06666666666666667, "wall_ms": 0 }, "mibig_truth_loci": 5, "native_vs_gecco_bp_jaccard": 0.06834279255255638, "native_vs_gecco_matched_clusters": 4, "native_vs_gecco_cluster_jaccard": 0.0975609756097561, "domain_concordance": { "native_calls": 97, "gecco_calls": 145, "shared": 94, "jaccard": 0.6351351351351351, "family_count_pearson_r": 0.9242355868170458 }, "native_gene_call_ms": 13817, "native_domain_scan_ms": 9404, "native_cluster_call_ms": 0, "truth": [ { "mibig_id": "BGC0001515", "seq_id": "BN001302.1", "start": 74783, "end": 138817, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.4020301397673148, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0002758", "seq_id": "BN001302.1", "start": 162823, "end": 193481, "classes": "PKS", "quality": "high", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001121", "seq_id": "BN001302.1", "start": 214879, "end": 224786, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 1.0, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0000107", "seq_id": "BN001302.1", "start": 1136055, "end": 1142873, "classes": "PKS", "quality": "questionable", "native_cover_frac": 0.0, "gecco_cover_frac": 0.8809209561519284, "gecco_sensitive_cover_frac": 1.0 }, { "mibig_id": "BGC0001399", "seq_id": "BN001302.1", "start": 3924000, "end": 3948000, "classes": "NRPS", "quality": "questionable", "native_cover_frac": 0.8397150118745053, "gecco_cover_frac": 0.943669013791092, "gecco_sensitive_cover_frac": 1.0 } ], "native_clusters": [ { "cluster_id": "BN001302.1_native_1", "seq_id": "BN001302.1", "start": 113074, "end": 142735, "gene_count": 11, "core_gene_count": 3, "classes": [ "NRPS" ], "domains": [ "PF00501", "PF00550", "PF00668" ] }, { "cluster_id": "BN001302.1_native_2", "seq_id": "BN001302.1", "start": 408600, "end": 421773, "gene_count": 10, "core_gene_count": 2, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00501", "PF00550" ] }, { "cluster_id": "BN001302.1_native_3", "seq_id": "BN001302.1", "start": 3539497, "end": 3568181, "gene_count": 20, "core_gene_count": 4, "classes": [ "PKS-I", "PKS-II" ], "domains": [ "PF00067", "PF00109", "PF00550", "PF00698", "PF02801", "PF08659", "PF14765", "PF16197" ] }, { "cluster_id": "BN001302.1_native_4", "seq_id": "BN001302.1", "start": 3917414, "end": 3944153, "gene_count": 11, "core_gene_count": 2, "classes": [ "NRPS", "NRPS-like" ], "domains": [ "PF00067", "PF00501", "PF00550" ] } ], "gecco_default_clusters": [ { "seq_id": "BN001302.1", "start": 74783, "end": 153227, "label": "NRP" }, { "seq_id": "BN001302.1", "start": 162823, "end": 243072, "label": "Polyketide" }, { "seq_id": "BN001302.1", "start": 299001, "end": 361104, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 396209, "end": 415845, "label": "NRP" }, { "seq_id": "BN001302.1", "start": 431088, "end": 476969, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 659547, "end": 700266, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 730594, "end": 792672, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 817978, "end": 845014, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 856653, "end": 889942, "label": "Polyketide" }, { "seq_id": "BN001302.1", "start": 907319, "end": 918376, "label": "RiPP" }, { "seq_id": "BN001302.1", "start": 955569, "end": 1004689, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 1127645, "end": 1142061, "label": "Polyketide" }, { "seq_id": "BN001302.1", "start": 1218159, "end": 1235290, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 1356261, "end": 1417742, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 1701725, "end": 1712229, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 1772922, "end": 1795996, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 1958090, "end": 2008819, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2020816, "end": 2054159, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2129324, "end": 2144053, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2202252, "end": 2222959, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2281926, "end": 2296304, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2301912, "end": 2335164, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2406356, "end": 2417067, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2450951, "end": 2476330, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2615331, "end": 2644897, "label": "NRP" }, { "seq_id": "BN001302.1", "start": 2707846, "end": 2718994, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2760210, "end": 2799758, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 2909088, "end": 2920505, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3043903, "end": 3070285, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3128516, "end": 3140954, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3204310, "end": 3230884, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3234348, "end": 3267819, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3343834, "end": 3359181, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3388797, "end": 3398525, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3457921, "end": 3468091, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3545341, "end": 3579797, "label": "Polyketide" }, { "seq_id": "BN001302.1", "start": 3594923, "end": 3627882, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3664557, "end": 3675917, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3865306, "end": 3913502, "label": "Unknown" }, { "seq_id": "BN001302.1", "start": 3918046, "end": 3946648, "label": "NRP" }, { "seq_id": "BN001302.1", "start": 3987989, "end": 4011006, "label": "Unknown" } ] } ], "total_genome_bp": 27503313, "total_mibig_loci": 33, "native_total_recalled_any": 15, "native_v1_total_recalled_any": 14, "gecco_total_recalled_any": 27, "gecco_sensitive_total_recalled_any": 30, "native_total_recalled_half": 13, "gecco_total_recalled_half": 27, "mean_bp_jaccard_native_vs_gecco": 0.39493198877406355, "mean_domain_jaccard": 0.6453222844012318, "bgc_rich_clusters_native": 24, "bgc_rich_clusters_gecco": 65, "negative_control_clusters_native": 1, "negative_control_clusters_gecco": 2, "signal_rating_beakers": 3, "signal_rating_label": "3 Comparative Synthesis (provisional; finalised after review)", "ascii_master_summary_table": "==================================================================================================================================================\nTOOL COMPARISON #15: NATIVE ARCHITECTURE-AWARE BGC ENGINE vs. GECCO v0.11.0 (CRF) -- MIBiG 4.0 GROUND TRUTH\n==================================================================================================================================================\nGenome | Organism | Mb | MIBiG | Nat v2/v1 hit | GECCO.8 hit/half | GECCO.3 hit | Nat/G.8/G.3 clusters | bp-Jacc | Dom-Jacc\n-------------+-----------------------------------+-------+-------+---------------+------------------+-------------+----------------------+---------+---------\nAL645882.2 | Streptomyces coelicolor A3(2) | 8.67 | 15 | 7/7 | 14/14 | 15 | 12/ 46/ 73 | 0.288 | 0.613\nCP000560.1 | Bacillus velezensis FZB42 | 3.92 | 6 | 4/4 | 5/5 | 5 | 9/ 10/ 12 | 0.825 | 0.729\nAE004091.2 | Pseudomonas aeruginosa PAO1 | 6.26 | 6 | 1/1 | 2/2 | 4 | 3/ 9/ 18 | 0.370 | 0.615\nU00096.3 | Escherichia coli K-12 MG1655 | 4.64 | 1 | 1/0 | 1/1 | 1 | 1/ 2/ 7 | 0.424 | 0.635\nBN001302.1 | Aspergillus nidulans FGSC A4 chr | 4.01 | 5 | 2/2 | 5/5 | 5 | 4/ 41/ 45 | 0.068 | 0.635\n-------------+-----------------------------------+-------+-------+---------------+------------------+-------------+----------------------+---------+---------\nTOTAL | 5 genomes (4 bacterial, 1 fungal) | 27.50 | 33 | 15/14 | 27/27 | 30 | | 0.395 | 0.645\n==================================================================================================================================================", "total_duration_ms": 168590 }