{ "benchmark": { "archive_commit": "bb8500d60f90cb43397cc41de5aed396725aa800", "archive_sha256": "35d8484f00e4988d2e101038aa067fe1f93bb177157a1039aa457c0fc8deaf4f", "archive_url": "https://github.com/aswalker-lab/BGC-clustering-benchmark/archive/bb8500d60f90cb43397cc41de5aed396725aa800.tar.gz", "local_git_head_informational": "433ea7a31aff3ae95722784e7c44bc687913a7a9", "repository": "https://github.com/aswalker-lab/BGC-clustering-benchmark" }, "counts": { "all_mapped_bgcs": 1438, "ambiguous_exclusions": 437, "proteins": 24281, "sequence_bgcs": 1343, "source_genbank_files": 1343, "unambiguous_gold_bgcs": 1001 }, "license_note": "Benchmark source data are CC BY-NC 4.0; repository code and baseline licenses remain governed by their recorded upstream license files.", "records": { "key_inputs": [ { "modified_ns": 1781040051000000000, "path": "bgc-clustering-benchmark/source_data/NPAtlas_bm_v1.tsv", "sha256": "22941034330cb62d6bbca7c0dd1e4008a9ec9648db786358980dcc32441a35a6", "size_bytes": 29653300 }, { "modified_ns": 1781040051000000000, "path": "bgc-clustering-benchmark/tanimoto_results/NPAtlas_bm_v1.tsv", "sha256": "801d6794a7c370a4dc14c2458b084e358000e1a0977fb72d6790554c5478844d", "size_bytes": 40677771 }, { "modified_ns": 1781040051000000000, "path": "bgc-clustering-benchmark/bgc_similarities/bigscape_similarity_score_1.csv", "sha256": "0424fec86bc0dc8c3a1cea1ed50410edda3b4e44f7dee69d87d25805945c8a25", "size_bytes": 25588513 } ], "licenses": [ { "modified_ns": 1781040051000000000, "path": "bgc-clustering-benchmark/LICENSE", "sha256": "f989979ecb3b4eb219711e5473a9068f868cb663c58ca997d19efca2cf713968", "size_bytes": 1890 }, { "modified_ns": 1781040051000000000, "path": "bgc-clustering-benchmark/source_data/LICENSE", "sha256": "5e8ddbe5c8c552ab58a775b58f92443f0baa0def7e7a9d765472ab41e9dfbee4", "size_bytes": 18076 }, { "modified_ns": 1786365937050765942, "path": "BGC-MLM/LICENSE", "sha256": "12db62e5d1f00c80fb9856689f5f47853ba49781165689e02fae100c271b8846", "size_bytes": 1069 }, { "modified_ns": 1786365938045250602, "path": "BGC-MAP/README.md", "sha256": "04647b5fe896efa4b3da0e7f538da3c0d71d3b5954de9436f7ade585cbc07b8b", "size_bytes": 9459 } ], "processed_outputs": [ { "modified_ns": 1786366553055202716, "path": "processed/gold_bgc_product_mapping.csv", "sha256": "7b3194026936fd8e289d0b8d6a47cf41a711203ce0780772aba88666b45c8ac1", "size_bytes": 137743 }, { "modified_ns": 1786366553057159857, "path": "processed/all_bgc_product_metadata.csv", "sha256": "96c7328631b7f2eb5f9fea7540522c667092f346dfbf9b1659b4eb6c96833e30", "size_bytes": 110667 }, { "modified_ns": 1786366553058159861, "path": "processed/ambiguous_product_exclusions.csv", "sha256": "167625be31fd9fd2cfe29de55cbfc69ba55892227f4676f46fb410774aa1bf7c", "size_bytes": 54470 }, { "modified_ns": 1786366557720178633, "path": "processed/external_proteins.fasta", "sha256": "178fa042d25d4a0477f1cd123de3715317b71084c45cb563639b3f470b933dcf", "size_bytes": 17125714 }, { "modified_ns": 1786366557726178658, "path": "processed/external_atlas.csv", "sha256": "4420eac248985c905f9e3d15bafec606157cf8106c6457b9f569b710bd0de5fa", "size_bytes": 563730 }, { "modified_ns": 1786366557913179410, "path": "processed/external_sequence_provenance.json", "sha256": "c566d07f80cb0c5b5ac82206fafb463968c3e4133be01b6ebedf3274012a9b25", "size_bytes": 265576 } ] }, "records_sha256": "36cf6d661f6873cb733ea3d68936fdefe25a6e95c170ac927861581b1271ec8e", "released_baselines": { "BGC-MAP": { "commit": "d6119811d9c1bab2ea45ef77fc5d20dfb6fc3361", "repository": "https://github.com/EvoCatalysis/BGC_annotation" }, "BGC-MLM": { "commit": "1ca3239f48b71432c2ef378fa7edda635e2ddbcb", "repository": "https://github.com/aswalker-lab/BGC-MLM" } }, "schema_version": 1, "supersedes": "data/manifests/external_benchmark_manifest.json" }