{
 "id": "Nugkta/bgc-bench",
 "owner": "Nugkta",
 "name": "bgc-bench",
 "downloads": 102,
 "likes": 0,
 "last_modified": "2026-10-29T16:37:29.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{xiao2026bgcbench,\n  title     = {Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters},\n  author    = {Xiao, Hanlin and Takano, Eriko and {\\'A}lvarez, Mauricio A. and Breitling, Rainer},\n  booktitle = {Advances in Neural Information Processing Systems (Evaluations and Datasets Track)},\n  year      = {2026}\n}\n@article{mibig4,\n  title   = {{MIBiG} 4.0: advancing biosynthetic gene cluster curation through global collaboration},\n  author  = {Zdouc, Mitja M. and others},\n  journal = {Nucleic Acids Research}, volume = {53}, pages = {D678--D690}, year = {2025},\n  doi     = {10.1093/nar/gkae1115}\n}\n@article{mistry2021pfam,\n  title   = {{Pfam}: The Protein Families Database in 2021},\n  author  = {Mistry, Jaina and Chuguransky, Sara and Williams, Lowri and others},\n  journal = {Nucleic Acids Research}, volume = {49}, number = {D1}, pages = {D412--D419}, year = {2021},\n  doi     = {10.1093/nar/gkaa913}\n}\n@article{navarro2020bigscape,\n  title   = {A Computational Framework to Explore Large-Scale Biosynthetic Diversity},\n  author  = {Navarro-Mu{\\~n}oz, Jorge C. and Selem-Mojica, Nelly and Mullowney, Michael W. and others},\n  journal = {Nature Chemical Biology}, volume = {16}, number = {1}, pages = {60--68}, year = {2020},\n  doi     = {10.1038/s41589-019-0400-9}\n}\n@article{npclassifier,\n  title   = {{NPClassifier}: A Deep Neural Network-Based Structural Classification Tool for Natural Products},\n  author  = {Kim, Hyun Woo and Wang, Mingxun",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "f64c7f6eb6d3910cc7b4434cdc114dc7501305b1",
 "stated_evidence": "https://huggingface.co/datasets/Nugkta/bgc-bench/blob/f64c7f6eb6d3910cc7b4434cdc114dc7501305b1/README.md",
 "file_evidence": "https://huggingface.co/datasets/Nugkta/bgc-bench/tree/f64c7f6eb6d3910cc7b4434cdc114dc7501305b1",
 "card_nc": false
}