Metraipolis › archive › dc_fb93bbefc38c

Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters — arXiv:2611.02275

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02275
License (as archived): CC0-1.0
Archived: 2026-11-03T10:23:40.805Z
SHA-256 of the archived text: db1b7e1c2e717967370426aa1b538a7cd644a961de3c30df23d532672a104ae8
Stable URL of this page: https://metraipolis.com/documento/dc_fb93bbefc38c

How to cite

Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters — arXiv:2611.02275 — arXiv (en), https://arxiv.org/abs/2611.02275 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb93bbefc38c (Metraipolis archive dc_fb93bbefc38c, sha256 db1b7e1c2e717967370426aa1b538a7cd644a961de3c30df23d532672a104ae8)

BibTeX

@misc{dcfb93bbefc38c,
  title = {Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters — arXiv:2611.02275},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02275},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb93bbefc38c; sha256 db1b7e1c2e717967370426aa1b538a7cd644a961de3c30df23d532672a104ae8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02275. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Biosynthetic gene clusters (BGCs) are co-located genes that encode the biosynthesis of specialized metabolites, an important source of antibiotics, anticancer agents, immunosuppressants, and agricultural bioactives. Deep learning, particularly self-supervised foundation models, has spurred interest in BGC sequence modeling, but evaluation has lagged behind: existing benchmarks often rely on coarse classification over small curated datasets, providing limited discrimination among models and insight into downstream utility. We propose a benchmark-design framework in which an informative benchmark should be discriminative, separating models with statistical confidence, and applicable, spanning scientifically meaningful tasks under different levels of generalization. We instantiate this framework as BGC-Bench, which derives five tasks from MIBiG, ranging from A-domain substrate prediction to BGC-molecule retrieval, evaluates them under genotype- and phenotype-shift splits, includes an active-learning setting for label-scarce discovery, and is easily extensible to new tasks and encoders. BGCs further provide a shared testbed across granularities and modalities: BGC-Bench compares twelve encoders on nucleotide, amino-acid, or Pfam-domain sequences, including compositional baselines for each input type, and combines BGC and chemical encoders for cross-modal retrieval. No single representation dominates: the best granularity depends on the biological scale of the task, and pretrained encoders do not consistently outperform other representations across tasks and splits. Active-learning experiments show that most tasks remain data-limited, encoder rankings change with labeling budget, and acquisition strategies yield modest gains. These results show that BGC model evaluation requires task-diverse, shift-aware benchmarks, and the framework can be generalized to benchmark design beyond BGCs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02275 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:19:49.868Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).