Article

Sequence-Derived Representations versus Pfam-Domain Content for Biosynthetic Gene Cluster Retrieval

2026-08-22

Abstract excerpt

Retrieving BGCs related to those of a known producer can be regarded as a representation-learning objective. We hypothesize that ESM-2 sequence-derived representations of BGCs can improve retrieval beyond the Pfam-domain content metric. Our toolkit is the following: group-disjoint train, validation, and test assignments, validation-frozen model selection, ﬁve seeds, and family-level paired inference. Of 6,953 atla...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 3b388842-f168-5752-8bac-64b2533155d0
DOI: 10.64898/2026.08.21.746127

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Sequence-Derived Representations versus Pfam-Domain Content for Biosynthetic Gene Cluster RetrievalDOI 10.64898/2026.08.21.746127Read

An interpreted atlas of biosynthetic gene clusters from 1,000 fungal genomesSemantic proximity Read

Diversity and taxonomic distribution of bacterial biosynthetic gene clusters predicted to produce compounds with therapeutically relevant bioactivitiesSemantic proximity Read

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine LearningSemantic proximity Read

Leveraging existing data to maximise quality and consistency across gene model annotations: a <i>Fusarium</i> pan-annotationSemantic proximity Read

iPRESTO: Automated discovery of biosynthetic sub-clusters linked to specific natural product substructuresSemantic proximity Read

MicroGenomer: A Foundation Model for Transferable Microbial Genome Representations Enabling Multi-scale Genomic Understanding and Ecophysiological Trait PredictionSemantic proximity Read

iPRESTO: automated discovery of biosynthetic sub-clusters linked to specific natural product substructuresSemantic proximity Read

Quantifying cumulative phenotypic and genomic evidence for procedural generation of metabolic network reconstructions.Semantic proximity Read

Gene-language models are whole genome representation learnersSemantic proximity Read

Predicting phenotypic traits of prokaryotes from protein domain frequencies.Semantic proximity Read

Accelerating High-Performance Classification of Bacterial Proteins Secreted via Non-Classical Pathways: no needing for deepnessSemantic proximity Read

The secondary metabolism collaboratory: a database and web discussion portal for secondary metabolite biosynthetic gene clustersSemantic proximity Read