MicroFuse: Protein-to-Genome Expert Fusion for Microbial Operon Reasoning

TL;DR

MicroFuse is a novel fusion framework that integrates protein and genome context representations to improve microbial operon prediction, especially in ambiguous cases.

Contribution

It introduces a protein-to-genome expert fusion method with a Mixture-of-Experts model and a new large benchmark dataset for operon prediction.

Findings

MicroFuse outperforms existing baselines on the OG-Operon100K benchmark.

Cross-modal contrastive alignment is crucial for performance.

Largest gains occur in biologically ambiguous cases with conflicting signals.

Abstract

Predicting microbial operon co-membership requires integrating two complementary biological signals: protein-scale molecular identity and genome-context organization. While recent biological foundation models provide powerful representations of each view independently, naive concatenation of these modalities ignores a key biological property -- protein identity and genomic context may agree when adjacent genes form a coherent functional module, or conflict when sequence similarity is misleading but genomic layout indicates independent regulation. We present MicroFuse, a protein-to-genome expert fusion framework that integrates structure-aware protein representations from ProstT5 with genome-context representations from Bacformer through a four-expert Mixture-of-Experts module (protein, genome-context, agreement, and conflict experts) with a learned soft router. Training combines binary cross-entropy with symmetric cross-modal InfoNCE alignment and disagreement-weighted supervised contrastive shaping. We further construct OG-Operon100K, a 100,000-pair scaffold-level benchmark from the OMG metagenomic corpus with biologically grounded positive and negative criteria. On OG-Operon100K, MicroFuse achieves the strongest AUROC, AUPRC, mAP, and mAR among ProstT5-only, Bacformer-only, and Concat MLP baselines. Ablations identify cross-modal contrastive alignment as the dominant component, and a hard sequence-conflict subset reveals MicroFuse's largest gains precisely in biologically ambiguous cases where protein identity alone is misleading.