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

• URL: http://arxiv.org/abs/2605.08815v1
• Date: Sat, 09 May 2026 09:07:11 GMT
• Title: MicroFuse: Protein-to-Genome Expert Fusion for Microbial Operon Reasoning
• Abstract summary: MicroFuse is a protein-to-genome expert fusion framework.<n>It integrates structure-aware protein representations from ProstT5 with genome-context representations from Bacformer.<n>On OG-Operon100K, MicroFuse achieves the strongest AUROC, AUPRC, mAP, and mAR among ProstT5-only, Bacformer-only, and Concat baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design [18.17410967913783]
  We introduce MCTH (Monte Carlo Tree Hallucination), an inference-only framework that casts all-atom sequence-structure co-design as uncertainty-aware planning.<n>Across protein-RNA, protein-DNA, protein-protein, and protein-ligand design, matched-budget experiments show that adaptive search improves over simpler sampling and cycling strategies.
  arXiv  Detail & Related papers  (2026-08-18T05:16:41Z)
• BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells [64.21963170814706]
  BioM-JEPA predicts aggregate representations of graph-connected gene blocks.<n>A student network infers each target-block representation from the remaining genes in a cell.<n>Across CellBench tasks, BioM-JEPA embeddings retained expression, pathway and neighbourhood information.
  arXiv  Detail & Related papers  (2026-08-06T11:58:29Z)
• AMix-2: Establishing Protein as a Native Modality in Large Language Models [88.00237394496698]
  We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs)<n>AMix-2 is built upon two key ideas: (1) a unified protein-text formulation that embeds natural language and protein sequence in a shared token space; and (2) a block-wise diffusion language modeling backbone.<n>We introduce ProteinArena, a comprehensive benchmark with time-aware and homology-aware protocols across various understanding and design tasks.
  arXiv  Detail & Related papers  (2026-05-29T07:58:08Z)
• MIMIC: A Generative Multimodal Foundation Model for Biomolecules [33.78730863042891]
  We present MIMIC, a generative multimodal foundation model trained on our newly curated and aligned dataset, LORE.<n>MIMIC uses a split-track encoder-decoder architecture to condition on arbitrary subsets of observed modalities.<n>MIMIC achieves state-of-the-art performance on RNA and protein downstream modeling tasks.
  arXiv  Detail & Related papers  (2026-04-27T14:10:01Z)
• Classifying Metamorphic versus Single-Fold Proteins with Statistical Learning and AlphaFold2 [1.5905165019585945]
  Metamorphic proteins, which can adopt multiple distinct conformations, have conformational diversity that cannot be adequately modeled by AlphaFold2.<n>We develop a novel classification framework by re-purposing AlphaFold2 to generate conformational ensembles.<n>A random forest classifier trained on a benchmark dataset of known metamorphic and single-fold proteins achieves a mean AUC of 0.869 with cross-validation.
  arXiv  Detail & Related papers  (2025-12-10T20:37:21Z)
• Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers [76.95505296417866]
  Self-supervised training of language models (LMs) has seen great success for protein sequences in learning meaningful representations and for generative drug design.<n>Most protein LMs are based on the Transformer architecture trained on individual proteins with short context lengths.<n>In this work, we propose LC-PLM based on an alternative protein LM architecture, BiMamba-S, built upon selective structured state-space models.
  arXiv  Detail & Related papers  (2024-10-29T16:43:28Z)
• Large-Scale Multi-omic Biosequence Transformers for Modeling Protein-Nucleic Acid Interactions [4.36852565205713]
  We present OmniBioTE, the largest open-source multi-omic model trained on over 250 billion tokens of mixed protein and nucleic acid data.<n>We show that OmbiBioTE achieves state-of-the-art results predicting the change in Gibbs free energy of the binding interaction between a given nucleic acid and protein.
  arXiv  Detail & Related papers  (2024-08-29T03:56:40Z)
• Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning [78.38442423223832]
  We develop a novel codebook pre-training task, namely masked microenvironment modeling. We demonstrate superior performance and training efficiency over state-of-the-art pre-training-based methods in mutation effect prediction.
  arXiv  Detail & Related papers  (2024-05-16T03:53:21Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Learning Geometrically Disentangled Representations of Protein Folding Simulations [72.03095377508856]
  This work focuses on learning a generative neural network on a structural ensemble of a drug-target protein. Model tasks involve characterizing the distinct structural fluctuations of the protein bound to various drug molecules. Results show that our geometric learning-based method enjoys both accuracy and efficiency for generating complex structural variations.
  arXiv  Detail & Related papers  (2022-05-20T19:38:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.