BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models

• URL: http://arxiv.org/abs/2506.08936v1
• Date: Tue, 10 Jun 2025 16:01:11 GMT
• Title: BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models
• Authors: Amina Mollaysa, Artem Moskale, Pushpak Pati, Tommaso Mansi, Mangal Prakash, Rui Liao,
• Abstract summary: We present BioLangFusion, a simple approach for integrating pre-trained DNA, mRNA, and protein language models into unified molecular representations.<n>Three fusion techniques are studied: (i) codon-level embedding concatenation, (ii) entropy-regularized attention pooling inspired by multiple-instance learning, and (iii) cross-modal multi-head attention.
• Score: 4.03394966596019
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present BioLangFusion, a simple approach for integrating pre-trained DNA, mRNA, and protein language models into unified molecular representations. Motivated by the central dogma of molecular biology (information flow from gene to transcript to protein), we align per-modality embeddings at the biologically meaningful codon level (three nucleotides encoding one amino acid) to ensure direct cross-modal correspondence. BioLangFusion studies three standard fusion techniques: (i) codon-level embedding concatenation, (ii) entropy-regularized attention pooling inspired by multiple-instance learning, and (iii) cross-modal multi-head attention -- each technique providing a different inductive bias for combining modality-specific signals. These methods require no additional pre-training or modification of the base models, allowing straightforward integration with existing sequence-based foundation models. Across five molecular property prediction tasks, BioLangFusion outperforms strong unimodal baselines, showing that even simple fusion of pre-trained models can capture complementary multi-omic information with minimal overhead.

Related papers

• A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery [32.573496601865465]
  Structure-based drug discovery (SBDD) is a systematic scientific process that develops new drugs by leveraging the detailed physical structure of the target protein.<n>Recent advancements in pre-trained models for biomolecules have demonstrated remarkable success across various biochemical applications.
  arXiv  Detail & Related papers  (2025-03-06T12:04:56Z)
• Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification [53.488387420073536]
  Life-Code is a comprehensive framework that spans different biological functions.<n>Life-Code achieves state-of-the-art performance on various tasks across three omics.
  arXiv  Detail & Related papers  (2025-02-11T06:53:59Z)
• Biology Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models [51.316001071698224]
  We introduce Biology-Instructions, the first large-scale multi-omics biological sequences-related instruction-tuning dataset.<n>This dataset can bridge the gap between large language models (LLMs) and complex biological sequences-related tasks.<n>We also develop a strong baseline called ChatMultiOmics with a novel three-stage training pipeline.
  arXiv  Detail & Related papers  (2024-12-26T12:12:23Z)
• SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation [97.99658944212675]
  We introduce a novel pre-training strategy for protein foundation models. It emphasizes the interactions among amino acid residues to enhance the extraction of both short-range and long-range co-evolutionary features. Trained on a large-scale protein sequence dataset, our model demonstrates superior generalization ability.
  arXiv  Detail & Related papers  (2024-10-31T15:22:03Z)
• DPLM-2: A Multimodal Diffusion Protein Language Model [75.98083311705182]
  We introduce DPLM-2, a multimodal protein foundation model that extends discrete diffusion protein language model (DPLM) to accommodate both sequences and structures. DPLM-2 learns the joint distribution of sequence and structure, as well as their marginals and conditionals. Empirical evaluation shows that DPLM-2 can simultaneously generate highly compatible amino acid sequences and their corresponding 3D structures.
  arXiv  Detail & Related papers  (2024-10-17T17:20:24Z)
• BSM: Small but Powerful Biological Sequence Model for Genes and Proteins [6.6055625629542085]
  We introduce BSM, a small but powerful mixed-modal biological sequence foundation model. It is trained on three types of data: RefSeq, Gene Related Sequences, and interleaved biological sequences from the web. It significantly enhances learning efficiency and cross-modal representation, outperforming models trained solely on unimodal data.
  arXiv  Detail & Related papers  (2024-10-15T11:12:28Z)
• Multi-modal Transfer Learning between Biological Foundation Models [2.6545450959042234]
  We propose a multi-modal-specific model that connects DNA, RNA, and proteins by leveraging information from different pre-trained modality encoders. We show that our model, dubbed IsoFormer, is able to accurately predict differential transcript expression, outperforming existing methods. We open-source our model, paving the way for new multi-modal gene expression approaches.
  arXiv  Detail & Related papers  (2024-06-20T09:44:53Z)
• Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey [75.47055414002571]
  The integration of biomolecular modeling with natural language (BL) has emerged as a promising interdisciplinary area at the intersection of artificial intelligence, chemistry and biology. We provide an analysis of recent advancements achieved through cross modeling of biomolecules and natural language.
  arXiv  Detail & Related papers  (2024-03-03T14:59:47Z)
• xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein [74.64101864289572]
  We propose a unified protein language model, xTrimoPGLM, to address protein understanding and generation tasks simultaneously.<n>xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories.<n>It can also generate de novo protein sequences following the principles of natural ones, and can perform programmable generation after supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-01-11T15:03:17Z)
• Integrating Chemical Language and Molecular Graph in Multimodal Fused Deep Learning for Drug Property Prediction [9.388979080270103]
  We construct multimodal deep learning models to cover different molecular representations. Compared with mono-modal models, our multimodal fused deep learning (MMFDL) models outperform single models in accuracy, reliability, and resistance capability against noise.
  arXiv  Detail & Related papers  (2023-12-29T07:19:42Z)
• 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)

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.