# BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language

arXiv: https://arxiv.org/abs/2606.22138 · HTML: https://mlsanity.com/paper/2606.22138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 156 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language](https://mlsanity.com/paper/2209.05481/) (2022)
- [Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models](https://mlsanity.com/paper/1705.10843/) (2017)
- [BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine](https://mlsanity.com/paper/2308.09442/) (2023)
- [A Text-guided Protein Design Framework](https://mlsanity.com/paper/2302.04611/) (2023)
- [MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning](https://mlsanity.com/paper/2507.16812/) (2025)
- [Nature Language Model: Deciphering the Language of Nature for Scientific Discovery](https://mlsanity.com/paper/2502.07527/) (2025)
- [Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale](https://mlsanity.com/paper/2603.25040/) (2026)
- [Is Transfer Learning Necessary for Protein Landscape Prediction?](https://mlsanity.com/paper/2011.03443/) (2020)
- [Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation](https://mlsanity.com/paper/2412.14642/) (2024)
- [Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey](https://mlsanity.com/paper/2403.01528/) (2024)
- [SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines](https://mlsanity.com/paper/2509.21320/) (2025)
- [MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learning](https://mlsanity.com/paper/2506.00009/) (2025)
- [KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge](https://mlsanity.com/paper/2510.19484/) (2025)
- [BioMedGPT-Mol: Multi-task Learning for Molecular Understanding and Generation](https://mlsanity.com/paper/2512.04629/) (2025)
- [Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences](https://mlsanity.com/paper/2606.16905/) (2026)
- [Interleaved Tool-Call Reasoning for Protein Function Understanding](https://mlsanity.com/paper/2601.03604/) (2026)

## Built on by (most cited first, 1 of 1)

- [S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation](https://mlsanity.com/paper/2607.15686/) (2026)

## Abstract (arXiv)

We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules and proteins within a single decoder-only architecture. Existing biological foundation models pursue native multimodality and broad entity coverage separately: those that fuse multiple modalities under a shared objective remain confined to a single entity type, while those spanning multiple entity types either omit explicit structural modeling or rely on adapter-based designs in which the model cannot natively generate the very modalities it can read. BioMatrix closes this gap by mapping molecular sequences (supporting both SMILES and SELFIES notations), molecular structures, protein sequences, protein structures, and natural language into a shared discrete token space through a unified tokenization scheme, so that all modalities are consumed and produced uniformly under a single next-token prediction objective -- without external encoders, projection adapters, or modality-specific output heads. Built upon the Qwen3 language model (1.7B and 4B), BioMatrix is continually pretrained on 304.4 billion tokens spanning general and domain-specific text, sequence and structure views of molecules and proteins, and cross-modal corpora that interleave biomolecular entities with scientific text and link distinct entities through molecule-protein and protein-protein interaction data. After tuning on a comprehensive suite of downstream applications covering 80 tasks across 6 categories -- encompassing single-entity and multi-entity understanding and generation tasks across and within modalities -- BioMatrix achieves state-of-the-art or competitive performance on 77 out of 80 tasks, demonstrating that a single, natively multimodal generalist model can effectively match or surpass specialized approaches across a wide range of biological tasks.