Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917460290043904 |
|---|---|
| author | Wu, Fang Xuan, Weihao Qi, Heli Cao, Hanqun Chang, Heng-Jui Zhou, Zeqi Zhao, Haokai Jian, Ma Ma, Carl Cheng, Yu-Chi Pang, Kuan Tang, Xiangru Wang, Zehong Li, Guanlue Wang, Hanchen Ying, Kejun Lu, Pan Im, Chiho Han, Seungju Xia, Peng Xu, Tinson Li, Yinxi Zhu, Deyao Heng, Pheng-Ann Yokoya, Naoto Sugiyama, Masashi Li, Li Erran Leskovec, Jure Choi, Yejin |
| author_facet | Wu, Fang Xuan, Weihao Qi, Heli Cao, Hanqun Chang, Heng-Jui Zhou, Zeqi Zhao, Haokai Jian, Ma Ma, Carl Cheng, Yu-Chi Pang, Kuan Tang, Xiangru Wang, Zehong Li, Guanlue Wang, Hanchen Ying, Kejun Lu, Pan Im, Chiho Han, Seungju Xia, Peng Xu, Tinson Li, Yinxi Zhu, Deyao Heng, Pheng-Ann Yokoya, Naoto Sugiyama, Masashi Li, Li Erran Leskovec, Jure Choi, Yejin |
| contents | Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce \textbf{Proteo-R1}, a reasoning-guided protein design framework that explicitly decouples \emph{molecular understanding} from \emph{geometric generation}. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an \emph{understanding expert}, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based \emph{generation expert}, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Proteo-R1: Reasoning Foundation Models for De Novo Protein Design Wu, Fang Xuan, Weihao Qi, Heli Cao, Hanqun Chang, Heng-Jui Zhou, Zeqi Zhao, Haokai Jian, Ma Ma, Carl Cheng, Yu-Chi Pang, Kuan Tang, Xiangru Wang, Zehong Li, Guanlue Wang, Hanchen Ying, Kejun Lu, Pan Im, Chiho Han, Seungju Xia, Peng Xu, Tinson Li, Yinxi Zhu, Deyao Heng, Pheng-Ann Yokoya, Naoto Sugiyama, Masashi Li, Li Erran Leskovec, Jure Choi, Yejin Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce \textbf{Proteo-R1}, a reasoning-guided protein design framework that explicitly decouples \emph{molecular understanding} from \emph{geometric generation}. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an \emph{understanding expert}, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based \emph{generation expert}, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/. |
| title | Proteo-R1: Reasoning Foundation Models for De Novo Protein Design |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2605.02937 |