Proteo-R1: Reasoning Foundation Models for De Novo Protein Design

2026-05-01

AI Summary

Current de novo protein design methods lack explicit reasoning mechanisms, making it difficult to distinguish functionally critical residues from the structural generation process, thereby limiting interpretability and controllability. This work proposes Proteo-R1, a novel framework that, for the first time, integrates residue-level functional reasoning as a hard constraint into the design pipeline: a multimodal large language model identifies functionally essential sites, and a diffusion model performs conditional geometric co-design under this constraint. This dual-expert architecture decouples molecular understanding from structure generation, enabling stable and modular integration of LLM-based reasoning with generative modeling. The approach significantly enhances design fidelity, interpretability, and the reuse of biochemical knowledge, allowing precise anchoring and systematic modulation of key interaction sites.

Abstract

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/.

Problem

• de novo protein design
• reasoning
• functional residues
• interpretability
• controllability

Innovation

• reasoning-guided design
• de novo protein design
• multimodal large language model
• diffusion-based generation
• residue-level constraints