aiqbench analysis
CODesign addresses the core consistency challenge in de novo protein design by jointly generating sequences and structures rather than decoupling them. The framework leverages a multimodal joint flow model and a distilled dataset to achieve state-of-the-art success rates for binder design, offering significant performance gains with negligible additional computational cost. This advancement represents a meaningful step forward in the practical application of generative models for molecular engineering.
CODesign: Consistency from Data to Trajectory in All-Atom Protein Binder Co-Design
arXiv:2610.01773v1 Announce Type: cross Abstract: The central challenge in de novo protein design is generating plausible, mutually compatible structures and sequences, such that each designed sequence folds into its intended structure and the structure accommodates that sequence. Compared to typical two-stage design methods, which decouple the modeling of the interdependent modalities, co-design models improve the cross-modal consistency by jointly generating sequences and structures. However, naively generating sequences and structures simultaneously does not ensure their consistency. To address this challenge, we propose CODesign framework. We improve data consistency by generating approximately 105,000 consistency-distilled dimers. We further promote consistency through a multimodal joint flow model that captures the joint distribution of sequences, backbone structures, and local atomic configurations, together with a consistency-aware joint resampling strategy that iteratively refines sequences and side chains. Experiments show that CODesign achieves state-of-the-art performance with the highest in silico success rates on both protein- and ligand-target binder design. Ablation studies also demonstrate our distilled dataset increases performance by 70.9%, which can be further improved by our proposed resampling mechanism with negligible additional computational cost. Code, model weights and the new dataset will be completely open-source.
Abstract:The central challenge in de novo protein design is generating plausible, mutually compatible structures and sequences, such that each designed sequence folds into its intended structure and the structure accommodates that sequence. Compared to typical two-stage design methods, which decouple the modeling of the interdependent modalities, co-design models improve the cross-modal consistency by jointly generating sequences and structures. However, naively generating sequences and structures simultaneously does not ensure their consistency. To address this challenge, we propose CODesign framework. We improve data consistency by generating approximately 105,000 consistency-distilled dimers. We further promote consistency through a multimodal joint flow model that captures the joint distribution of sequences, backbone structures, and local atomic configurations, together with a consistency-aware joint resampling strategy that iteratively refines sequences and side chains. Experiments show that CODesign achieves state-of-the-art performance with the highest in silico success rates on both protein- and ligand-target binder design. Ablation studies also demonstrate our distilled dataset increases performance by 70.9%, which can be further improved by our proposed resampling mechanism with negligible additional computational cost. Code, model weights and the new dataset will be completely open-source.
Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI)
arXiv:2610.01773 [cs.CE]
(or arXiv:2610.01773v1 [cs.CE] for this version)
https://doi.org/10.48550/arXiv.2610.01773 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 283 words
Related coverage
DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales
arXiv · Jul 20, 2026
DCFold: Efficient Protein Structure Generation with Single Forward Pass
arXiv · Sep 30, 2026
Stochastic Control Policies for Robust Molecular Transition Path Sampling
arXiv · Aug 17, 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · Oct 8, 2026