analiza aiqbench
SymFold advances protein inverse folding by integrating pretrained sequence evolution knowledge from protein language models with structural insights from multimodal models within a symmetric dual-path architecture. This approach overcomes the limitations of serial pipelines where post-hoc refinements are constrained by upstream prediction errors, achieving state-of-the-art results on standard benchmarks. The work highlights a promising direction for leveraging complementary AI priors to improve accuracy in computational biology applications like enzyme engineering and drug discovery.
SymFold: Synergizing Evolutionary and Structural Priors for Accurate Protein Inverse Folding
arXiv:2609.01353v1 Announce Type: new Abstract: Protein inverse folding aims to recover amino acid sequences for a given 3D protein structure, underpinning broad applications such as enzyme engineering and drug discovery.Current methods often follow a serial pipeline, in which a structure encoder predicts a coarse sequence, which is then refined by protein language models (PLMs). However, because PLMs only perform post-hoc sequence edits, the refinement is bounded by the quality of upstream predictions.Thanks to recent multimodal protein language models (MPLMs), we could directly encode structure to generate sequences with pretrained structural knowledge, but we observe that they are not effective for inverse folding. Therefore, we introduce a symmetric dual-path architecture that both leverages PLMs for pretrained sequence evolution knowledge and MPLMs for pretrained structural knowledge to iteratively guide protein sequence generation.Through extensive experiments across standard protein inverse folding benchmarks, our method achieves state-of-the-art performance, surpassing prior approaches, and ablation studies validate the rationale of our symmetric design, revealing a promising direction for the community.
Abstract:Protein inverse folding aims to recover amino acid sequences for a given 3D protein structure, underpinning broad applications such as enzyme engineering and drug this http URL methods often follow a serial pipeline, in which a structure encoder predicts a coarse sequence, which is then refined by protein language models (PLMs). However, because PLMs only perform post-hoc sequence edits, the refinement is bounded by the quality of upstream this http URL to recent multimodal protein language models (MPLMs), we could directly encode structure to generate sequences with pretrained structural knowledge, but we observe that they are not effective for inverse folding. Therefore, we introduce a symmetric dual-path architecture that both leverages PLMs for pretrained sequence evolution knowledge and MPLMs for pretrained structural knowledge to iteratively guide protein sequence this http URL extensive experiments across standard protein inverse folding benchmarks, our method achieves state-of-the-art performance, surpassing prior approaches, and ablation studies validate the rationale of our symmetric design, revealing a promising direction for the community.
Artificial Intelligence (cs.AI)
arXiv:2609.01353 [cs.AI]
(or arXiv:2609.01353v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.01353 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.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026
Why Specialization Is Inevitable
Hugging Face · 30 iun. 2026
A General Harness for Protein Foundation Model Fitness Prediction
arXiv · 29 sept. 2026
Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
arXiv · 3 iun. 2026