cs.AINov 2, 2026

Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction

Authors: Zilu Zhang, Jing Bao, Lifeng Qiao, Sheng Xu, Qiantai Feng, Siqi Sun, Yang Yang

Organizations: Beijing University of Posts and Telecommunications, Beijing, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China · Research Institute of Intelligent Complex Systems, Fudan University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China

Abstract

Protein-complex structure prediction with AlphaFold 3 depends on MSA content, depth, and cross-chain pairing. Current pipelines apply uniform recipes, typically maximizing depth and pairing by species, yet even whether cross-chain pairing helps AF3 remains contested. We show that the value of both depth and pairing is strongly target-dependent, so no single recipe is optimal across interfaces. We introduce an autonomous agent that treats a frozen AF3 as a black-box experimental instrument. For each target, the agent formulates biological hypotheses, analyzes and reorganizes the MSA, and iteratively refines sequence selection and pairing using predictor label-free signals alone. On 1{,}015 protein--protein interfaces from three benchmarks released after AF3's training cutoff, the agent improves overall interface DockQ over AF3's default pipeline and fixed MSA recipes on every benchmark, while using on average 60% fewer MSA sequences than the default. Gains are largest for inter-species heteromers, where species-based pairing is unreliable: mean DockQ increases from 0.465 to 0.612 on FoldBench and from 0.482 to 0.562 on HD439. The improvements arise from both sequence construction and pairing policy, including deliberate non-pairing. These results recast MSA design as a target-specific problem and show that an autonomous agent can adapt it at test time through biological reasoning and self-directed, confidence-guided experimentation.

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Shortcut to Structure in AlphaFold 3

    Oct 6, 2026Jonathan Feldman, Jeffrey SkolnickProtein Structure PredictionMechanistic Interpretability

  2. AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design

    Aug 27, 2026Mingquan Liu, Jiangyu Chen, Hanqun Cao +9AI Agents for Scientific DiscoveryProtein Structure Prediction

  3. Predicting protein structures at any folding stage from sequence

    Nov 3, 2026Lisheng Zhang, Qingsong Li, Zinan Xie +7Protein Conformational Ensemble GenerationProtein Structure Prediction