Reproduce “Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zilu Zhang, Jing Bao, Lifeng Qiao, Sheng Xu, Qiantai Feng, Siqi Sun, Yang Yang
The authors introduce an agent that adapts multiple sequence alignments (MSAs) for each protein-complex target, selecting sequences and testing pairing choices with frozen AlphaFold 3 feedback. Across three post-training benchmarks, its mean DockQ exceeds AF3-Default and fixed MSA recipes. On FoldBench-v1, it scores 0.604 versus 0.584, but this does not establish lower computational cost.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.