Reproduce “DS-ProGen: A Dual-Structure Deep Language Model for Functional Protein Design” 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
Yanting Li, Jiyue Jiang, Zikang Wang, Ziqian Lin, Dongchen He, Yuheng Shan, Yanruisheng Shao, Jiayi Li and 6 more
DS-ProGen addresses inverse protein folding by generating amino-acid sequences from both a protein’s backbone geometry and surface chemistry. Separate encoders represent the scaffold and exterior, and an autoregressive decoder produces the sequence one residue at a time. On the PRIDE test set, it achieved 61.47% recovery, versus 51.85% for ESM-IF; differing training conditions limit direct comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.