Reproduce “STAMP as a topology-aware molecular language for fragment-level learning and editing” 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
Yuxuan Ren, Jiatong Li, Ziqiao Meng, Yatao Bian
STAMP makes molecular fragments addressable so a model can change one part while preserving the rest. It separates fragment identity, attachment atoms, and tree structure; depth-first ordering gives each subtree a contiguous span, and a decoder and compiler support edits. Compatible subtree replacement was strictly valid in 98.5% of trials, versus 23.6% for arbitrary spans; these computational results do not establish clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.