Reproduce “Predicting Drug Interactions and Mutagenicity with Ensemble Classifiers on Subgraphs of Molecules” 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
Andrew Schaumberg, Angela Yu, Tatsuhiro Koshi, Xiaochan Zong, Santoshkalyan Rayadhurgam
The authors predict drug–target interactions by counting small local subgraphs in molecular graphs and classifying those counts with a random forest, rather than enumerating separated subgraph pairs. On the reported DrugBank comparison, they report 94.5% AUROC and 86.1% validation accuracy, versus 74% and 67.5% for a prior cosine-kernel method; differing data and missing uncertainty estimates limit the comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.