Reproduce “scTREAT: Latent Diffusion for Single-Cell Drug-Response 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

Zhaokang Liang, Shuyang Zhuang, Xiaoran Jiao, Weian Mao, Hao Chen, Chunhua Shen

scTREAT predicts drug-induced expression changes from a cell’s baseline state and a drug at dose. It trains a diffusion model on combinations of these inputs, then adjusts state and drug guidance separately during generation. On Tahoe-100M pseudobulk tests, it leads on 10 of 12 criteria for held-out cell-line–drug pairs and 11 of 12 for held-out drugs, but not every metric.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.