Reproduce “SCOPE: Single-Cell Omics Prediction from Histology via RNA-Protein Prior Enhancement” 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

Leyang Tao, Xuan Gong, Luyuan Xie, Arjun Beniwal, Yuqi Tan, Kun-Hsing Yu

SCOPE predicts RNA and protein profiles from H&E images and nuclei using shared gene representations enriched with information from related genes. Training uses unpaired assay sections, so test-time predictions require no molecular measurements from the test section. Joint training improves unseen-protein Pearson correlation by 0.0413 on external CRC and 0.0306 on external ORION, but does not establish universal molecular recovery.

Summary by alphaXiv.

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