Reproduce “scAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells” 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
Zhaoqi Song, Ye Du, Yusuke Iwasawa, Yutaka Matsuo, Qian Niu
scAnyOmics predicts missing RNA, protein, or chromatin measurements in single-cell data. It trains a student to predict hidden modalities using a pretrained RNA model. In sample-held-out tests, it beat simple baselines on six RNA- or protein-target tasks; for protein from ATAC alone, median Spearman correlation was 0.22 versus 0.10. Tests do not establish donor generalization or reliable predictions for every cell.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.