Reproduce “Learning developmental dynamics from lineage context” 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
Gokul Gowri, Nic Fishman, William N. Colgan, Minming Wang, Yusuke Kijima, Sachin A. Kumar, Aleksandr Zimin, Luke W. Koblan and 5 more
The authors introduce lineage inpainting, a model that uses states across a lineage tree to infer states. It uses relatives as context, rather than matching expression. In a 4-million-cell atlas, it infers five endothelial progenitor types; inferred transitions are 93% consistent with a curated list. Tbx5 predictions correlate with measurements (r = 0.57), but counterfactuals assume unchanged transition rules.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.