Reproduce “Count Bridges enable Modeling and Deconvolving Transcriptomic Data” 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
Nic Fishman, Gokul Gowri, Tanush Kumar, Jiaqi Lu, Valentin de Bortoli, Jonathan S. Gootenberg, Omar Abudayyeh
Count Bridges model integer-valued counts with Poisson birth-and-death bridges, then use aggregate-conditioned sampling to infer unit-level profiles from pooled totals, with images as side information. In artificially pooled MERFISH mouse-brain data, profiles match held-out cell-profile distributions better than assigning each cell the spot mean: MMD is 0.203 versus 0.409. This supports distributional fit, not recovery of each cell’s original profile.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.