Reproduce “MitoWorld: A Stochastic World Model of the Single-Cell Cycle under Genetic Perturbation” 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
Ting Long, Xiaojing Sun, Cheng Han, Zhicheng Ji, Yingnian Wu, Jiebo Luo, Heng Fan, Dongfang Liu
MitoWorld models possible image trajectories and division times for cells after gene knockdown. It advances cell states through stochastic, gene-conditioned transitions, predicts division with a learned hazard, and renders states as images. On 325 held-out MitoCheck tracks, it improves future-frame FID (35.54 versus 54.36) and sequence JEDi (2.04 versus 3.75) over HI; evaluation covers known knockdowns in one HeLa dataset.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.