Reproduce “ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration” 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
Anqi Yu, Xudong Xu, Jianzhi Lu, Yuqi Sun, Bingguo Chen, Chenxi Ma, Weimin Tan, Bo Yan
ILR-SMO integrates spatial multi-omics through successive modality-by-modality updates to a shared representation, with learned reliability-aware gating and spatial and dispersion regularization. In a mouse-brain benchmark, it achieves 59.16% ARI versus 35.45% for SpatialGlue. Under Gaussian noise injected into ATAC in that dataset, its ARI remains around 0.5 at intensity 1.6, but this test does not establish robustness across other settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.