DR-GEM: Self-Supervised Framework Fixes Dimensionality Reduction Bias Against Rare Cell Types
anshulkundaje · x · 2026-09-29
A Stanford team published DR-GEM in Nature Communications, a self-supervised dimensionality reduction and clustering framework for single-cell and spatial transcriptomics. They show existing methods equate abundance with importance, fitting oversampled classes and missing rare cell types. DR-GEM uses distributionally robust, group-aware consensus learning to refocus on underrepresented but important regions, with principles extending to unevenly sampled settings like rare diseases and ancestry cohorts.
More from Research
- Google Research unveils multi-agent 'AI video co-director' for consistent long-form video generation — rseroter · 2026-09-29
- BLUE from Google internship lands NeurIPS: LLM-written user profiles boost recommendations — shangbinfeng · 2026-09-29
- Collatz twist: Krasikov-Lagarias-style X^0.84 bounds apply to any root, and equally to 3x-1 — AlexKontorovich · 2026-09-29
- Emergence debunked? Researcher argues emergent LLM abilities are labels in your imagination — gerardsans · 2026-09-29
- MHCflurry 2.3 ships with multi-GPU speedups and first new model weights in ages — iskander · 2026-09-29
- 2,000+ navigation tasks across 133 environments test how far LLMs are from zero-shot robot control — PaulYacoubian · 2026-09-29