New OGM Neural Network Architecture for Disease Risk Prediction
anshulkundaje · x · 2026-08-06
A new preprint introduces the Omnigenic Model (OGM), a neural network architecture designed specifically for human genetics.
The model leverages biological system structure to aggregate genetic variations for disease risk prediction. Unlike traditional black-box models, OGM aims to provide interpretability, helping researchers understand the complex associations between genes and diseases.
Related event: Neural Network Architecture OGM Proposed for Human Disease Risk Prediction(2 posts)→
More from Research
- MatrAIx: Harvard, MIT & Stanford Simulate the World with 8.3B Persona Agents — HennyJieCC · 2026-08-06
- IBM Introduces Cross-Encoder Query Expansion to Boost Hybrid Search Recall — burkov · 2026-08-06
- 100k Hours of Real-World Data Yields Only 57% Success in Robotics — eigenron · 2026-08-06
- Chunky Post-Training: Frontier Models Show Generalization Failures — basedjensen · 2026-08-06
- Harvard, MIT, Stanford Launch MatrAIx: 8.3B Persona Agents for AI Evaluation — BrihiJ · 2026-08-06
- Dongfang Starlink Launches AI Hyperspectral Satellites, Plans 2M Lunar Robots for Data Center — 新智元 · 2026-08-06