MIT FINGERS-7B: First Multi-Omics AI Model for Alzheimer’s Prevention
Summary
MIT released FINGERS-7B, a 7-billion-parameter multi-omics foundation model trained on data from 30,000 individuals to predict Alzheimer's risk years in advance. The model is accessible via the AD Workbench and is accompanied by a research paper on OpenReview.
Similar Articles
Chinese brain-reading AI model may help predict depression risk 4 years in advance
Chinese researchers have developed an AI model that uses brain scan data to predict the risk of depression up to four years in advance, potentially enabling earlier interventions.
The biggest AI breakthrough in medicine & drug discovery
MAML is a novel multi-modal AI model that unifies understanding of chemistry, genetics, and proteins, outperforming specialized models on 11 drug discovery benchmarks, promising to accelerate pharmaceutical research and improve success rates.
Leakage-Controlled Multimodal Learning for Diagnosis and Progression Prediction in Alzheimer's Disease Research
该论文提出一种泄漏可控的多模态多任务学习框架，结合SFCN MRI编码器、因果临床Transformer和ODE-GRU动力学，用于阿尔茨海默病诊断与病程进展预测，在ADNI、OASIS-2、MIRIAD数据集上取得内部诊断AUROC 0.935、混合AUROC 0.951，并在OASIS-3上完成外部验证。
AlphaGenome: AI for better understanding the genome
DeepMind introduces AlphaGenome, an AI model that predicts how DNA sequence variants impact gene regulation and biological processes across diverse cell types and tissues. The model processes up to 1 million base pairs and is available via API for non-commercial research, with the full paper published in Nature.
@GoogleDeepMind: Together with scientists around the world, our models and tools are helping make disease more detectable, treatable, an…
Google DeepMind highlights how its AI models and tools—including AlphaFold and AlphaGenome Atlas—are helping scientists worldwide make diseases more detectable, treatable, and preventable, from drug repurposing to mapping genetic variants linked to aging.