Small-cohort GWAS discovery with AI over massive functional genomics knowledge graph.

Genome-wide association studies (GWASs) have identified tens of thousands of disease associated variants and provided critical insights into developing effective treatments. However, limited sample sizes have hindered the discovery of variants for uncommon and rare diseases. Here, we introduce KGWAS, a novel geometric deep learning method that leverages a massive functional knowledge graph across variants and genes to improve detection power in small-cohort GWASs significantly.

Comparison of High n-3 PUFA Levels and Cyclic Heat Stress Effects on Carcass Characteristics, Meat Quality, and Oxidative Stability of Breast Meat of Broilers Fed Low- and High-Antioxidant Diets.

This study investigated the individual and combined effects of a high dietary n-3 PUFA intake and cyclic heat stress (HS) on the carcass characteristics, meat quality, and oxidative stability of broiler breast meat and the potential of antioxidant supplementation (vitamins E, C, and selenium) to mitigate these effects. A total of 192 one-day-old male Ross 308 broilers were randomly assigned to 24 pens within two controlled environment chambers and fed with the following diets: a basal diet low in antioxidants according to NRC recommendations (NRC group), a basal diet according to Aviagen recommendations additionally supplemented with 200 IU/kg vitamin E, 250 mg/kg vitamin C, and 0.15 mg/kg selenium (HAOX group), and these two diets further supplemented with 5% linseed oil (NRC N-3 and HAOX N-3 groups).

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities.

The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells.

A foundation model for clinician-centered drug repurposing.

Drug repurposing-identifying new therapeutic uses for approved drugs-is often a serendipitous and opportunistic endeavour to expand the use of drugs for new diseases. The clinical utility of drug-repurposing artificial intelligence (AI) models remains limited because these models focus narrowly on diseases for which some drugs already exist. Here we introduce TxGNN, a graph foundation model for zero-shot drug repurposing, identifying therapeutic candidates even for diseases with limited treatment options or no existing drugs.