The growing role of multi-omics within drug discovery Harnessing multi-omics and AI, researchers are transforming drug discovery by revealing disease mechanisms, pinpointing therapeutic targets, and speeding up development. Written byBree Foster, PhD

The growing role of multi-omics within drug discovery Harnessing multi-omics and AI, researchers are transforming drug discovery by revealing disease mechanisms, pinpointing therapeutic targets, and speeding up development. Written byBree Foster, PhD https://www.drugdiscoverynews.com/the-growing-role-of-multi-omics-within-drug-discovery-17097?utm_campaign=DDN_Newsletter_Dose&utm_medium=email&_hsenc=p2ANqtz--eZkE2RFdsdMb8DN-kmWB7uVa8nUXSe_FENTgeLw6eyAzhg2Iv9oKOCJcXyI-8gDfb-AfL_hKpZGbeNQRdhcBe6WJn0A&_hsmi=434032591&utm_content=434032591&utm_source=hs_email Drug discovery has long been a high-risk, high-reward endeavor. Developing a new therapeutic from initial concept to market approval can take over a decade and cost more than $2 billion on average. Despite these staggering investments, the failure rate remains high, with many drugs faltering in late-stage clinical trials due to unforeseen toxicity, lack of efficacy, or poor patient stratification. Traditional approaches often focus on targeting a single molecule or pathway, an approach increasingly recognized as insufficient for tackling complex diseases such as cancer, neurodegeneration, and autoimmune disorders. Can better training data fix AI antibody design? The field has invested heavily in building better models for antibody discovery. The structural interaction data those models are trained on has not kept pace — and that shortfall is now a defining constraint on what AI can reliably do. Written byAndrea Corona https://www.drugdiscoverynews.com/can-better-training-data-fix-ai-antibody-design-17211?utm_campaign=DDN_Newsletter_Dose&utm_medium=email&_hsenc=p2ANqtz-9IHi0YXjvamui5CmnXpL0g-NVgV9akzvA8Ls0j41AjlkP-O-L47wYGyJc68CPWAD6TcLZFCq8ES_RyJ048aEny6RQKcg&_hsmi=434032591&utm_content=434032591&utm_source=hs_email The last several years of progress in protein artificial intelligence (AI) have been undeniably impactful. AlphaFold's demonstration that protein folding could be predicted with near-experimental accuracy reset expectations across structural biology, and the models that followed, for protein design, interaction prediction, and sequence generation, have moved antibody discovery into a new computational era.