AI 2.0 with federated learning: “To help application developers industrialise their AI technology and expand the application’s business benefit, AI must be trained and validated on data that resides outside the possession of their group, institution and geography.In order to leverage the world’s largest data sources, multimodal AI will bring us to that new frontier in discovering disease pathways, as well as personalising the treatment and prognosis of patients.” Multiple sources of health data need to be used, whether it is to discover drugs or treat patients. Multimodal AI: “There are over ten thousand diseases without a therapy.The breakthroughs of AlphaFold and RoseTTAFold that created a thousand-fold explosion of known protein structures, and AI that can generate a thousand more potential chemical compounds has increased the opportunity to discover drugs by a million times. AI accelerates million-times drug discovery: “ Molecular simulations help to model target and drug interactions completely in silico.
NVIDIA’s vice president of healthcare Kimberly Powell shared with Pharmaceutical Technology the company’s top three predictions for supercomputing in pharma: NVIDIA has partnered up with GSK and its AI team to unlock vast quantities of genetic and clinical data and help the company to develop more effective drugs and vaccines, faster. GSK’s own research has a steadfast focus on genetically validated targets, which are twice as likely to become approved therapies and now make up more than 70% of the company’s drugs pipeline.
NVIDIA is collaborating with AstraZeneca to build a transformer-based generative AI model for chemical structures, which will allow researchers to leverage massive datasets using self-supervised training methods and enable faster drug discovery. The Cambridge-1 supercomputer has the potential to significantly accelerate and optimise every stage of drug research. Along with the launch of Cambridge-1, NVIDIA also announced a series of collaborations with the pharma behemoths AstraZeneca and GlaxoSmithKline, and institutions like Guy’s and St Thomas’ NHS Foundation Trust, King’s College London and Oxford Nanopore Technologies. This year, US tech company NVIDIA launched Cambridge-1, the UK’s most powerful supercomputer, to help British healthcare researchers solve some of the industry’s most urgent healthcare challenges. It makes sense, then, that researchers are looking to apply supercomputing to the exhaustive process of drug discovery and design. Supercomputers are vastly superior to general-purpose computers in terms of speed and performance, and are particularly valuable when it comes to performing scientific and data-intensive tasks.
0 kommentar(er)
