![\"A](\"https:\/\/www.europesays.com\/us\/wp-content\/uploads\/2025\/10\/d41586-025-03441-6_51605464.jpg\"\/)
<\/p>\n <\/p>\n
An artificial-intelligence method that incorporates gene-expression data could help to speed up drug discovery.Credit: Qilai Shen\/Bloomberg\/Getty<\/p>\n
An artificial intelligence (AI) model trained on complex data from human cells could provide a shortcut in the race to develop new drugs1<\/a>.<\/p>\n The approach, published on 23 October in Science, builds on a trend that is sweeping the field of drug discovery: the use of AI<\/a> to speed up the tedious process of trawling through massive collections of chemical compounds in search of those that could become the next big therapy.<\/p>\n \u201cIt\u2019s a powerful blueprint for the future,\u201d says Hongkui Deng, a cell biologist at Peking University in Beijing, who was not involved in the work. \u201cIt creates a \u2018smart\u2019 screening system that learns from its own experiments.\u201d<\/p>\n Tedious method<\/p>\n For decades, researchers have searched for drugs by working their way through large chemical libraries, testing each compound\u2019s effect on cells that are grown in the laboratory. The approach has had success, identifying drugs that kill cancer cells, for example. <\/p>\n Increasingly, researchers are dreaming of more complex screening methods that could harness the past decade\u2019s explosion in genomic data collected from individual cells<\/a>. Such methods could, in theory, evaluate how compounds perturb entire networks of gene activity \u2014 a test that could open new avenues for drug discovery.<\/p>\n But, researchers typically screen tens of thousands of compounds or more for drug discovery, says Alex Shalek, a biomedical engineer at the Massachusetts Institute of Technology in Cambridge. And it would be too expensive and laborious to integrate such large screens with complex assays, he says.<\/p>\n
![\"\"](\"https:\/\/www.europesays.com\/us\/wp-content\/uploads\/2025\/10\/d41586-025-03441-6_18291218.jpg\"\/)
<\/p>\n