Novartis NYSE: NVS is applying artificial intelligence across drug research and clinical development, with executives reporting faster trial enrollment and drug candidate selection while cautioning that evidence of improved clinical success will take longer to emerge.
At an investor event, company leaders described how AI is being used to identify drug targets, design molecules, plan clinical trials and analyze safety data. They also stressed that researchers must validate AI-generated findings in the laboratory and, ultimately, in clinical trials.
Faster trials and drug discovery
Max Lawson, head of AI and process innovation at Novartis, said AI-enabled site selection accelerated enrollment by six months in the company’s V1P effort. He also said 90% of the content in clinical study reports is now AI-assisted, reducing authoring and review time by 25%.
Lawson said the company’s Intelligent Decision System can run thousands of simulations of a potential study in minutes. The simulations were 50% more accurate at predicting enrollment timelines than the prior planning process, he said.
Fiona Marshall, president of biomedical research, said the average time from starting a research program to selecting a drug candidate has fallen from three to four years to less than 2.5 years. Much of that gain came from AI-assisted generative chemistry, she said. Some programs driven primarily by AI have reached a one-year cycle time, though the company is still collecting comparative data.
Marshall said eight or nine molecules developed through generative chemistry and predictive safety processes are undergoing dose-range-finding toxicology work. Data on whether the approach reduces safety-related attrition could be available within a few years, she said.
Data and partnerships
Christian Diehl, Novartis’ chief data and digital officer, said the company has generated more than 150 petabytes of research data over the years. He said Novartis has spent roughly a decade organizing and connecting data through its Data42 initiative, allowing researchers to draw on information across disease areas.
Access to clinical data for secondary analysis requires a stated scientific purpose and approval, Diehl said. Marshall said researchers have used Data42 to compare safety findings with past experience when deciding whether to stop or continue programs.
Novartis also works with outside companies across different stages of research. Marshall cited Isomorphic Labs for protein structure and drug design, Relation for generating human tissue data, Chai Discovery for predictive software, and Deciphex for digitizing slides used in safety research.
Diehl said Novartis uses proprietary external models, open-source tools and models developed internally. The company generally seeks to bring external models behind its firewall for training, with models fine-tuned on Novartis data remaining with Novartis, he said.
Limits and the path to validation
Marshall said AI approaches have helped researchers find potentially relevant binding sites on targets where conventional methods had failed. In neurodegeneration, she said, three novel targets identified through a process combining foundation models and multiple data sets have advanced into later-stage programs.
She cautioned, however, that AI outputs need testing in relevant cell-based or animal models. “A lot of the things that come out just do not translate into even the cell models, let alone into the clinic,” Marshall said.
Diehl said Novartis is working to predict potential toxicities earlier and simulate trials in different patient subgroups. Such approaches are intended to improve the probability of success, but new targets must still be tested clinically, he said.
Marshall also warned against underestimating the difficulty of turning molecules into medicines, particularly in diseases where little data exists. Understanding human biology remains a challenge, she said, “even in the context of AI.”
About Novartis (NYSE:NVS)
Novartis AG is a Swiss pharmaceutical company focused on discovering, developing, manufacturing and commercializing innovative medicines. Its research and products address conditions in areas including oncology, immunology, neuroscience, and cardiovascular, renal and metabolic health. The company's medicines include treatments such as Kisqali for certain breast cancers, Cosentyx for inflammatory diseases, Entresto for heart failure and Kesimpta for multiple sclerosis. Its portfolio also includes radioligand therapies and other specialized treatments.
This instant news alert was generated by narrative science technology and financial data from MarketBeat in order to provide readers with the fastest reporting and unbiased coverage. Please send any questions or comments about this story to contact@marketbeat.com.
Before you consider Novartis, you'll want to hear this.
MarketBeat keeps track of Wall Street's top-rated and best performing research analysts and the stocks they recommend to their clients on a daily basis. MarketBeat has identified the five stocks that top analysts are quietly whispering to their clients to buy now before the broader market catches on... and Novartis wasn't on the list.
While Novartis currently has a Hold rating among analysts, top-rated analysts believe these five stocks are better buys.
View The Five Stocks Here
Discover the next wave of investment opportunities with our report, 7 Stocks That Will Be Magnificent in 2026. Explore companies poised to replicate the growth, innovation, and value creation of the tech giants dominating today's markets.
Get This Free Report
Continue following MarketBeat
Add MarketBeat as your preferred source on Google to see our latest stories in your feed.