{"id":7162,"date":"2026-07-23T13:00:12","date_gmt":"2026-07-23T13:00:12","guid":{"rendered":"https:\/\/hoo.central12.com\/portal\/2026\/07\/23\/how-ai-helps-scientists-design-the-next-generation-of-medicines\/"},"modified":"2026-07-23T13:00:12","modified_gmt":"2026-07-23T13:00:12","slug":"how-ai-helps-scientists-design-the-next-generation-of-medicines","status":"publish","type":"post","link":"https:\/\/hoo.central12.com\/portal\/2026\/07\/23\/how-ai-helps-scientists-design-the-next-generation-of-medicines\/","title":{"rendered":"How AI helps scientists design the next generation of medicines"},"content":{"rendered":"

Designing and developing a new medicine<\/a> is an expensive, failure-prone scientific challenge. <\/a><\/a>A new drug can take many years to develop, at the cost of a significant investment. And even then, most possible candidates never reach the patient. For biologic medicines, therapies made from engineered proteins rather than synthetic chemistry (which are often used to treat conditions across most major acute and chronic diseases), the complexity is even greater.<\/p>\n

Scientists explore vast quantities of possible molecules, looking for the rare few that will bind to the right target, remain stable in the human body, and be manufacturable at scale. Today, AI is speeding up these processes and has quickly become a core part of the infrastructure in pharmaceutical R&D.<\/p>\n

\"\"<\/figure>\n

AI-assisted design is a growing part of how biologic drug candidates are developed, and companies like AstraZeneca are actively building its engineering teams to push this further. \u201cEverything we do, whether it\u2019s design, make, test, or analyze, is now computationally enhanced,\u201d says Puja Sapra, senior vice president and head of R&D biologics engineering and oncology targeted discovery at AstraZeneca. \u201cThe cycle times are getting shorter while productivity and innovation increase.\u201d<\/p>\n

Sapra explains that AstraZeneca\u2019s approach follows a build-measure-learn loop. AI generates or prioritizes candidate molecules computationally, predicting which designs are most likely to succeed. Scientists then focus lab resources only on the top-ranked candidates. This leads to a tighter feedback cycle with fewer dead ends, faster iteration, and the ability to go after disease targets that were previously considered untreatable by medicine. Because the number of possible molecular combinations far exceeds what any human team can systematically explore, using AI to narrow and refine the options for testing has become a major focus in biologics drug design.<\/p>\n

Navigating complex drug design problems<\/strong><\/h3>\n

Beyond accelerating timelines, AI is also being applied to the discovery of entirely new classes of medicines. Traditional biologics typically target one disease pathway. The next generation of drugs can hit multiple targets simultaneously or precisely deliver therapeutic payloads to specific cells. Achieving this requires optimization across many variables at once. Looking ahead AI-driven models could help design these increasingly complex, multi-specific biologics, explains Puja Sapra. \u201cFor example,\u201d she continues, \u201csuch models could help identify which two or three targets to prioritize based on the underlying biology, then optimize across multiple parameters to balance a molecule\u2019s potency, stability, manufacturability, and safety.\u201d \u201cDrugging the undruggable is becoming a reality,\u201d Sapra says. \u201cThese technologies will eventually enable us to develop medicines against targets once thought impossible to reach. The potential for benefit to patients is remarkable.\u201d<\/p>\n

The data moat<\/strong><\/h3>\n

McKinsey estimates<\/a> that generative AI, combined with other computational tools, could cut drug discovery timelines by as much as 50%. But every AI model is only as good as its training data. In drug discovery, that means ample quantities of high-quality biological data. Experiments can provide a rich source of such data. Whether they succeed or fail, each experiment generates a signal about what does and does not work.<\/p>\n

\u201cData is our differentiator,\u201d says Sapra, explaining how the company\u2019s datasets are proprietary and multimodal and include molecular structures, binding measurements, safety profiles, and manufacturing outcomes. \u201cWe\u2019ve built an intentionally diverse portfolio across multiple disease areas and drug types. All of that data empowers us to fine-tune frontier AI models with richer, more representative training sets.\u201d She continues, \u201cFurther, we have invested in deep screening technologies to generate additional datasets required in volume to constantly refine and validate our models.\u201d<\/p>\n

Building an autonomous discovery engine<\/strong><\/h3>\n

To bring all of that data together in one place, AstraZeneca is building what it calls a \u201clab of the future\u201d facility in Kendall Square, Cambridge, Massachusetts where AI and robotic automation will be able to form a continuous, closed-loop discovery system. \u201cWhere a self-driving car uses sensors and models to navigate its environment, this system uses AI to make predictions, robotic systems to execute experiments, and instruments to generate data,\u201d explains Sapra. That data feeds directly back into the models, accelerating each subsequent cycle.<\/p>\n

\u201cThroughout, scientists will remain central to the process, providing the oversight, judgement, and strategic direction that ensure outputs are explainable, tolerable, and directed toward potential patient benefit,\u201d she adds.<\/p>\n

Eventually, automated high-throughput systems will be able to make and evaluate thousands of molecular interactions on a weekly basis. \u201cThis will generate AI-ready data at a scale that traditional workflows cannot match,\u201d Sapra says. \u201cRobotic sample handling, automated quality checks, and integrated data pipelines also have the potential to help accelerate early drug development timelines significantly.\u201d<\/p>\n

The next frontier: Generating medicines from scratch<\/strong><\/h3>\n

Ultimately, Sapra says, the end-state vision for AI in biologic drug discovery is what the field calls \u201cde novo\u201d design. For this, the goal is for AI to generate entirely new protein sequences that precisely fit the desired drug properties. This includes designing the structure, predicting safety, how it will behave in the body and how to make it manufacturable.<\/p>\n

\u201cThe field is making great progress toward a completely AI-generated biologic, designed from scratch all the way to a clinical candidate,\u201d Sapra says. \u201cAs we continue to leverage frontier models and fine-tune them with the right datasets, we bring ourselves closer to this reality. I believe it will come. It\u2019s a matter of time.\u201d<\/p>\n

Several key elements are needed to reach this point, however. First is richer and more standardized training data across the industry. Second, robust evaluation benchmarks for AI-generated candidates. And third, teams that know how to work at the intersection of machine learning and biology. Of all the prerequisites, however, safety prediction may be the most consequential, and perhaps the least discussed, Sapra says.<\/p>\n

\u201cOne of the hardest problems in de novo design is predicting whether a computationally generated molecule will be safe in the human body,\u201d Sapra explains. AstraZeneca is tackling this with what amounts to virtual clinical trials. These are advanced cell systems and micro-scale organ models that function as physical testbeds, paired with AI that learns from their outputs.<\/p>\n

 \u201cThese systems have the potential to generate enhanced biological signals without traditional testing bottlenecks, and they’re a critical missing piece in closing the loop between AI-generated designs and clinical-ready candidates,\u201d Sapra adds.<\/p>\n

A shift currently underway is the move toward agentic AI systems that can simultaneously generate molecule candidates and predict how efficacious and safe they are likely to be. These autonomous workflows can connect disease-level insights directly to molecule design, bridging what were previously separate data silos. \u201cThe complexity of the biology goes hand-in-hand with the design of the molecule,\u201d summarizes Sapra.<\/strong><\/p>\n

Human talent unlocks AI potential<\/strong><\/strong><\/h3>\n

The transformation underway in biologics is not just about technology. \u201cWith more autonomous systems, human oversight remains at the heart of this approach\u2014ensuring explainable and ethical AI for the benefit of patients,\u201d says Sapra.<\/p>\n

For scientists, working with AI is a collaborative process. \u201cScientists will work hand-in-hand with these model systems,\u201d she says. \u201cThere will be a world where models will design molecules, then scientists will work with the systems to test those molecules and put all that data together.\u201d Through this process of human checks, balances, and judgement calls, the models will evolve and constantly improve, ultimately with potential to benefit patients.<\/p>\n

For engineers, designing and building effective systems ready for human-AI collaboration will mean ensuring high levels of model transparency and explainability. According to Sapra, AstraZeneca\u2019s engineering teams include data scientists, automation specialists, and AI engineers, who are developing systems that act as \u201cthinking partners\u201d rather than black boxes. \u201cEngineers are designing systems that generate, validate, and learn at speed. And the problems are genuinely hard: Multimodal data fusion, closed-loop optimization, uncertainty quantification, and interpretability at the point of clinical decision-making,\u201d she adds.<\/p>\n

In taking on such technically demanding challenges, engineers and scientists have the opportunity to contribute to the research and development of potentially life-changing treatments for many diseases, says Sapra. \u201cThe biologic medicines we can develop today, and those we\u2019ll design tomorrow, depend on combining world-class AI and engineering talent with deep scientific expertise.\u201d<\/p>\n<\/p>\n

This article has been initiated and funded by AstraZeneca.  Z4-85058, July 2026.<\/em><\/p>\n

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review\u2019s editorial staff. It was researched, designed, and written by human writers, editors, analysts, and illustrators. This includes the writing of surveys and collection of data for surveys. AI tools that may have been used were limited to secondary production processes that passed thorough human review.<\/em><\/p><\/p>\n","protected":false},"excerpt":{"rendered":"

Designing and developing a new medicine is an expensive, failure-prone scientific challenge. A new drug can take many years to develop, at the cost of a significant investment. And even then, most possible candidates never reach the patient. For biologic medicines, therapies made from engineered proteins rather than synthetic chemistry […]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[68],"tags":[67],"class_list":["post-7162","post","type-post","status-publish","format-standard","hentry","category-mit-feed","tag-mit-tech"],"_links":{"self":[{"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/posts\/7162","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/comments?post=7162"}],"version-history":[{"count":0,"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/posts\/7162\/revisions"}],"wp:attachment":[{"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/media?parent=7162"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/categories?post=7162"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hoo.central12.com\/portal\/wp-json\/wp\/v2\/tags?post=7162"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}