Personalized medicine is moving from concept to clinical reality as artificial intelligence and robotics automate the painstaking work of growing iPS cells and designing treatments for individual patients. Rather than relying on a doctor's experience or one-size-fits-all drug protocols, researchers are now using AI to analyze patient data, predict disease risk, and optimize the conditions for growing custom cells that could restore function lost to disease or injury.

Why Does Personalized Medicine Matter for Drug Discovery?

The fundamental problem driving this shift is simple but profound: the same diagnosis produces wildly different outcomes across patients. One person responds well to a medication while another sees no benefit. Some patients with early-stage cancer experience recurrence within years; others diagnosed with terminal cancer survive decades without relapse. This variation has long puzzled the medical field and prompted researchers to ask whether treatment should really depend on a doctor's intuition rather than data.

Professor Kawakami Eiryo of Chiba University has spent his career tackling this question through a data-driven lens. His work focuses on disease stratification, using large-scale clinical data combined with AI to predict disease onset and prognosis. The vision is ambitious: a form of medicine that allows people to live long, stay healthy, and then die without prolonged illness, potentially achievable by around 2050.

"I believe medicine that enables people to live long, stay healthy, and then die without prolonged illness is something that we can realistically achieve. Five or ten years won't be enough, but I hope that we will see this come to fruition by around 2050," said Kawakami.

Professor Kawakami Eiryo, Institute for Advanced Academic Research at Chiba University

How Are Robots and AI Transforming Cell Cultivation?

One of the biggest bottlenecks in regenerative medicine has always been the cultivation of high-quality cells at scale. Historically, growing iPS cells, which are ordinary cells reprogrammed to become any cell type in the body, relied heavily on the skill and experience of individual researchers. Conditions had to be adjusted by hand, making it difficult to produce consistent results or scale up production.

In June 2022, researchers at Epistra, a Tokyo-based AI startup focused on life sciences, demonstrated a breakthrough: an automated system that uses AI and robotics to optimize cell cultivation conditions without human trial-and-error. The system combines a robot called Mahoro with AI analysis software called Epistra Accelerate. The AI determines optimal conditions such as temperature and nutrient delivery, the robot executes those instructions, and the results feed back into the AI to determine the next set of conditions to test. By repeating this cycle, researchers achieved efficient production of high-quality cells.

This automation addresses a critical challenge in regenerative medicine: variability. Cell quality depends on which genes, proteins, and other elements are introduced, in what amounts, and in what sequence. What once required significant time and effort to identify through manual experimentation can now be determined more efficiently with AI. Robots can accurately repeat the same movements over and over, something humans cannot sustain reliably over long periods, especially for delicate cell procedures.

Steps to Integrate AI Into Drug Development Workflows

• Establish baseline data collection: Gather comprehensive clinical and biospecimen data from patient populations to train AI models on disease patterns and treatment responses specific to your research focus.
• Deploy AI-driven optimization tools: Implement machine learning systems to automatically test and refine conditions for cell cultivation, drug candidate screening, or other repetitive optimization tasks rather than relying on manual experimentation.
• Combine organoid and AI image analysis: Grow three-dimensional tissue models from iPS cells and use AI-powered image analysis alongside omics data to identify disease mechanisms and discover drugs suited to specific patient populations.

What Role Do Organoids Play in Personalized Drug Discovery?

Beyond cell cultivation, researchers are advancing the use of organoids, which are miniature three-dimensional tissue structures just a few millimeters in diameter that replicate the structure and function of real organs. Because organoids can reproduce human cell characteristics outside the body, they serve as disease models for studying how illnesses develop and progress.

A concrete example demonstrates the power of this approach. A research team at the Institute of Science Tokyo used iPS cells to create kidney organoids lacking the gene responsible for nephronophthisis, a rare genetic disease designated as intractable in Japan. By comparing these organoids with normal kidney cells, researchers discovered an abnormality in molecules involved in fibrosis, a process where tissues become stiff. They then identified a medicine that prevents this abnormality, opening a path to new treatments.

The real innovation emerges when organoids are combined with AI. Researchers are integrating AI image analysis with omics data analysis, which comprehensively examines genes, proteins, and other molecular components. This combination accelerates both drug discovery and the development of personalized medicine approaches tailored to individual patient physiology.

How Is AI Replacing Animal Testing in Drug Development?

Beyond personalized medicine, AI is playing a crucial role in a broader shift away from animal testing in pharmaceutical research. In November 2025, the UK government published a long-awaited strategy to replace animal use in research, pointing to advances in AI, genomics, organoids, and three-dimensional cell systems as technologies that could end animal testing "in all but exceptional circumstances".

The strategy acknowledges that phasing out animal testing requires reliable alternatives with the same level of safety assurance for human exposure. Several categories of animal tests are already being replaced. For instance, the rabbit pyrogen test, which involved injecting solutions into rabbits to check for fever-causing contaminants in vaccines and blood products, is being replaced by a monocyte activation test that uses human immune cells instead.

In pharmacokinetic studies, which investigate how drugs are absorbed, distributed, and eliminated in the body, AI prediction tools using molecular structure data may provide viable alternatives and at least reduce the number of animal experiments needed. The hope is that combining in vitro human tissue cultures, organoids, and organ-on-a-chip models with AI could significantly diminish reliance on animals.

AI models are already being deployed in drug development to mine datasets for novel targets and drug candidates. One notable example is INS018_055, an AI-designed drug candidate now being tested for idiopathic pulmonary fibrosis, a serious lung disease. The use of AI in candidate identification has enabled faster progression through development stages.

The transformation from manual craft to reproducible technology represents a fundamental shift in how medicine is developed. By combining AI optimization, robotics, organoid models, and personalized patient data, researchers are building a future where treatments are tailored to individual biology rather than applied broadly to populations. This convergence of technologies promises not only faster drug discovery but also more effective therapies with fewer failures and less reliance on animal testing.