Astellas DX Strategy Series Vol.2: Drug Discovery Platform Integrating Humans, AI, and Robots
Accelerating the drug research and development process—which has traditionally taken between 10 to 20 years with a 1 in 30,000 chance of success—is essential to meet patient needs more quickly and efficiently. To this end, Astellas has been driving forward digital transformation (DX) initiatives throughout its value chain. Combining the capabilities of AI and robots with the skills and experience of people, the company has created a state-of-the-art drug discovery platform that enables the development of high-quality drugs in a shorter time.
Shortening the time of drug candidate compounds acquisition by approximately 70% in successful cases.
In simple terms, the process of drug discovery involves optimizing a hit compound (a compound that can readily bind to a disease-causing target molecule) to a drug candidate compound—a compound with enhanced suitability as a drug. Historically, this process has been costly and taken a great deal of time. By establishing a "Human-in-the-Loop" drug discovery platform that integrates humans, AI, and robots, Astellas has succeeded in reducing the time it takes from hit compound to acquisition of a drug candidate compound by approximately 70% in successful cases. The key to speeding up the drug discovery process is utilizing AI and robots together with researchers' input, ideas, and comprehensive judgment. Our platform revolves around a DMTA cycle—" Design," "Make" the compound, "Test" the effects, and "Analyze." Based on the result, we can further design a better compound.
Having previously utilized this platform in small molecule drug discovery and witnessing the dramatically improved speed, we wanted to develop the platform for new modalities such as cells and genes. Therefore, we developed Mahol-A-Ba, based on Maholo—a robot that had already been introduced at the Tsukuba Research Center to utilize iPS cells for drug discovery.
[A GUIDE TO]
A Human-in-the-Loop Drug Discovery Platform
Integrating Humans, AI, and Robots
Pushing the limits of iPS cell culture
The background to the development of the Mahol-A-Ba platform was the growing need for new drug discovery research methods. Astellas conducts R&D into therapeutic drugs for rare diseases, but the patient population for some of these target diseases is small, presenting challenges to sample collection and limiting the potential for drug discovery through traditional approaches. Against this backdrop, a solution came to light with the advent of technology that utilizes iPS cells to differentiate cells into target cells.
However, the fact that iPS cells are extremely difficult to handle presented a further challenge. To culture and differentiate the cells, the techniques and sound judgment of the most experienced researchers with subject matter expertise are required. The observational skills of talented researchers are also needed to evaluate whether the cells have differentiated into the target cells and whether the compound has the desired pharmacological effects. There are very few of these researchers worldwide.
Drug discovery through iPS cells faced more hurdles due to the nature of the cells themselves. Even though their ability to change into various cell types is advantageous, they can also alter their state and differentiate into completely different cells due to minor differences in how they are handled by researchers. And even for highly skilled researchers, the possibility of human error remains alongside a limitation on experimentation time.
Astellas developed the Mahol-A-Ba as a solution to these challenges. Our robot, Maholo, conducts cell culture and differentiation in its role as the "Expert Arm," taking over the tasks previously performed by researchers. Our "Expert Eye" robot then evaluates the activity of differentiated cells and their pharmacological effects. The vast amount of data they produce is analyzed by AI and comprehensively judged by the researchers to feed back into the platform for learning and improvement. Mahol-A-Ba has made it possible to reproduce the biology of even rare diseases in vitro, enabling us to verify hypotheses about drug targets, confirm pharmacological effects of drug candidates, and elucidate mechanisms.
“Expert Arm” and “Expert Eye” robots: conducting experiments at 100 to 1,000 times the scale
Daisuke Shimojo, Ph.D. is a senior researcher at Astellas and the handler of Maholo, the "Expert Arm" robot. As a skilled iPS cell researcher, Dr. Shimojo digitalizes his own techniques and reproduces them on Maholo.
He explains, “If you want to seed* cells uniformly in a container for cell culture, you must consider multiple factors. You need to think about a lot of factors. For example, the volume of liquid set in a container and cell suspension to be added to the culture vessel, the number of times and speed of stirring before aspirating the cell suspension into a pipette, the coordinates and speed at which the cell suspension is transferred to the culture vessel.
Other parameters are also necessary to score the cell distribution and determine the optimal behavior.”
He continues by stating, "Once we have discovered the optimal conditions, Maholo is able to seed the same cell distribution repeatedly. We have been able to obtain these optimal operating values in about two weeks to one month. Maholo allows us to continue our experiments over time with a high degree of precision and reproducibility beyond that of a skilled researcher."
*The term "seeding" was originally derived from planting or sowing the seeds of plants. In the pharmaceutical industry, the term refers to the state in which small dots are scattered randomly—as if scattering seeds. In biology, it is used to mean adding cells to a culture vessel.
Working alongside Dr. Shimojo is Astellas' research fellow, Ichiji Namatame, Ph.D. who handles the "Expert Eye" robot.
Dr. Namatame explains how the “Expert Eye” fits into the process. “The "Expert Eye" robot utilizes an imaging system to track the morphological changes of cells cultured and differentiated by Maholo every few hours for about a week. The robot is equipped with AI technology to convert the cell differentiation status and the strength of pharmacological effects into quantitative data. AI is utilized in our image processing technology to provide clearer and more precise results. The robot also has the ability to test a vast number of specimens simultaneously.”
The researcher then uses this acquired data to evaluate the pharmacological effects of the compound, and the knowledge gained is utilized for the next experiment. If any issues occur with the cellular condition, the results are fed back to Dr. Shimojo, who will then optimize the cell preparation process on the Maholo side. We believe the "Expert Eye" robot will enable the discovery of new functional abnormalities and drug targets that have been previously undetected, leading to the creation of new drug discovery themes."
The two researchers comment on the fact that "Mahol-A-Ba enables us to conduct experiments on a scale of 100 to 1,000 times larger in the same amount of time as our previous research. The full automation of experiments has also created a more efficient workflow. Researchers no longer need to do the routine work between experiments, such as changing plates, etc., which leaves more time for data analysis, future experiment planning, and the development of mid- to long-term strategies and plans.
Because researchers can operate Mahol-A-Ba remotely, Astellas is currently building an environment that will allow researchers worldwide to apply their ideas to drug discovery and research. This project is expected to be operational by the mid-2020s.
Accelerating drug discovery research with humans, AI, robots to meet patient needs
The use of AI and robotics is a new approach to accelerate the speed of R&D, reduce costs, and improve the quality of drugs, enabling us to do things that were previously impossible with human power alone. We will globally utilize these technologies in small molecules and antibodies, as well as new modalities such as cells and genes, to realize agile drug discovery research.
The name "Mahol-A-Ba" derives from the ancient Japanese word "Mahoroba," which roughly translates as a "utopia" or "spiritual home." Here, the "A" represents "Astellas," and the "Ba" refers to "place." The overarching meaning is an optimal place for Astellas to utilize Maholo, a concept that aligns with our commitment to deliver high-quality drugs to patients as quickly as possible through AI, robot-assisted DX, and the necessary power of people.
Astellas is continuously driving forward DX initiatives through the concerted efforts of employees in all business areas. Among our wide range of projects, we will introduce a series of efforts that represent and clearly highlight our commitment.
Astellas DX Strategy Series
Vol.1 Implementing DX to Create and Maximize VALUE for PatientsRead more
Vol.3 A New Approach to Clinical Trials Powered by Patient Voice and TechnologyRead more
Vol.4 Innovation in Manufacturing—An Original Data Mining System to Shape the Future of Pharmaceutical ProductionRead more