Blending human knowhow, artificial intelligence aids drug discovery
The pandemic did not create the use of technology in life sciences, but its arrival on the planet has certainly accelerated the use of artificial intelligence, machine learning, and other tech tools. Kenji Tabata (senior vice president and head of discovery intelligence, applied research, and operations at Astellas) recently connected with Outsourcing-Pharma to discuss how the pharma firm is accelerating drug discovery through the use of an innovative platform that blends artificial intelligence, automation, and human brainpower.
OSP: Could you please share your perspective on the evolving use of AI in the life sciences, specifically in drug discovery and development?
KT: Accelerating the drug research and development process—which traditionally takes 10-20 years and has a 1 in 30,000 chance of success—is essential for pharmaceutical companies to more quickly and efficiently meet patient needs. To reduce the cost and time associated with drug discovery, Astellas has been driving forward digital transformation (DX) initiatives throughout our value chain. We believe DX is one of the critical enablers to achieving the goals in our Corporate Strategic Plan 2021.
With data-driven management, we aim to provide innovative technologies, AI, robotics, and platforms that will revolutionize the way solutions are designed, created, tested, and analyzed. By combining the capabilities of artificial intelligence (AI) and robots with the skills and experience of people, we believe we can engage in state-of-the-art drug discovery that enables the development of high-quality drugs in a shorter time.
OSP: What is HITL artificial intelligence—how does it compare with standard AI practices and technology?
KT: In the conventional drug discovery environment, it takes a great deal of time to optimize a compound that readily binds to a disease-causing target molecule.
Our Human-in-the-Loop (HITL) drug discovery platform integrates humans, AI, and robots and revolves around a DMTA cycle—"Design," "Make" the compound, "Test" the effects, and "Analyze." By utilizing AI and robots together with researchers' input, ideas, and comprehensive judgment, we can significantly speed up the drug discovery process. In fact, one specific example of this approach reduced the time it took from hit compound to acquisition of a drug candidate compound by about 70%.
OSP: Please tell us about the “Mahol-A-Ba” technique, and how the Astellas team developed and put it to use.
KT: Our Mahol-A-Ba platform is our newest HITL drug discovery approach, integrating human expertise, AI, and automation robotics for new modalities such as cells and genes. The platform leverages the Maholo LabDroid—a robot that has been used for induced pluripotent stem (iPS) cell drug discovery at the Tsukuba Research Center in Japan. The development of Mahol-A-Ba stemmed from our growing need for new drug discovery research methods to help us achieve our R&D goals.
Astellas conducts R&D into therapeutic drugs for rare diseases. The small patient populations present challenges to sample collection and limit 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.
Mahol-A-Ba overcomes challenges associated with iPS drug discovery, including handling, culture and differentiation, experimentation time limitations, and availability of skilled researchers.
Our Maholo robot 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. Finally, the vast amount of data the robots produce is analyzed by AI and comprehensively judged by our researchers to feed back into the platform for learning and improvement.
Mahol-A-Ba makes 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 of action.
OSP: What are the benefits of the Mahol-A-Ba approach?
KT: Mahol-A-Ba enables us to conduct experiments that are 100 to 1,000 times larger than our previous research in the same amount of time. The full automation of experiments has also created a more efficient workflow and reduced the possibility of human error. 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.
The type of DX we aspire to implement at Astellas is not one where technology replaces our people. Instead, it is one where digital technology works alongside our employees, complementing each other in areas of mutual strength: DX such as AI and robots will be responsible for collecting and analyzing necessary data and engaging in repetitive tasks, and experts in their respective fields will utilize this data to spark ideas that only the human brain is capable of and inspire shifts and directional decisions based on strong volition.
OSP: What should researchers know about the process if they are interested in integrating it into their operations—what skills, equipment, and other new considerations might be involved?
KT: Mahol-A-Ba is an Astellas-specific approach – not an off-the-shelf process – but Astellas’ experiences can inform the creation of a similar approach in other research organizations. In addition to a robot, key components of establishing an approach similar to Astellas’ Mahol-A-Ba are experienced researchers, workflow management and security software, and computer networks.
In terms of expectations for DX talent in drug discovery, a common skill to look for across all small molecule and cellular drug discovery is experimental experience. Many failures and successes through experimentation will be utilized to master Mahol-A-Ba. Astellas HITL researchers are synthesis researchers who are familiar with the AI robot while experimenting with actual synthesis, and Mahol-A-Ba researchers are skilled in iPS cell culture and are users of the AI robot. Mahol-A-Ba researchers should have basic knowledge of robotics and programming about the lab automation processes, and they can work with experts from machine manufacturers to acquire mechanical and control system engineering skills.
Mahol-A-Ba requires workflow management software that integrates the complex lab automation processes, as well as network-attached storage (NAS) servers and network security systems to retrieve and analyze large amounts of data, especially for remote access. In an era when remote research is becoming more and more possible, it will be important to ensure transparency and strengthen information security.
OSP: Do you have anything to add?
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. And 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 regardless of their location.
The name Mahol-A-Ba derives from the ancient Japanese word "Mahoroba," which roughly translates to "utopia" or "spiritual home." In Mahol-A-Ba, 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 treatments to patients as quickly as possible through AI, robot-assisted DX, and the necessary power of people. Mahol-A-Ba is the latest example of how Astellas is driving forward DX initiatives through the concerted efforts of employees across all our business areas.