UAH collaboration creates self-learning AI platform to discover new drugs
Newswise – HUNTSVILLE, Alabama. (May 4, 2022) – A cross-university collaboration at the University of Alabama at Huntsville (UAH) has developed a self-learning artificial intelligence (AI) platform that uses big data analytics to discover how new pharmaceutical drugs and various molecules function inside living cells.
Cutting-edge research at UAH, part of the University of Alabama system, involves molecular biophysicist Dr. Jerome Baudry, Ms. Pei-Ling Chan Chair of the Department of Biological Sciences and director of the laboratory Baudry; Dr. Vineetha Menon, assistant professor in the Department of Computer Science and director of the Big Data Analytics Lab; computer science PhD student Shivangi Gupta, lead author of a research paper; and the doctoral student Armin Ahmadi, who conducts his doctoral research at the Baudry Lab.
Supported by UAH’s Office of Technology Commercialization, scientists develop their intellectual property research for industrial applications in drug discovery.
“It is a strong and integrated collaboration and we all bring our own expertise, but the main novelty of this work concerns machine learning and data mining, and the leader of the whole project is the Dr. Menon, who is an internationally recognized expert in these fields,” explains Dr. Baudry.
Dr. Baudry’s role is to interpret computational results in terms of biology and drug discovery potential. Gupta is involved in AI and machine learning algorithmic developments and analysis of the results. Ahmadi works on translating machine learning results into drug discovery applications.
“We are moving away from analytical problem solving like we used to do in graduate school by solving equations and deducing what should happen,” says Dr. Baudry.
Instead, researchers are increasingly using real-world data to find the mathematical rules that underlie observations, he says.
“From a philosophical point of view, this is not something entirely new; observing nature and deducing general rules from those observations has always been part of science. But nowadays, the sheer quantity and complexity of what is observed would make it impossible for a scientist to analyze the phenomena of interest, even if they spent their life on one problem.
Only computers have the power to do such monumental analysis, but they require complex mathematical approaches. These are not plug-and-play approaches, but rather mathematical analyzes that must be tailored to individual problems.
“Add in the inherent complexity of biological events, and you have a massive amount of extremely complex data that we make sense of,” says Dr. Baudry.
The use of artificial intelligence and machine learning helps researchers more effectively understand the biological significance of findings.
“For life to occur, molecules in cells must interact with each other in an endless dance that forms and breaks interactions between chemicals,” says Dr. Baudry. “It is the dynamics and the nature of these interactions that interest us, from a biophysical point of view. What physical properties make two molecules capable of interacting with each other?
Because the same principles that guide how molecules interact with each other in a living cell are also responsible for how pharmaceuticals work in the body, when researchers understand this molecular dance between chemicals, they can design new pharmaceuticals.
“They will ‘enter the cell dance’, and we can develop them much cheaper and much faster than what the pharmaceutical industry is currently able to do,” says Dr. Baudry.
The cooperative fusion of computing and biological sciences is absolutely essential to accelerate discoveries in molecular biophysics and data science applications, especially to combat any future pandemic scenarios, says Dr. Menon.
“Contemporary research is interdisciplinary and collaborative,” she says. “You don’t really have individuals like Einstein or Curie or Pasteur anymore, who worked alone in their labs in their ivory towers, but you have highly specialized teams that have to come together to do research and power the industrial applications of tomorrow. “
These specialized scientific teams attract funds, create knowledge and transform this knowledge into industrial applications, explains Dr. Menon.
“The success of contemporary research is a direct product of how these teams work together. As brilliant as the individual labs are, they must become better than the sum of the parts, like an orchestra. The two UAH labs have been working together for a few years, and the recent milestone reported in the research paper shows that they have co-evolved to be highly effective as a team, Dr. Menon says.
“The labs understand everyone’s ways of thinking and we leverage everyone’s expertise,” she says.
Dr. Baudry agrees.
“That’s why UAH works so well,” he says. “We are large enough to have a very wide range of expertise in high-tech research, but we are also keen on collaboration and able to create these ad hoc teams capable of answering the most complex scientific and industrial questions and most modern.”
Pursuing artificial intelligence as a more efficient way to answer biological questions puts the university on a direct path to the future, says Dr. Baudry.
“The future is, without a doubt, towards artificial intelligence, machine learning, etc. You see it everywhere,” he says. “The most visible aspects of this scientific revolution are found in the self-driving cars on our roads. You can imagine all the data cars need to acquire and analyze to run on their own safely and efficiently. Tomorrow it could be autonomous aircraft or largely automated surgery.
“We shouldn’t be afraid of that,” he said. “We should, instead, embrace it and use this tremendous power as an agent of change, as an agent of good. And anyway, we will always need drivers, airplane pilots and surgeons – technology will help us, it will not replace us.
But science must first develop for this to happen.
“Even if I want to be in a safe automated car or plane, what happens in life – inside our cells and our bodies – is much more complex than what happens on the road with automobiles,” says Dr. Baudry. “So we have to do a lot of basic research here, and that’s what we do. And basic research can certainly be a goal in itself, but it’s also a path that has many points for industrial applications, and we are also very active in this regard.
Scientists succeed because they care a lot about the rigor of science, but also because it’s fun and exciting, he says.
“We’re really excited to see the younger generation of scientists, working on their PhDs or MScs in our labs, embracing these new directions in science,” says Dr. Baudry. “That’s ultimately what counts: the enthusiasm and skills of UAH students. And they are very bright, so the future is in good hands.
About the University of Alabama at Huntsville
Launched from America’s quest to conquer space, the University of Alabama at Huntsville is one of America’s leading research-intensive, doctoral-granting universities. Located in the second largest research park in the United States, UAH has strong capabilities in astrophysics, cybersecurity, data analytics, logistics and supply chain management, optical systems and engineering, reliability and failure analysis , rotorcraft and unmanned systems, severe weather, space propulsion and more. UAH prepares students for demanding positions in engineering, science, business, nursing, education, arts, humanities, and social sciences.