Age: 18Mequon, WI
Project Title: Multiobjective De Novo Drug Design with Recurrent Neural Networks and Nondominated Sorting
Jacob developed an artificial intelligence-based approach to pharmaceutical drug development, a traditionally time-consuming and expensive pipeline with extremely high failure rates. His system is uniquely able to generate drug-like molecules from scratch and optimize them on many molecular properties (e.g. absorption, toxicity, activity, etc.) collectively. The quality of generated molecules improved 14-fold over just five iterations of his cyclic algorithm, showing promise as an efficient tool in early-stage drug discovery.
Jacob Yasonik is a graduate of Homestead High School in Mequon, Wisconsin and an incoming undergraduate at the Massachusetts Institute of Technology (MIT). He is especially interested in artificial intelligence and its applications in medicine, giving rise to his recent work in computational biology. Jake is beyond grateful for his selection as a 2020 Davidson Fellow Laureate and looks forward to meeting like-minded peers from the Davidson community.
Working from home, Jake developed an artificial intelligence-based approach to pharmaceutical drug development. His system generates drug-like molecules from scratch and is uniquely able to optimize many molecular properties collectively. This is important, as current drug design approaches often struggle to account for activity, absorption, toxicity, and other traits all at once, causing inefficiencies throughout the pharmaceutical pipeline. Jake’s model demonstrates a more economical and agile approach; his algorithm yielded a 14-fold improvement in the quality of molecules generated across five different molecular criteria, demonstrating potential in early-stage drug discovery.
Unable to find a lab or mentor, Jake initially struggled to get his project off the ground. Seemingly simple chemistry questions and programming setbacks took weeks to solve as he combed through online forums and open-access research papers. Though frustrating in the moment, Jake found enjoyment in testing different approaches and going down different paths, despite them often ending in failure (e.g. his model failed to generate valid molecules, then kept generating duplicates of the same molecule, etc.). Through these challenges, Jake gained a greater appreciation for the research process: a process filled with obstacles that make the end-result that much more rewarding.
Jake’s research addresses the most fundamental problems in drug discovery: current methods lack scalability and lack multiobjectivity. Traditional approaches are rooted in trial and error and struggle to account for many molecular properties collectively, resulting in long timelines (10 - 15 years), excessive costs ($160 million - $2.6 billion), and extremely high failure rates (87% - 97%), just to develop a single new drug. Jake’s new artificial intelligence-based approach could significantly improve drug discovery by reducing the reliance on trial and error and pre-made molecular databases through a generative approach. Additionally, his approach is unique in its ability to optimize for many molecular characteristics at once, which could result in far better success rates further along the pharmaceutical pipeline.
Jake attended Homestead High School, a public high school in Wisconsin, and was lucky to have had many caring teachers who went above and beyond. He finished the available math and computer science curriculum during his junior year and took two self-guided, independent studies in computer science afterwards. Jake will attend MIT and hopes to major in Mathematics with Computer Science. Further down-the-line, Jake hopes to find himself in an industry R&D lab or starting his own company.
For his work, Jake was recognized as a finalist in the 2020 Regeneron Science Talent Search (STS) and awarded the Third Grand Award at the 2019 Intel International Science and Engineering Fair (ISEF). He recently published his research in the Journal of Cheminformatics as the sole author. Beyond research, Jake loves piano, chess, calligraphy, and long-distance running. He previously performed at Carnegie Hall and ran the Chicago Half Marathon. Jake also worked at a local dry cleaners and volunteered at the Discovery World Science Museum. When not engrossed in one of his projects, Jake can be found glued to an NBA game or hiking nearby trails.
Where do you see yourself in 10 years?
Pitching a biotech startup or working at an AI research lab
If you could have dinner with the five most interesting people in the world, living or dead, who would they be?
Mr. Rogers, Alan Turing, Grace Hopper, Winston Churchill, Nikola Tesla
I can't choose, so here's three of my absolute favorites:
"The best argument against democracy is a five-minute conversation with the average voter." -Winston Churchill
"The amount of energy needed to refute nonsense is an order of magnitude bigger than to produce it." -Brandolini's Law
"We prefer crash pads over training wheels." -MIT Media Lab
In the News
MEQUON TEEN AWARDED $50,000 FOR DEVELOPING A NEW APPROACH TO PHARMACEUTICAL DRUG DEVELOPMENT USING ARTIFICIAL INTELLIGENCE
Jacob Yasonik to be Named a 2020 Davidson Fellow Scholarship Winner
Mequon, Wis. – The Davidson Fellows Scholarship Program has announced the 2020 scholarship winners. Among the honorees is 18-year-old Jacob Yasonik of Mequon. Yasonik won a $50,000 scholarship for his project, Multiobjective De Novo Drug Design with Recurrent Neural Networks and Nondominated Sorting. He is one of only 20 students across the country to be recognized as a scholarship winner.
“I am beyond grateful for my selection as a 2020 Davidson Fellow Laureate,” said Yasonik. “I look forward to meeting like-minded peers from the Davidson community.”
Working from home, Yasonik developed an artificial intelligence-based approach to pharmaceutical drug development that generates drug-like molecules from scratch and is uniquely able to optimize many molecular properties collectively. Yasonik’s new artificial intelligence-based approach could significantly improve drug discovery by reducing the reliance on trial and error and pre-made molecular databases through a generative approach due to its unique ability to optimize for many molecular characteristics at once, which could result in far better success rates further along the pharmaceutical pipeline.
Yasonik will be attending Massachusetts Institute of Technology in the fall where he plans to continue his education in artificial intelligence and its applications in medicine, which inspired his recent work in computational biology.
Click here to download the full press release
Click the image to download hi-res photos:
The following disclosure is provided pursuant to Nevada Revised Statutes (NRS) 598.1305:The Davidson Institute for Talent Development is a Nevada non-profit corporation which is recognized by the Internal Revenue Service as a 501(c)3 tax-exempt private operating foundation. We are dedicated to supporting the intellectual and social development of profoundly gifted students age 18 and under through a variety of programs. Contributions are tax deductible.
Profoundly gifted students are those who score in the 99.9th percentile on IQ and achievement tests. Read more about this population in this article.