Introduction The fundamental steps of rational drug design include the identification of a clinically relevant target protein, the discovery of “hit” ligands that weakly modulate the target protein in the de­sired manner, and the optimization of selected hits for high po­tency against the target, low potency against all related off-targets, and good absorption, distribution, metabolism, ex­cretion, and toxicity (ADMET). Target identification and the opti­mization of selected hits are informed by biology and medicinal chemistry, respectively. In contrast, the initial discovery of hits that are active against the target, and can be effectively optimized, is more dependent on exhaustive searching and luck. Conventional approaches for hit discovery are expensive, inaccurate, and can only explore a minuscule fraction of the full space of synthesiz­able, drug-like molecules. Generative machine learning (ML) promises to efficiently op­timize more accurate estimates of binding affinity and other phar­macological properties over the entirety of drug-like chemical space. Rather than exhaustively testing a screening library or making small changes to the best known compounds, generative ML maps chemical space to a smooth search space in which small moves correspond to small changes in potency, ADMET, etc. Within this search space, a diverse set of potent, selective, lead-like, and novel…

Recognition of the strategic importance of AI. The importance of AI is being elevated to a national level where capability is seen as a nationally-strategic priority. While that means more government funding for research, it also means that some nation-states are closing themselves off to the free flow of research and circling their wagons. This doesn’t do anyone any good. With the increasing stratification of nation-states along ideological/geopolitical lines, I don’t see this getting any better in the near term and that is very concerning. As part of our series about the future of Artificial Intelligence, I had the pleasure of interviewing Handol Kim. Handol is Co-Founder & CEO of Variational AI, a Vancouver-based AI for drug discovery start-up developing novel therapeutics in oncology and beyond. He is a three-time tech entrepreneur with 20+ years in executive leadership roles in AI/ML, quantum computing, software, cloud, and semiconductor in start-ups and public companies in Silicon Valley, Canada, and Asia-Pacific. Thank you so much for joining us in this interview series! Can you share with us the ‘backstory” of how you decided to pursue this career path in AI? Myjourney in AI started at a quantum computing company called D-Wave Systems. I…

While the topic of AI in drug discovery has received considerable attention in recent years, mature deployments of techniques such as machine learning in the industry remain rare.  “The chemistry domain is qualitatively different from any other problem that machine learning has exhibited real success in,” said Jason Rolfe, CTO of Variational AI (Vancouver, Canada).  A dataset involving FDA-approved drugs that have been tested in humans would be orders of magnitude smaller than the sort of datasets that underlie Generative Pre-trained Transformer 3 (GPT-3), a language model from OpenAI, an AI research company co-founded by Elon Musk.    High-throughput screening can generate substantially larger datasets. The PubChem database is billed by NIH as the “largest collection of freely accessible chemical information,” but the data can be noisy. Many of the apparent active compounds likely won’t be validated in a secondary screen due to factors such as aggregation, contamination of samples and assay interference.  “These datasets are intrinsically more difficult to work with than something like ImageNet, which has been the workhorse for much of the architectural development in machine learning,” Rolfe said.  With ImageNet, a visual database containing more than 14 million annotated images, the data are relatively clean. “Some…

The news: Variational AI, a Vancouver, B.C.-based company leveraging artificial intelligence to help develop new small molecule drugs, has raised $3.5 million in seed funding. The tech: Variational AI’s Enki software generates novel molecular structures using its algorithms trained on a set of compounds screened against drug targets from both experimental and computational sources. The six-employee company has partnerships with an undisclosed public biopharma company, the University of British Columbia, and others. The field: Advances in biomedical science and artificial intelligence have combined to spawn efforts at drug design and discovery in the last several years. Researchers are training their machine learning engines on databases of drugs and their targets to help build new or improved compounds. The people: CEO Handol Kim co-founded the company in 2019 with CTO Jason Rolfe and three of the company’s machine learning researchers, Ali Saberali, Mehran Khodabandeh and Zaccary Alperstein. Kim previously co-founded three other companies in the mobile marketing and AI areas. Leveraging new tools: As part of its software, Variational AI will leverage tools developed by Alphabet’s DeepMind and the University of Washington’s Institute for Protein Design, led by David Baker. The tools have stunned scientists with their speed and accuracy at predicting protein folding. “We can make use of the innovations from Deepmind/Baker Lab since they’re illuminating…

Leading Cancer and Drug Discovery Biologists Dr. John F. Boylan and Dr. Mads Daugaard Join SAB Vancouver, BC – June 27, 2022 – Variational AI, developer of generative AI-based drug discovery platform for novel kinase inhibitors, today announced that it has added industry and scientific leaders Dr. John F. Boylan and Dr. Mads Daugaard to the company’s Scientific Advisory Board. “We are pleased to welcome Drs Boylan and Daugaard to our scientific advisory board,” said Handol Kim, co-Founder and CEO, Variational AI. “Their respective expertise in cell biology and biology complements our existing strengths in machine learning and chemistry and will help us focus on rapidly developing novel multi-targeted kinase inhibitors for oncology. We look forward to working with our SAB members to bring new therapeutics to market to positively impact patient outcomes.” Dr. John F. Boylan is a cell biologist by training focused on oncology drug discovery with a record of clinical success, contributing to 12 development candidates, 8 drugs that reached first-in-human clinical trials, and one approved drug; Vemurafenib (mutant BRAF inhibitor).  His broad drug discovery success encompasses small molecule, antibody, and antibody drug conjugate modalities. Dr. Boylan has led multidisciplinary teams and departments seeking to discover novel…

Leading Chemistry and Drug Development Researchers Alexander Tropsha, Ph.D. and Robert N. Young, Ph.D. Join SAB Vancouver, BC – April 5, 2022 – Variational AI, developer of state-of-the-art generative AI technology to redefine the economics of drug development by accelerating the discovery of novel and optimized small molecule therapeutics, today announced that it has added industry leaders Alexander Tropsha, Ph.D. and Robert N. Young, Ph.D.  to the company’s Scientific Advisory Board. Dr. Alexander Tropsha is a K.H. Lee Distinguished Professor at the University of North Carolina at Chapel Hill Eshelman School of Pharmacy and Chief Domain Scientist for Molecular Informatics at the Renaissance Computing Institute, UNC-Chapel Hill. He has extensive expertise in computational chemistry, structural bioinformatics and cheminformatics, which brings together chemistry and computer science to assist in the discovery of new drugs. He has authored more than 260 peer-reviewed papers as well as 25 books and chapters. In addition to serving as pharmacy professor, Dr. Tropsha is also an adjunct professor for the UNC Department of Biomedical Engineering and the Department of Computer Science and is a member of the UNC Lineberger Comprehensive Cancer Center. Dr. Tropsha is an elected Fellow of the American Institute for Medical and Biomedical…

Industry Veteran to Lead Company’s Therapeutic Development Vancouver, BC – March 15, 2022 – Variational AI, developer of state-of-the-art generative AI technology to redefine the economics of drug development by accelerating the discovery of novel and optimized small molecule therapeutics, today announced that Peter Guzzo, Ph.D., has joined the company as vice president, head of drug discovery. Guzzo has spent his 25-year career focused on finding innovative therapeutics for poorly treated diseases and will work on translating hits for various important biological targets discovered through Variational AI’s proprietary generative AI platform into candidate compounds for clinical development. Peter has knowledge in multiple therapeutic indications, including oncology, central nervous system diseases, metabolic disorders, intellectual property creation and building entrepreneurial teams. He is an inventor on 43 patents, co-author of 47 scientific publications and has presented 28 invited lectures. During his career, he has led cross-functional teams, delivering 11 innovative drugs into clinical development. He has extensive experience collaborating with pharma, biotech, academic institutions and contract research organizations to execute drug discovery and development projects. Guzzo most recently served as vice president, drug development at Tryp Therapeutics, Inc. and senior vice president of drug discovery and development at SciMount Therapeutics, co-founder and…

AI-Generated Antiviral is Intended to Treat Variants of Concern Such as Omicron and Delta Vancouver, BC – December 15, 2021 – Variational AI, developer of state-of-the-art generative AI technology to redefine the economics of drug development by accelerating the discovery of novel and optimized small molecule therapeutics, today announced the company has generated and ordered compounds for validation in partnership with the University of British Columbia (UBC) and adMare BioInnovations to develop a novel SARS-CoV-2 Main Protease (3CLpro) inhibitor. The therapeutic is intended to be efficacious against the wild type and current variants of concern, including Delta and potentially Omicron, in the form of an antiviral pill. The COVID-19 drug discovery program is funded by Canada’s Digital Technology Supercluster, which is supported by the Canadian Ministry of Innovation, Science and Industry. “The Variational AI team is honored to partner with the University of British Columbia and adMare BioInnovations to work to address this most urgent medical need,” said Handol Kim, co-founder and CEO, Variational AI. “As society continues to grapple with COVID-19 variants, it is more important than ever to leverage the power of machine learning to accelerate our drug discovery efforts.” Variational AI has trained its generative AI algorithm…