Skip to main content

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 SaberaliMehran 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 new targets. Our approach generates novel molecules that bind to these targets – so it helps us,” Kim told Geekwire in an email.

Jostling with big players and new upstarts: Companies harnessing AI for drug discovery focus on different strategies. Seattle-based Cyrus Biotechology and A-Alpha Bio focus on therapeutic proteins with tech spun out of the IPD. Pharma companies have shown interest in the new protein-folding tools, and Alphabet launched Isomorphic Laboratories this month to leverage them in small molecule and protein-based drug discovery.

Variational AI uses an approach similar to InSilico Medicine, Genesis Therapeutics and Valence Discovery, said Kim. Its software goes beyond pulling out key compounds from existing databases, and instead outputs new compounds with potentially enhanced properties. Variational AI accomplishes the task with less starting data, said Kim. Instead of licensing its platform, Variational AI aims to develop and license its own compounds.

The backers: Flying Fish VenturesAlliance of Angels and A&E Investments led the funding round, with participation from company advisors Lip-Bu Tan and Amarjit Gill. The new funding builds on $1 million (CAD) from the Digital Technology Supercluster, a Canadian government-funded innovation centre, and $210,000 (CAD) from angel investors and the University of British Columbia Seed Fund (Saberali and Alperstein were UBC graduate students).

The future: Variational AI will use the new cash to accelerate its discovery programs for COVID-19, cancer and other diseases and to hire employees in medicinal chemistry, cheminformatics, and machine learning. It will also recruit a scientific advisory board.