Genesis Therapeutics, a pioneer in artificial intelligence (AI), has closed an oversubscribed $200 million round of Series B financing. The company’s platform combines “3D structure-aware” deep neural networks with molecular simulation.
The financing was co-led by “a U.S.-based life-sciences-focused investor,” along with returning investor Andreessen Horowitz, which led the company’s seed financing, as well as several other new investors.
In May of this year, Genesis announced a collaboration with Eli Lilly to discover novel therapies for up to five targets across a range of therapeutic areas. In October 2020 the start-up inked a multi-target drug discovery partnership with Genentech.
For the Lilly deal, the two companies are partnering on three initial targets and Genesis will receive an upfront payment of $20 million. Lilly will have the option to nominate two more targets for an additional payment per target. Genesis will be eligible to receive up to $670 million total in upfront and target nomination fees, as well as preclinical, development, regulatory, and sales milestone payments. Genesis is also eligible to receive royalties on net sales.
Less details are available on the Genentech deal, but the release said, “Genesis will receive an upfront payment and is eligible to receive pre-clinical, clinical, and regulatory milestone payments, as well as future royalties on Genentech’s sales of approved drugs resulting from the collaboration.”
Genesis sprang from AI research at Stanford University where CEO Evan Feinberg, PhD, co-invented PotentialNet, an algorithm for molecular property prediction, which was described in ACS Central Science.
Genesis says its platform can address previously undruggable and data-poor targets using “robust computational infrastructure that scales the AI platform on the cloud, enabling immense swaths of chemical space to be searched.”
Its GEMS platform combines deep learning and molecular simulations. Dynamic PotentialNet predicts potency, selectivity, and ADMET. Dynamic PotentialNet represents 3D structure and interactions of protein-ligand complexes as spatial graphs. “By training on a combination of molecular simulations and experimental data, it learns representations of the physical interactions underlying binding affinity,” the company reports.
Dynamic PotentialNet also integrates Genesis’s proprietary molecular simulation platform, which incorporates data about 3D binding dynamics, including effects of protein flexibility and critical water molecules. The company has also developed a molecular generation engine. GEMS uses ML models to create novel molecules and investigate chemical space for each drug program. “During Hit ID, GEMS generates billions of drug-like and synthetically accessible molecules,” the company reports.
“We are excited to join forces with Lilly and their world-class research and development teams to discover novel drugs for patients suffering with severe diseases,” said Feinberg.
In another statement, he said “This partnership with Genentech enables us to leverage our AI technology platform with Genentech’s unmatched capabilities in molecular innovation and structural biology.
He also said, “At Genesis, interdisciplinary teams of accomplished AI researchers, software engineers, chemists and biologists work closely together to push the boundaries of chemical machine learning and create novel therapies for protein targets that have evaded traditional discovery methods. We look forward to addressing critical areas of unmet medical need by combining the expertise of our respective organizations.”
