Genesis Therapeutics, founded in 2019 and based in Burlingame, California, develops artificial intelligence to discover and design small-molecule drugs with greater speed and a higher probability of success. The company emerged from research at Stanford on graph neural networks for molecular property prediction, and has built that foundation into a proprietary platform it calls GEMS, short for Genesis Exploration of Molecular Space.
GEMS pairs generative AI, which proposes novel molecular structures, with predictive AI that estimates critical properties such as potency, selectivity, and drug-like behavior. The platform integrates deep learning with physics-based modeling so that candidate molecules can be evaluated computationally before they are ever synthesized in the lab. This allows Genesis to search enormous regions of chemical space and concentrate experimental resources on the most promising compounds, targeting diseases that have proven difficult for traditional medicinal chemistry.
The company operates a hybrid business model. It forms collaborations with pharmaceutical partners to apply its platform against their targets, and it advances its own pipeline of wholly owned programs with the goal of becoming a clinical-stage company. This dual approach lets Genesis generate near-term partnership value while building long-term equity in its own drug candidates.
In its Series B financing, Genesis raised $200 million in a round co-led by Andreessen Horowitz Bio + Health alongside a major U.S.-based life-sciences investor, with new participation from Fidelity Management & Research, BlackRock, and NVIDIA's venture arm NVentures, plus existing backers including T. Rowe Price, Rock Springs Capital, Radical Ventures, and Menlo Ventures. The capital is funding expansion of its discovery pipeline, continued investment in the AI platform, and the company's transition toward clinical development. With more than $280 million raised since inception, Genesis is among the more prominent AI-native drug-discovery players bridging machine learning and medicinal chemistry.