Review waiting, please be patient. This may take 3 months or more, since drafts are reviewed in no specific order. There are 4,441 pending submissions waiting for review. If the submission is accepted, then this page will be moved into the article space. If the submission is declined, then the reason will be posted here. In the meantime, you can continue to improve this submission by editing normally. Where to get help If you need help editing or submitting your draft, please ask us a question at the AfC Help Desk or get live help from experienced editors. These venues are only for help with editing and the submission process, not to get reviews. If you need feedback on your draft, or if the review is taking a lot of time, you can try asking for help on the talk page of a relevant WikiProject. Some WikiProjects are more active than others so a speedy reply is not guaranteed. How to improve a draft Wikipedia:Contributing to Wikipedia – a basic overview on how to edit Wikipedia. Help:Wikitext – how to use the markup Help:Referencing for beginners – how to include references Wikipedia:Article development – how to develop your article Wikipedia:Writing better articles – how to improve your article Wikipedia:Verifiability – make sure your article includes reliable third-party sources You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Add tags to your draft Editor resources Easy tools: Citation bot (help) | Advanced: Fix bare URLs Reviewer tools Instructions · What links here · Genesis Molecular AI (talk: + · bio) · (log) · Copyvios report · reFill · Citation Bot · (Search: Google, Wikipedia) · Submitted 52 days ago by Jlaub3 (talk: D · +) · Last edited 46 hours ago by Jlaub3

• Comment: In accordance with the Wikimedia Foundation's Terms of Use, I disclose that I have been paid by my employer for my contributions to this article. Jlaub3 (talk) 00:20, 15 April 2026 (UTC)

Genesis Molecular AI, Inc. is a private artificial intelligence (AI) company headquartered in the San Francisco Bay Area, with locations in San Mateo, San Diego and New York. Founded in 2019, the company is developing generative and predictive artificial intelligence technologies for the discovery of small molecule drugs. ^[1]

Genesis (formerly Genesis Therapeutics), was founded in 2019 by Evan Feinberg. The company emerged from Feinberg's work with Vijay S. Pande at Stanford University, where they developed artificial intelligence methods for drug discovery and were early pioneers of graph neural networks (GNN's) for molecules. This work included PotentialNet, a family of spatial graph convolutional deep learning algorithms in Vijay S. Pande’s lab.^{[2] [3]}

Since its founding, Genesis has raised over $300 million.^[2] In 2020, the company announced a $52M Series A led by Rock Springs Capital.^[4] In 2023, the company raised an oversubscribed $200M Series B, co-led by Andreessen Horowitz.^[5] Genesis has been recognized in the Forbes AI 50 list in 2020, 2021 and 2022. ^{[6] [7] [8]} It was also listed on the Fierce Medtech's Fierce 15 list in 2023 and on CB Insights AI 100: The top AI companies in 2024.^{[9] [10]}

Genesis’ platform, called Genesis Exploration of Molecular Space (GEMS), uses novel AI systems, including diffusion models, multi-task ADME models, language models, and physical simulations to generate drug candidates across multiple therapeutic areas by optimizing small molecules for complex targets.^{[11] [12]}

In 2025 with co-authorship from NVIDIA, Genesis announced Pearl (Placing Every Atom in the Right Location),^[13] a foundation model for biomolecular structure prediction. Pearl predicts 3D protein–ligand complex structures through a SO(3)-equivariant diffusion model trained on both experimental and synthetic protein-ligand complexes. The authors of Pearl report that it was the first to outperform Google DeepMind’s AlphaFold 3 model on certain benchmarks. ^[13]

Genesis Molecular AI has entered into multiple collaborations with major pharmaceutical and technology companies, including:

In September 2024, pharmaceutical company Gilead Sciences partnered with Genesis for AI-based drug discovery work on three undisclosed targets. Gilead paid $35 million upfront with the option to nominate additional targets for a predetermined per-target fee.^[14]

In December 2024, Genesis announced its partnership and additional investment from NVIDIA to optimize AI architectures and infrastructure for drug discovery.^[2]

In February 2025, Incyte entered a strategic collaboration with Genesis to develop small molecule medicines against undisclosed targets. The deal included a $30 million upfront payment with up to $295 million per target in development, regulatory and commercial milestones, alongside tiered royalties.^[15] In May 2026, the companies announced an expansion of the collaboration, broadening the deployment of Genesis’ platform across at least five additional targets, with Incyte’s proprietary experimental data being used to train GEMS.^[16] Under the terms of the expansion, Genesis received $120 million in upfront consideration, including $80 million in cash and $40 million in equity commitment, and is eligible to receive $232 million per target in development.^[16][17][18] Jlaub3 (talk) 20:56, 31 March 2026 (UTC)