At Fathom Therapeutics, the AI platform autonomously iterates to generate drug candidates, bypassing tedious manual steps. This frees up scientists from the time-consuming "mechanic" work of building molecular connections, allowing them to dedicate their expertise to analyzing the high-quality, system-generated options and data.
No single AI platform can solve the complexities of biology. The greatest impact will come from multiple, specialized platforms—such as generative chemistry, organoids, and virtual cells—working closely together. This requires companies to have humility about their own platform's limitations and prioritize strategic collaboration.
When planning a company's future, founders should avoid naming successful companies as role models. Instead, they should define the specific character traits, values, and impact they want their organization to embody, much like an individual defines their personal goals and character.
The explosion of AI-generated molecular candidates creates a new problem: physically testing them at scale. A significant portion of R&D effort should be redirected from AI model development to inventing novel, high-throughput instrumentation and assays to experimentally validate the flood of predictions AI produces.