DeepChem

DeepChem is an open-source deep learning platform for drug discovery, materials science, quantum chemistry, and biology. The mission: democratize the tools so that any researcher, anywhere, can apply deep learning to molecular problems without rebuilding infrastructure from scratch.

My role has been research architect and Google Summer of Code mentor — working with PhD students and postdocs to build and contribute to the platform’s core capabilities. Projects have included neural ODEs, conformal prediction, and transformer models for genomics. Ten-plus mentees across multiple GSoC cycles, contributing thousands of lines of code to an ecosystem that serves the entire computational chemistry community.

DeepChem matters because it proves a model: open-source infrastructure shared freely produces better science than proprietary tools locked behind licenses. The code is open. The mentorship is open. The knowledge compounds. That’s the pattern Lattice Protocol extends to federated research at scale.