Clay Moore
Ph.D. Student @ Texas A&M University.
Houston, TX
Researcher working at the interface of neuroscience, natural products, and AI-driven drug discovery. My research focuses on computational modeling of neuroinflammation and neural plasticity, with an emphasis on identifying plant-derived and natural product-inspired compounds that may influence therapeutic pathways. I build in silico pipelines for molecular screening, receptor-state classification, and translational discovery workflows that connect computational biology with future wet-lab validation.
📰 News
Aug 5, 2026  · linkedin
I’m glad to be contributing to Recursion’s Nesso-1 through PR #3. I identified two training-only tensors - disto_target and token_to_rep_atom - that were still being generated and transferred during inference even though Nesso-1’s forward pass never used them. Removing those unused inference tensors cut input-batch GPU memory from 155.1 MiB to 16.8 MiB, about 9x smaller, and reduced host-to-device transfer...
Jul 30, 2026  · github
AlphaFold 3 v3.0.4 dropped - and I’m credited in the release notes for a memory optimization merged into this version. The headline feature is that AlphaFold 3 is now runnable on CPU-only machines and Apple Silicon, which meaningfully expands access beyond GPU clusters. My contribution (PR #674) is in there: the OuterProductMean module was rewritten to replace two sequential einsum...
Jul 23, 2026  · linkedin
Valence Labs just released Nesso-1, an open-source coarse-grained protein–ligand co-folding model for binding affinity prediction. Nesso-1 replaces full atomistic diffusion with residue-level protein representations, ligand heavy atoms, ESM-2 embeddings, and a Pairformer-style trunk. It also uses NVIDIA cuEquivariance, which provides optimized GPU kernels for expensive geometric operations such as triangle-based pair updates. The result is better reported affinity ranking than...