Assessing Modern AI-Driven Protein-Ligand Modeling with Phenethylamine and Tryptamine Psychedelics
AI Chemistry February 10, 2026 Benjamin R. Cummins, Charles D. Nichols
Modern AI-based tools for predicting how drug-like molecules bind to proteins show uneven performance across different receptor types and chemical classes. Newly available cryo-electron microscopy structures of several psychedelic compounds bound to the serotonin 5HT2A receptor, an important G protein-coupled receptor, allowed comparison of three modeling approaches: AI-based protein–ligand cofolding (Boltz-2), an AI-driven docking module (Uni-Mol Docking v2), and a classical physics-based docking pipeline (AutoDock Vina). Predicted binding poses were compared with the experimental structures, and calcium-mobilization assays provided a functional readout. AI-based cofolding often produced global binding orientations closer to experimental structures, while classical docking showed greater variability across ligands but outperformed AI-driven docking on average. The findings highlight both the growing utility and current limitations of AI-assisted structure prediction in serotonergic drug discovery.