Assessing Modern AI-Driven Protein-Ligand Modeling with Phenethylamine and Tryptamine Psychedelics

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.

Study at a glance

Abstract

Modern advances in artificial intelligence have accelerated the development of computational tools for protein–ligand structure prediction, yet their real-world performance remains uneven across receptor classes and ligand chemotypes. Recently published cryo-EM structures of several different psychedelics bound to the serotonin 5HT2A receptor provide a unique opportunity to explore how modern AI-based modeling performs in a pharmacologically important GPCR system. Here, we compare three major approaches: AI-based protein–ligand cofolding (Boltz-2), a leading AI-driven docking module (Uni-Mol Docking v2), and a widely used classical physics-based docking pipeline (AutoDock Vina) across a series of tryptamine and phenethylamine psychedelics. Predicted binding poses were comparatively assessed through structural alignment with these newly available cryo-EM complexes. Additionally, calcium-mobilization assays were performed to provide a coarse functional readout for comparison with computationally predicted binding affinities. This study integrates methodological review with exploratory benchmarking to illustrate how different modeling paradigms behave on a shared receptor–ligand test set. Our results highlight substantial variation between modeling strategies, with AI-based cofolding often producing global binding orientations more closely resembling experimental structures, and classical docking showing greater variability across ligands, while still outperforming AI-driven docking on average. These observations underscore both the growing utility and current limitations of AI-assisted structure prediction in serotonergic drug discovery, and emphasize the importance of careful, experimentally anchored evaluation as such tools continue to advance.