How accurately can one predict drug binding modes using AlphaFold models?
Computational prediction of protein structure has been pursued intensely for decades, motivated largely by the goal of using structural models for drug discovery. Recently developed machine-learning methods such as AlphaFold 2 (AF2) have dramatically improved protein structure prediction, with reported accuracy approaching that of experimentally determined structures. To what extent do these advances translate to an ability to predict more accurately how drugs and drug candidates bind to their target proteins? Here, we carefully examine the utility of AF2 protein structure models for predicting binding poses of drug-like molecules at the largest class of drug targets, the G-protein-coupled receptors. We find that AF2 models capture binding pocket structures much more accurately than traditional homology models, with errors nearly as small as differences between structures of the same protein determined experimentally with different ligands bound. Strikingly, however, the accuracy of ligand-binding poses predicted by computational docking to AF2 models is not significantly higher than when docking to traditional homology models and is much lower than when docking to structures determined experimentally without these ligands bound. These results have important implications for all those who might use predicted protein structures for drug discovery.
View details for DOI 10.7554/eLife.89386
View details for PubMedID 38131311
View details for PubMedCentralID PMC10746139
GPR161 structure uncovers the redundant role of sterol-regulated ciliary cAMP signaling in the Hedgehog pathway.
bioRxiv : the preprint server for biology
The orphan G protein-coupled receptor (GPCR) GPR161 is enriched in primary cilia, where it plays a central role in suppressing Hedgehog signaling1. GPR161 mutations lead to developmental defects and cancers2,3,4. The fundamental basis of how GPR161 is activated, including potential endogenous activators and pathway-relevant signal transducers, remains unclear. To elucidate GPR161 function, we determined a cryogenic-electron microscopy structure of active GPR161 bound to the heterotrimeric G protein complex Gs. This structure revealed an extracellular loop 2 that occupies the canonical GPCR orthosteric ligand pocket. Furthermore, we identify a sterol that binds to a conserved extrahelical site adjacent to transmembrane helices 6 and 7 and stabilizes a GPR161 conformation required for Gs coupling. Mutations that prevent sterol binding to GPR161 suppress cAMP pathway activation. Surprisingly, these mutants retain the ability to suppress GLI2 transcription factor accumulation in cilia, a key function of ciliary GPR161 in Hedgehog pathway suppression. By contrast, a protein kinase A-binding site in the GPR161 C-terminus is critical in suppressing GLI2 ciliary accumulation. Our work highlights how unique structural features of GPR161 interface with the Hedgehog pathway and sets a foundation to understand the broader role of GPR161 function in other signaling pathways.
View details for DOI 10.1101/2023.05.23.540554
View details for PubMedID 37292845
View details for PubMedCentralID PMC10245861
Geometric deep learning of RNA structure.
Science (New York, N.Y.)
2021; 373 (6558): 1047-1051
RNA molecules adopt three-dimensional structures that are critical to their function and of interest in drug discovery. Few RNA structures are known, however, and predicting them computationally has proven challenging. We introduce a machine learning approach that enables identification of accurate structural models without assumptions about their defining characteristics, despite being trained with only 18 known RNA structures. The resulting scoring function, the Atomic Rotationally Equivariant Scorer (ARES), substantially outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges. By learning effectively even from a small amount of data, our approach overcomes a major limitation of standard deep neural networks. Because it uses only atomic coordinates as inputs and incorporates no RNA-specific information, this approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond.
View details for DOI 10.1126/science.abe5650
View details for PubMedID 34446608