More Like this

1. Assessing the potential of deep learning for protein–ligand docking

   https://doi.org/10.1038/s42256-025-01160-1  

   Morehead, Alex; Giri, Nabin; Liu, Jian; Neupane, Pawan; Cheng, Jianlin (January 2026, Nature Machine Intelligence)

   Abstract The effects of ligand binding on protein structures and their in vivo functions carry numerous implications for modern biomedical research and biotechnology development efforts such as drug discovery. Although several deep learning (DL) methods and benchmarks designed for protein–ligand docking have recently been introduced, so far no previous works have systematically studied the behaviour of the latest docking and structure prediction methods within the broadly applicable context of: (1) using predicted (apo) protein structures for docking (for example, for applicability to new proteins); (2) binding multiple (cofactor) ligands concurrently to a given target protein (for example, for enzyme design); and (3) having no previous knowledge of binding pockets (for example, for generalization to unknown pockets). To enable a deeper understanding of the real-world utility of docking methods, we introduce PoseBench, a comprehensive benchmark for broadly applicable protein–ligand docking. PoseBench enables researchers to rigorously and systematically evaluate DL methods for apo-to-holo protein–ligand docking and protein–ligand structure prediction using both primary ligand and multiligand benchmark datasets, the latter of which we introduce to the DL community. Empirically, using PoseBench, we find that: (1) DL cofolding methods generally outperform comparable conventional and DL docking baseline algorithms, but popular methods such as AlphaFold 3 are still challenged by prediction targets with new protein–ligand binding poses; (2) certain DL cofolding methods are highly sensitive to their input multiple sequence alignments, whereas others are not; and (3) DL methods struggle to strike a balance between structural accuracy and chemical specificity when predicting new or multiligand protein targets. 

   more » « less
2. A Diffusion-Based Framework for Designing Molecules in Flexible Protein Pockets

   https://doi.org/10.1101/2025.05.27.656443  

   Wang, Jian; Zhang, Dong Yan; Budakoti, Shreshty; Dokholyan, Nikolay V (May 2025, bioRxiv)

   Abstract The design of molecules for flexible protein pockets represents a significant challenge in structure-based drug discovery, as proteins often undergo conformational changes upon ligand binding. While deep learning-based approaches have shown promise in molecular generation, they typically treat protein pockets as rigid structures, limiting their ability to capture the dynamic nature of protein-ligand interactions. Here, we introduce YuelDesign, a novel diffusion-based framework specifically developed to address this challenge. YuelDesign employs a new protein encoding scheme with a fully connected graph representation to encode protein pocket flexibility, a systematic denoising process that refines both atomic properties and coordinates, and a specialized bond reconstruction module tailored for de novo generated molecules. Our results demonstrate that YuelDesign generates molecules with favorable drug-likeness and low synthetic complexity. The generated molecules also exhibit diverse chemical functional groups, including some not even present in the training set. Redocking analysis reveals that the generated molecules exhibit docking energies comparable to native ligands. Additionally, a detailed analysis of the denoising process shows how the model systematically refines molecular structures through atom type transitions, bond dynamics, and conformational adjustments. Overall, YuelDesign presents a versatile framework for generating novel molecules tailored to flexible protein pockets, with promising implications for drug discovery applications. 

   more » « less
3. Improving the generalizability of protein-ligand binding predictions with AI-Bind

   https://doi.org/10.1038/s41467-023-37572-z  

   Chatterjee, Ayan; Walters, Robin; Shafi, Zohair; Ahmed, Omair Shafi; Sebek, Michael; Gysi, Deisy; Yu, Rose; Eliassi-Rad, Tina; Barabási, Albert-László; Menichetti, Giulia (December 2023, Nature Communications)

   Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery. 

   more » « less
4. What Makes GPCRs from Different Families Bind to the Same Ligand?

   https://doi.org/10.3390/biom12070863  

   Dankwah, Kwabena Owusu; Mohl, Jonathon E.; Begum, Khodeza; Leung, Ming-Ying (July 2022, Biomolecules)

   G protein-coupled receptors (GPCRs) are the largest class of cell-surface receptor proteins with important functions in signal transduction and often serve as therapeutic drug targets. With the rapidly growing public data on three dimensional (3D) structures of GPCRs and GPCR-ligand interactions, computational prediction of GPCR ligand binding becomes a convincing option to high throughput screening and other experimental approaches during the beginning phases of ligand discovery. In this work, we set out to computationally uncover and understand the binding of a single ligand to GPCRs from several different families. Three-dimensional structural comparisons of the GPCRs that bind to the same ligand revealed local 3D structural similarities and often these regions overlap with locations of binding pockets. These pockets were found to be similar (based on backbone geometry and side-chain orientation using APoc), and they correlate positively with electrostatic properties of the pockets. Moreover, the more similar the pockets, the more likely a ligand binding to the pockets will interact with similar residues, have similar conformations, and produce similar binding affinities across the pockets. These findings can be exploited to improve protein function inference, drug repurposing and drug toxicity prediction, and accelerate the development of new drugs. 

   more » « less
5. Essential Dynamics Ensemble Docking for Structure-Based GPCR Drug Discovery

   https://doi.org/10.3389/fmolb.2022.879212  

   McKay, Kyle; Hamilton, Nicholas B.; Remington, Jacob M.; Schneebeli, Severin T.; Li, Jianing (June 2022, Frontiers in Molecular Biosciences)

   The lack of biologically relevant protein structures can hinder rational design of small molecules to target G protein-coupled receptors (GPCRs). While ensemble docking using multiple models of the protein target is a promising technique for structure-based drug discovery, model clustering and selection still need further investigations to achieve both high accuracy and efficiency. In this work, we have developed an original ensemble docking approach, which identifies the most relevant conformations based on the essential dynamics of the protein pocket. This approach is applied to the study of small-molecule antagonists for the PAC1 receptor, a class B GPCR and a regulator of stress. As few as four representative PAC1 models are selected from simulations of a homology model and then used to screen three million compounds from the ZINC database and 23 experimentally validated compounds for PAC1 targeting. Our essential dynamics ensemble docking (EDED) approach can effectively reduce the number of false negatives in virtual screening and improve the accuracy to seek potent compounds. Given the cost and difficulties to determine membrane protein structures for all the relevant states, our methodology can be useful for future discovery of small molecules to target more other GPCRs, either with or without experimental structures. 

   more » « less