An official website of the United States government
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
NeuralDock: Rapid and Conformation-Agnostic Docking of Small Molecules
Virtual screening is a cost- and time-effective alternative to traditional high-throughput screening in the drug discovery process. Both virtual screening approaches, structure-based molecular docking and ligand-based cheminformatics, suffer from computational cost, low accuracy, and/or reliance on prior knowledge of a ligand that binds to a given target. Here, we propose a neural network framework, NeuralDock, which accelerates the process of high-quality computational docking by a factor of 10 6 , and does not require prior knowledge of a ligand that binds to a given target. By approximating both protein-small molecule conformational sampling and energy-based scoring, NeuralDock accurately predicts the binding energy, and affinity of a protein-small molecule pair, based on protein pocket 3D structure and small molecule topology. We use NeuralDock and 25 GPUs to dock 937 million molecules from the ZINC database against superoxide dismutase-1 in 21 h, which we validate with physical docking using MedusaDock. Due to its speed and accuracy, NeuralDock may be useful in brute-force virtual screening of massive chemical libraries and training of generative drug models.
more »
« less
- PAR ID:
- 10379634
- Date Published:
- Journal Name:
- Frontiers in Molecular Biosciences
- Volume:
- 9
- ISSN:
- 2296-889X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Structure-based virtual screening is a key tool in early drug discovery, with growing interest in the screening of multi-billion chemical compound libraries. However, the success of virtual screening crucially depends on the accuracy of the binding pose and binding affinity predicted by computational docking. Here we develop a highly accurate structure-based virtual screen method, RosettaVS, for predicting docking poses and binding affinities. Our approach outperforms other state-of-the-art methods on a wide range of benchmarks, partially due to our ability to model receptor flexibility. We incorporate this into a new open-source artificial intelligence accelerated virtual screening platform for drug discovery. Using this platform, we screen multi-billion compound libraries against two unrelated targets, a ubiquitin ligase target KLHDC2 and the human voltage-gated sodium channel NaV1.7. For both targets, we discover hit compounds, including seven hits (14% hit rate) to KLHDC2 and four hits (44% hit rate) to NaV1.7, all with single digit micromolar binding affinities. Screening in both cases is completed in less than seven days. Finally, a high resolution X-ray crystallographic structure validates the predicted docking pose for the KLHDC2 ligand complex, demonstrating the effectiveness of our method in lead discovery.more » « less
-
Abstract While significant advances have been made in predicting static protein structures, the inherent dynamics of proteins, modulated by ligands, are crucial for understanding protein function and facilitating drug discovery. Traditional docking methods, frequently used in studying protein-ligand interactions, typically treat proteins as rigid. While molecular dynamics simulations can propose appropriate protein conformations, they’re computationally demanding due to rare transitions between biologically relevant equilibrium states. In this study, we present DynamicBind, a deep learning method that employs equivariant geometric diffusion networks to construct a smooth energy landscape, promoting efficient transitions between different equilibrium states. DynamicBind accurately recovers ligand-specific conformations from unbound protein structures without the need for holo-structures or extensive sampling. Remarkably, it demonstrates state-of-the-art performance in docking and virtual screening benchmarks. Our experiments reveal that DynamicBind can accommodate a wide range of large protein conformational changes and identify cryptic pockets in unseen protein targets. As a result, DynamicBind shows potential in accelerating the development of small molecules for previously undruggable targets and expanding the horizons of computational drug discovery.more » « less
-
Molecular docking is a computational technique used to predict ligand binding potential, conformation, and location for a given receptor, and is regarded as an attractive method to use in drug design due to its relatively low computational and monetary cost. However, molecular docking programs tend not to be accessible to novice users. Most docking programs require at least a basic knowledge of command line and computer programming to install and configure the program. Additionally, tutorials for the most commonly used programs tend to be inflexible, requiring a specific molecule or set of molecules to be bound to a specific receptor, and need the installation and usage of other programs or websites to download and prepare structures. To increase general access to molecular docking, basil_dock utilizes a series of easy-to-use Jupyter notebooks that do not assume user familiarity with molecular docking procedures and concepts, requiring little command line usage and software installation. The series includes four notebooks that were created to reflect the different steps in the molecular docking process: (1) the preparation of ligand and protein files prior to docking, (2) the docking of ligands to a protein receptor, (3) analyzing the resulting data and determining how different functional groups in the ligand can affect protein-ligand binding, and (4) identifying essential locations for binding within the ligand and protein. The notebooks enable novice users flexibility and customization in exploring docking procedures and systems, as well as teaching users the basis behind molecular docking without having to leave the environment to obtain information and materials from other applications. The first version of basil_dock allows users to choose from receptors uploaded to the Protein Data Bank and to add additional ligands as desired. Users can then select between the Vina and Smina docking engines and change ligand functional groups to see how the substitution of atom groups affects binding affinity and ligand conformation. The data can then be analyzed to determine residues in the receptor and atom groups in the ligand that are likely to be integral to forming the ligand-protein complex and to discern which ligands are likely to be orally bioactive based on Lipinski’s Rule of Five. From this work, a package of python scripts has been created to streamline the generating, splitting, and writing of ligand files, greatly reducing the number of errors arising from attempting to split a comprehensive ligand file manually. Libraries used in basil_dock include Vina, Smina, RDKit, openbabel, and MDAnalysis. While the package has been designed based off the needs of basil_dock, it has been created to be extensible. Support for this project was provided by NSF 2142033more » « less
-
Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design. Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space. Empirically, DiffDock obtains a 38% top-1 success rate (RMSD<2A) on PDBBind, significantly outperforming the previous state-of-the-art of traditional docking (23%) and deep learning (20%) methods. Moreover, while previous methods are not able to dock on computationally folded structures (maximum accuracy 10.4%), DiffDock maintains significantly higher precision (21.7%). Finally, DiffDock has fast inference times and provides confidence estimates with high selective accuracy.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fmolb.2022.867241
