An official website of the United States government
Structure-based virtual screening utilizes molecular docking to explore and analyze ligand–macromolecule interactions, crucial for identifying and developing potential drug candidates. Although there is availability of several widely used docking programs, the accurate prediction of binding affinity and binding mode still presents challenges. In this study, we introduced a novel protocol that combines our in-house geometry optimization algorithm, the conjugate gradient with backtracking line search (CG-BS), which is capable of restraining and constraining rotatable torsional angles and other geometric parameters with a highly accurate machine learning potential, ANI-2x, renowned for its precise molecular energy predictions reassembling the wB97X/6-31G(d) model. By integrating this protocol with binding pose prediction using the Glide, we conducted additional structural optimization and potential energy prediction on 11 small molecule–macromolecule and 12 peptide–macromolecule systems. We observed that ANI-2x/CG-BS greatly improved the docking power, not only optimizing binding poses more effectively, particularly when the RMSD of the predicted binding pose by Glide exceeded around 5 Å, but also achieving a 26% higher success rate in identifying those native-like binding poses at the top rank compared to Glide docking. As for the scoring and ranking powers, ANI-2x/CG-BS demonstrated an enhanced performance in predicting and ranking hundreds or thousands of ligands over Glide docking. For example, Pearson’s and Spearman’s correlation coefficients remarkedly increased from 0.24 and 0.14 with Glide docking to 0.85 and 0.69, respectively, with the addition of ANI-2x/CG-BS for optimizing and ranking small molecules binding to the bacterial ribosomal aminoacyl-tRNA receptor. These results suggest that ANI-2x/CG-BS holds considerable potential for being integrated into virtual screening pipelines due to its enhanced docking performance.
more »
« less
AI ‐Assisted Protein–Peptide Complex Prediction in a Practical Setting
ABSTRACT Accurate prediction of protein–peptide complex structures plays a critical role in structure‐based drug design, including antibody design. Most peptide‐docking benchmark studies were conducted using crystal structures of protein–peptide complexes; as such, the performance of the current peptide docking tools in the practical setting is unknown. Here, the practical setting implies there are no crystal or other experimental structures for the complex, nor for the receptor and peptide. In this work, we have developed a practical docking protocol that incorporated two famous machine learning models, AlphaFold 2 for structural prediction and ANI‐2x for ab initio potential prediction, to achieve a high success rate in modeling protein–peptide complex structures. The docking protocol consists of three major stages. In the first stage, the 3D structure of the receptor is predicted by AlphaFold 2 using the monomer mode, and that of the peptide is predicted by AlphaFold 2 using the multimer mode. We found that it is essential to include the receptor information to generate a high‐quality 3D structure of the peptide. In the second stage, rigid protein–peptide docking is performed using ZDOCK software. In the last stage, the top 10 docking poses are relaxed and refined by ANI‐2x in conjunction with our in‐house geometry optimization algorithm—conjugate gradient with backtracking line search (CG‐BS). CG‐BS was developed by us to more efficiently perform geometry optimization, which takes the potential and force directly from ANI‐2x machine learning models. The docking protocol achieved a very encouraging performance for a set of 62 very challenging protein–peptide systems which had an overall success rate of 34% if only the top 1 docking poses were considered. This success rate increased to 45% if the top 3 docking poses were considered. It is emphasized that this encouraging protein–peptide docking performance was achieved without using any crystal or experimental structures.
more »
« less
- Award ID(s):
- 1955260
- PAR ID:
- 10627181
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Journal of Computational Chemistry
- Volume:
- 46
- Issue:
- 14
- ISSN:
- 0192-8651
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract In computational biology, accurate prediction of phosphopeptide-protein complex structures is essential for understanding cellular functions and advancing drug discovery and personalized medicine. While AlphaFold has significantly improved protein structure prediction, it faces accuracy challenges in predicting structures of complexes involving phosphopeptides possibly due to structural variations introduced by phosphorylation in the peptide component. Our study addresses this limitation by refining AlphaFold to improve its accuracy in modeling these complex structures. We employed weighted metrics for a comprehensive evaluation across various protein families. The enhanced model notably outperforms the original AlphaFold, showing a substantial increase in the weighted average local distance difference test (lDDT) scores for peptides: from 52.74 to 76.51 in the Top 1 model and from 56.32 to 77.91 in the Top 5 model. These advancements not only deepen our understanding of the role of phosphorylation in cellular signaling but also have extensive implications for biological research and the development of innovative therapies.more » « less
-
In recent years, the field of structural biology has seen remarkable advancements, particularly in modeling of protein tertiary and quaternary structures. The AlphaFold deep learning approach revolutionized protein structure prediction by achieving near‐experimental accuracy on many targets. This paper presents a detailed account of structural modeling of oligomeric targets in Round 55 of CAPRI by combining deep learning‐based predictions (AlphaFold2 multimer pipeline) with traditional docking techniques in a hybrid approach to protein–protein docking. To complement the AlphaFold models generated for the given oligomeric state of the targets, we built docking predictions by combining models generated for lower‐oligomeric states—dimers for trimeric targets and trimers/dimers for tetrameric targets. In addition, we used a template‐based docking procedure applied to AlphaFold predicted structures of the monomers. We analyzed the clustering of the generated AlphaFold models, the confidence in the prediction of intra‐ and inter‐chain residue‐residue contacts, and the correlation of the AlphaFold predictions stability with the quality of the submitted models.more » « less
-
Abstract The recent breakthroughs in structure prediction, where methods such as AlphaFold demonstrated near‐atomic accuracy, herald a paradigm shift in structural biology. The 200 million high‐accuracy models released in the AlphaFold Database are expected to guide protein science in the coming decades. Partitioning these AlphaFold models into domains and assigning them to an evolutionary hierarchy provide an efficient way to gain functional insights into proteins. However, classifying such a large number of predicted structures challenges the infrastructure of current structure classifications, including our Evolutionary Classification of protein Domains (ECOD). Better computational tools are urgently needed to parse and classify domains from AlphaFold models automatically. Here we present a Domain Parser for AlphaFold Models (DPAM) that can automatically recognize globular domains from these models based on inter‐residue distances in 3D structures, predicted aligned errors, and ECOD domains found by sequence (HHsuite) and structural (Dali) similarity searches. Based on a benchmark of 18,759 AlphaFold models, we demonstrate that DPAM can recognize 98.8% of domains and assign correct boundaries for 87.5%, significantly outperforming structure‐based domain parsers and homology‐based domain assignment using ECOD domains found by HHsuite or Dali. Application of DPAM to the massive AlphaFold models will enable efficient classification of domains, providing evolutionary contexts and facilitating functional studies.more » « 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 Manuscript
- Journal Article:
- https://doi.org/10.1002/jcc.70137
