Browse
Submit Data
Databases
API
Help

Dataset Information

25 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Incorporating Explicit Water Molecules and Ligand Conformation Stability in Machine-Learning Scoring Functions.

ABSTRACT: Structure-based drug design is critically dependent on accuracy of molecular docking scoring functions, and there is of significant interest to advance scoring functions with machine learning approaches. In this work, by judiciously expanding the training set, exploring new features related to explicit mediating water molecules as well as ligand conformation stability, and applying extreme gradient boosting (XGBoost) with ?-Vina parametrization, we have improved robustness and applicability of machine-learning scoring functions. The new scoring function ?vinaXGB can not only perform consistently among the top compared to classical scoring functions for the CASF-2016 benchmark but also achieves significantly better prediction accuracy in different types of structures that mimic real docking applications.

SUBMITTER: Lu J

PROVIDER: S-EPMC6878146 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Incorporating Explicit Water Molecules and Ligand Conformation Stability in Machine-Learning Scoring Functions.

Lu Jianing J Hou Xuben X Wang Cheng C Zhang Yingkai Y

Journal of chemical information and modeling 20191031 11

Structure-based drug design is critically dependent on accuracy of molecular docking scoring functions, and there is of significant interest to advance scoring functions with machine learning approaches. In this work, by judiciously expanding the training set, exploring new features related to explicit mediating water molecules as well as ligand conformation stability, and applying extreme gradient boosting (XGBoost) with Δ-Vina parametrization, we have improved robustness and applicability of m ...[more]

PMID: 31638801

Similar Datasets

Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints.

Project description:We propose a novel machine-learning-based scoring function for drug discovery that incorporates ligand and protein structural information into a knowledge-based PMF score. Molecular docking, a simulation method for structure-based drug design (SBDD), is expected to reduce the enormous costs associated with conventional experimental methods in terms of rational drug discovery. Molecular docking has two main purposes: to predict ligand-binding structures for target proteins and to predict protein-ligand binding affinity. Currently available programs of molecular docking offer an accurate prediction of ligand binding structures for many systems. However, the accurate prediction of binding affinity remains challenging. In this study, we developed a new scoring function that incorporates fingerprints representing ligand and protein structures as descriptors in the PMF score. Here, regression analysis of the scoring function was performed using the following machine learning techniques: least absolute shrinkage and selection operator (LASSO) and light gradient boosting machine (LightGBM). The results on a test data set showed that the binding affinity delivered by the newly developed scoring function has a Pearson correlation coefficient of 0.79 with the experimental value, which surpasses that of the conventional scoring functions. Further analysis provided a chemical understanding of the descriptors that contributed significantly to the improvement in prediction accuracy. Our approach and findings are useful for rational drug discovery.

| S-EPMC9178954 | biostudies-literature

Towards ligand docking including explicit interface water molecules.

Project description:Small molecule docking predicts the interaction of a small molecule ligand with a protein at atomic-detail accuracy including position and conformation the ligand but also conformational changes of the protein upon ligand binding. While successful in the majority of cases, docking algorithms including RosettaLigand fail in some cases to predict the correct protein/ligand complex structure. In this study we show that simultaneous docking of explicit interface water molecules greatly improves Rosetta's ability to distinguish correct from incorrect ligand poses. This result holds true for both protein-centric water docking wherein waters are located relative to the protein binding site and ligand-centric water docking wherein waters move with the ligand during docking. Protein-centric docking is used to model 99 HIV-1 protease/protease inhibitor structures. We find protease inhibitor placement improving at a ratio of 9:1 when one critical interface water molecule is included in the docking simulation. Ligand-centric docking is applied to 341 structures from the CSAR benchmark of diverse protein/ligand complexes [1]. Across this diverse dataset we see up to 56% recovery of failed docking studies, when waters are included in the docking simulation.

| S-EPMC3695863 | biostudies-literature

Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein-Ligand Scoring Functions.

Project description:Protein-ligand scoring functions are widely used in structure-based drug design for fast evaluation of protein-ligand interactions, and it is of strong interest to develop scoring functions with machine-learning approaches. In this work, by expanding the training set, developing physically meaningful features, employing our recently developed linear empirical scoring function Lin_F9 (Yang, C. J. Chem. Inf. Model. 2021, 61, 4630-4644) as the baseline, and applying extreme gradient boosting (XGBoost) with Δ-machine learning, we have further improved the robustness and applicability of machine-learning scoring functions. Besides the top performances for scoring-ranking-screening power tests of the CASF-2016 benchmark, the new scoring function ΔLin_F9XGB also achieves superior scoring and ranking performances in different structure types that mimic real docking applications. The scoring powers of ΔLin_F9XGB for locally optimized poses, flexible redocked poses, and ensemble docked poses of the CASF-2016 core set achieve Pearson's correlation coefficient (R) values of 0.853, 0.839, and 0.813, respectively. In addition, the large-scale docking-based virtual screening test on the LIT-PCBA data set demonstrates the reliability and robustness of ΔLin_F9XGB in virtual screening application. The ΔLin_F9XGB scoring function and its code are freely available on the web at (https://yzhang.hpc.nyu.edu/Delta_LinF9_XGB).

| S-EPMC9197983 | biostudies-literature

Systematic placement of structural water molecules for improved scoring of protein-ligand interactions.

Project description:Structural water molecules are found in many protein-ligand complexes. They are known to be vital in mediating hydrogen-bonding interactions and, in some cases, key for facilitating tight binding. It is thus very important to consider water molecules when attempting to model protein-ligand interactions for cognate ligand identification, virtual screening and drug design. While the rigid treatment of water molecules present in structures is feasible, the more relevant task of treating all possible positions and orientations of water molecules with each possible ligand pose is computationally daunting. Current methods in molecular docking provide partial treatment for such water molecules, with modest success. Here we describe a new method employing dead-end elimination to place water molecules within a binding site, bridging interactions between protein and ligand. Dead-end elimination permits a thorough, though still incomplete, treatment of water placement. The results show that this method is able to place water molecules correctly within known complexes and to create physically reasonable hydrogen bonds. The approach has also been incorporated within an inverse molecular design approach, to model a variety of compounds in the process of de novo ligand design. The inclusion of structural water molecules, combined with ranking based on the electrostatic contribution to binding affinity, improves a number of otherwise poor energetic predictions.

| S-EPMC3170077 | biostudies-literature

AutoDock-GIST: Incorporating Thermodynamics of Active-Site Water into Scoring Function for Accurate Protein-Ligand Docking.

Project description:Water plays a significant role in the binding process between protein and ligand. However, the thermodynamics of water molecules are often underestimated, or even ignored, in protein-ligand docking. Usually, the free energies of active-site water molecules are substantially different from those of waters in the bulk region. The binding of a ligand to a protein causes a displacement of these waters from an active site to bulk, and this displacement process substantially contributes to the free energy change of protein-ligand binding. The free energy of active-site water molecules can be calculated by grid inhomogeneous solvation theory (GIST), using molecular dynamics (MD) and the trajectory of a target protein and water molecules. Here, we show a case study of the combination of GIST and a docking program and discuss the effectiveness of the displacing gain of unfavorable water in protein-ligand docking. We combined the GIST-based desolvation function with the scoring function of AutoDock4, which is called AutoDock-GIST. The proposed scoring function was assessed employing 51 ligands of coagulation factor Xa (FXa), and results showed that both scoring accuracy and docking success rate were improved. We also evaluated virtual screening performance of AutoDock-GIST using FXa ligands in the directory of useful decoys-enhanced (DUD-E), thus finding that the displacing gain of unfavorable water is effective for a successful docking campaign.

| S-EPMC6274120 | biostudies-literature

Dynamics of water molecules in the bacteriorhodopsin trimer in explicit lipid/water environment.

Project description:Protonated networks of internal water molecules appear to be involved in proton transfer in various integral membrane proteins. High-resolution x-ray studies of protein crystals at low temperature deliver mean positions of most internal waters, but only limited information about fluctuations within such H-bonded networks formed by water and residues. The question arises as to how water molecules behave inside and on the surface of a fluctuating membrane protein under more physiological conditions. Therefore, as an example, long-time molecular dynamics simulations of bacteriorhodopsin were performed with explicit membrane/water environment. Based on a recent x-ray model the bacteriorhodopsin trimer was inserted in a fully solvated 16 x 16 1-palmitoyl-2-oleoyl-sn-glycero-3-phosphocholine (POPC)-bilayer patch, resulting in a system of approximately 84,000 atoms. Unrestrained molecular dynamics calculations of 5 ns were performed using the GROMACS package and force field. Mean water densities were computed to describe the anisotropic distribution of internal water molecules. In the whole protein two larger areas of higher water density are identified. They are located between the central proton binding site, the Schiff base, and the extracellular proton release site. Separated by Arg-82 these water clusters could provide a proton release pathway in a Grotthus-like mechanism as indicated by a continuum absorbance change observed during the photocycle by time-resolved Fourier transform infrared spectroscopy. Residues are identified which are H-bonded to the water clusters and are therefore facilitating proton conduction. Their influence on proton transfer via the H-bonded network as indicated by the continuum absorbance change is predicted. This may explain why several site-directed mutations alter the proton release kinetics without a direct involvement in proton transfer.

| S-EPMC1303921 | biostudies-literature

Dissecting the Influence of Protein Flexibility on the Location and Thermodynamic Profile of Explicit Water Molecules in Protein-Ligand Binding.

Project description:Explicit water molecules in the binding site of proteins play a crucial role for protein-ligand association. Recent advances in computer-aided drug discovery methodology allow for an accurate prediction of the localized position and thermodynamic profile of water molecules (i.e., hydration sites) in the binding site. The underlying calculations are based on MD simulations of explicit water molecules in a restrained protein structure. However, the ligand-binding process is typically associated with protein conformational change that influences the position and thermodynamic properties of the hydration site. In this manuscript, we present the developments of two methods to incorporate the influence of protein conformational change on hydration sites either by following the conformational transition step-by-step (method I) or to match the hydration sites of the two transition end states using local coordinate systems (method II). Using these methods, we highlight the difference in the estimated protein desolvation free energy with and without inclusion of protein flexibility. To the best of our knowledge, this is the first study that explicitly studies the influence of protein conformational change on the position and thermodynamic profiles of water molecules and provides methodology to incorporate protein flexibility into the estimation of the desolvation free energy.

| S-EPMC5397387 | biostudies-literature

Improving scoring-docking-screening powers of protein-ligand scoring functions using random forest.

Project description:The development of new protein-ligand scoring functions using machine learning algorithms, such as random forest, has been of significant interest. By efficiently utilizing expanded feature sets and a large set of experimental data, random forest based scoring functions (RFbScore) can achieve better correlations to experimental protein-ligand binding data with known crystal structures; however, more extensive tests indicate that such enhancement in scoring power comes with significant under-performance in docking and screening power tests compared to traditional scoring functions. In this work, to improve scoring-docking-screening powers of protein-ligand docking functions simultaneously, we have introduced a ?vina RF parameterization and feature selection framework based on random forest. Our developed scoring function ?vina RF20 , which employs 20 descriptors in addition to the AutoDock Vina score, can achieve superior performance in all power tests of both CASF-2013 and CASF-2007 benchmarks compared to classical scoring functions. The ?vina RF20 scoring function and its code are freely available on the web at: https://www.nyu.edu/projects/yzhang/DeltaVina. © 2016 Wiley Periodicals, Inc.

| S-EPMC5140681 | biostudies-literature

PlaceWaters: Real-time, explicit interface water sampling during Rosetta ligand docking.

Project description:Water molecules at the protein-small molecule interface often form hydrogen bonds with both the small molecule ligand and the protein, affecting the structural integrity and energetics of a binding event. The inclusion of these 'bridging waters' has been shown to improve the accuracy of predicted docked structures; however, due to increased computational costs, this step is typically omitted in ligand docking simulations. In this study, we introduce a resource-efficient, Rosetta-based protocol named "PlaceWaters" to predict the location of explicit interface bridging waters during a ligand docking simulation. In contrast to other explicit water methods, this protocol is independent of knowledge of number and location of crystallographic waters in homologous structures. We test this method on a diverse protein-small molecule benchmark set in comparison to other Rosetta-based protocols. Our results suggest that this coarse-grained, structure-based approach quickly and accurately predicts the location of bridging waters, improving our ability to computationally screen drug candidates.

| S-EPMC9154094 | biostudies-literature

XLPFE: A Simple and Effective Machine Learning Scoring Function for Protein-Ligand Scoring and Ranking.

Project description:Prediction of protein-ligand binding affinities is a central issue in structure-based computer-aided drug design. In recent years, much effort has been devoted to the prediction of the binding affinity in protein-ligand complexes using machine learning (ML). Due to the remarkable ability of ML methods in nonlinear fitting, ML-based scoring functions (SFs) can deliver much improved performance on a selected test set, such as the comparative assessment of scoring functions (CASF), when compared to the classical SFs. However, the performance of ML-based SFs heavily relies on the overall similarity of the training set and the test set. To improve the performance and transferability of an SF, we have tried to combine various features including energy terms from X-score and AutoDock Vina, the properties of ligands, and the statistical sequence-related information from either the binding site or the full protein. In conjunction with extreme trees (ET), an ML model, we have developed XLPFE, a new SF. Compared with other tested methods such as X-score, AutoDock Vina, ΔvinaXGB, PSH-ML, or CNN-score, XLPFE achieves consistently better scoring and ranking power for various types of protein-ligand complex structures beyond the CASF, suggesting that XLPFE has superior transferability. In particular, XLPFE performs better with metalloenzymes. With its faster speed, improved accuracy, and better transferability, XLPFE could be usefully applied to a diverse range of protein-ligand complexes.

| S-EPMC9245135 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data