Journal Article10.1007/S10822-020-00305-1
Improving the binding affinity estimations of protein–ligand complexes using machine-learning facilitated force field method
18
TL;DR: A new scoring function Bappl+ is presented that is designed to predict the binding affinities of non-metallo and metallo PL complexes and outperforms other state-of-the-art scoring functions, achieving a high Pearson correlation coefficient.
read more
Abstract: Scoring functions are routinely deployed in structure-based drug design to quantify the potential for protein–ligand (PL) complex formation. Here, we present a new scoring function Bappl+ that is designed to predict the binding affinities of non-metallo and metallo PL complexes. Bappl+ outperforms other state-of-the-art scoring functions, achieving a high Pearson correlation coefficient of up to ~ 0.76 with low standard deviations. The biggest contributors to the increased performance are the use of a machine-learning model and the enlarged training dataset. We have also evaluated the performance of Bappl+ on target-specific proteins, which highlighted the limitations of our function and provides a way for further improvements. We believe that Bappl+ methodology could prove valuable in ranking candidate molecules against a target metallo or non-metallo protein by reliably predicting their binding affinities, thus helping in the drug discovery process.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Artificial intelligence in virtual screening: models versus experiments.
TL;DR: A review of machine learning and deep learning-based scoring functions for solving classification and ranking problems in drug discovery can be found in this paper , where the authors highlight studies in which ML and DL models were successfully deployed to identify lead compounds for which the experimental validations are available from bioassay studies.
96
Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents.
TL;DR: In this article, a review of machine learning/artificial intelligence-triggered effort in the brain care domain is presented, where a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drugs design, ADMET prediction, de novo drug design and drug repurposing.
13
Machine Learning Approaches for Metalloproteins
TL;DR: How machine learning tools have consolidated and expanded the comprehension of various aspects of metalloproteins (structure, function, stability, ligand-binding interactions, and inhibitors) is reviewed.
Towards a General Intermolecular Binding Affinity Calculator
Chengle Zhuang
- 11 Aug 2022
TL;DR: In this paper , a general intermolecular binding affinity calculator (GIBAC) is proposed for protein structure prediction with deep learning algorithms, which can accelerate the traditional computer-aided drug design (CADD) and artificial intelligence-integrated drug discovery (AIDD) for both small molecules and biologics such as therapeutic proteins.
9
References
Automated docking with grid-based energy evaluation
TL;DR: In this paper, the authors present a method that combines a rapid geometric docking algorithm with the evaluation of molecular mechanics interaction energies to generate feasible binding orientations of a small molecule within a site of known structure.
1K
Free Energy Calculations by the Molecular Mechanics Poisson-Boltzmann Surface Area Method.
Nadine Homeyer,Holger Gohlke +1 more
TL;DR: The Molecular Mechanics Poisson–Boltzmann Surface Area approach is an efficient method for the calculation of free energies of diverse molecular systems and has great potential that allows comparative free energy analyses for various molecular systems at low computational cost.
960
A machine learning approach to predicting protein–ligand binding affinity with applications to molecular docking
TL;DR: A novel scoring function (RF-Score) that circumvents the need for problematic modelling assumptions via non-parametric machine learning is proposed and Random Forest was used to implicitly capture binding effects that are hard to model explicitly.
916
The PDBbind database: methodologies and updates.
TL;DR: The PDBbind database is developed to provide a comprehensive collection of binding affinities for the protein-ligand complexes in the Protein Data Bank, and a total of 900 complexes were selected to form a "refined set", which is of particular value as a standard data set for docking and scoring studies.
861
Prediction of protein-ligand interactions. Docking and scoring: successes and gaps.
TL;DR: The area of calculating molecular interactions, specifically docking, the positioning of a ligand in a protein binding site, and scoring, the quality assessment of docked ligands is called attention.
647