Protein-Ligand Scoring with Convolutional Neural Networks

Abstract

Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding and structural data enables the use of deep machine learning techniques for protein-ligand scoring. We describe convolutional neural network (CNN) scoring functions that take as input a comprehensive 3D representation of a protein-ligand interaction. A CNN scoring function automatically learns the key features of protein-ligand interactions that correlate with binding. We train and optimize our CNN scoring functions to discriminate between correct and incorrect binding poses and known binders and non-binders. We find that our CNN scoring function outperforms the AutoDock Vina scoring function when ranking poses both for pose prediction and virtual screening.

References in corpus (2)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Deep learning and the Schrödinger equation

Cited by in corpus (22)

• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• Deep Reinforcement Learning for De-Novo Drug Design
• Less is more: sampling chemical space with active learning
• Autonomous discovery in the chemical sciences part II: Outlook
• Computational Protein Design with Deep Learning Neural Networks
• Quantum Machine Learning for Chemistry and Physics
• DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteins
• Deep convolutional networks for quality assessment of protein folds
• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• Visualizing Convolutional Neural Network Protein-Ligand Scoring
• Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction
• Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
• Simulations meet Machine Learning in Structural Biology
• Pre-training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding
• Advancing bioinformatics with large language models: components, applications and perspectives
• TF3P: Three-dimensional Force Fields Fingerprint Learned by Deep Capsular Network
• Supervised machine learning of ultracold atoms with speckle disorder
• Structural biology meets data science: Does anything change?
• A Novel Framework Integrating AI Model and Enzymological Experiments Promotes Identification of SARS-CoV-2 3CL Protease Inhibitors and Activity-based Probe
• Site2Vec: a reference frame invariant algorithm for vector embedding of protein-ligand binding sites
• FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
• Get Global Guarantees: On the Probabilistic Nature of Perturbation Robustness