Guiding Conventional Protein–Ligand Docking Software with Convolutional Neural Networks

Abstract

The high-performance computational techniques have brought significant benefits for drug discovery efforts in recent decades. One of the most challenging problems in drug discovery is the protein–ligand binding pose prediction. To predict the most stable structure of the complex, the performance of conventional structure-based molecular docking methods heavily depends on the accuracy of scoring or energy functions (as an approximation of affinity) for each pose of the protein–ligand docking complex to effectively guide the search in an exponentially large solution space. However, due to the heterogeneity of molecular structures, the existing scoring calculation methods are either tailored to a particular data set or fail to exhibit high accuracy. In this paper, we propose a convolutional neural network (CNN)-based model that learns to predict the stability factor of the protein–ligand complex and exhibits the ability of CNNs to improve the existing docking software. Evaluated results on PDBbind data set indicate that our approach reduces the execution time of the traditional docking-based method while improving the accuracy. Our code, experiment scripts, and pretrained models are available at .

Pepsin-like aspartic proteases (PAPs) as model systems for combining biomolecular simulation with biophysical experiments

“…If Tyr residue shows Fermi resonance in Raman spectra that gives an indication of the rotational degrees of freedom associated with the Tyr side-chain. 103 docking, [111][112][113] free energy calculations 114 (e.g. FEP, ABFE, MM/ PBSA or MM/GBSA) and biochemical assay can then be used to identify BACE-1 inhibitors (in broad sense this concept is applicable for other PAP inhibitors e.g.…”

“…Machine learning based methods ( e.g. convolutional neural network) combined with molecular docking, 111–113 free energy calculations 114 ( e.g. FEP, ABFE, MM/PBSA or MM/GBSA) and biochemical assay can then be used to identify BACE-1 inhibitors (in broad sense this concept is applicable for other PAP inhibitors e.g.…”

Fluid: a framework for approximate concurrency via controlled dependency relaxation

“…The graph coloring is based on Big-graph with the implementation in [82]. We used our own implementations for Bellman-ford and NN, and used the implementation of MedusaDock from [39]. Inputs: K-means uses three input images with different pixel diversities.…”

The impact of cross-docked poses on performance of machine learning classifier for protein–ligand binding pose prediction

“…They found that the method performed consistently well in an inter-target pose prediction test, but it could hardly beat the classical Autodock Vina in an intra-target pose ranking test, which we are more concerned about. In 2020, Morrone et al proposed a dual-graph neural network model for pose prediction, which was concatenated by a ligand-only sub-graph to store ligand structures and an interaction-based sub-graph to represent protein–ligand interaction information [ 40 ]. Similarly, this model outperformed Autodock Vina in terms of the area under the receiver operating characteristic curve (AUROC) but did not show improved performance regarding the top 1 success rate.…”