Improving Docking-Based Virtual Screening Ability by Integrating Multiple Energy Auxiliary Terms from Molecular Docking Scoring

Abstract

Virtual Screening (VS) based on molecular docking is an efficient method used for retrieving novel hit compounds in drug discovery. However, the accuracy of the current docking scoring function (SF) is usually insufficient. In this study, in order to improve the screening power of SF, a novel approach named EAT-Score was proposed by directly utilizing the energy auxiliary terms (EAT) provided by molecular docking scoring through eXtreme Gradient Boosting (XGBoost). Here, EAT specifically refers to the output of the Molecular Operating Environment (MOE) scoring, including the energy scores of five different classical SFs and the Protein–Ligand Interaction Fingerprint (PLIF) terms. The performance of EAT-Score to discriminate actives from decoys was strictly validated on the DUD-E diverse subset by using different performance metrics. The results showed that EAT-Score performed much better than classical SFs in VS, with its AUC values exhibiting an improvement of around 0.3. Meanwhile, EAT-Score could achieve comparable even better prediction performance compared with other state-of-the-art VS methods, such as some machine learning (ML)-based SFs and classical SFs implemented in docking programs, in terms of AUC, LogAUC, or BEDROC. Furthermore, the EAT-Score model can capture important binding pattern information from protein–ligand complexes by Shapley additive explanations (SHAP) analysis, which may be very helpful in interpreting the ligand binding mechanism for a certain target and thereby guiding drug design.

Can drug repurposing strategies be the solution to the COVID-19 crisis?

“…are surprising, considering the known fact that the performance of docking studies is highly dependent on the system under study, and the high false-positive rate associated with docking-based virtual screening [48][49][50][51][52]. Some of the reviewed papers arrive at assertive conclusions despite that no proper (either in silico or experimental) validation was performed [53][54][55]: 'the docking simulation results also indicate the synergistic interactions of 10 substances in the Melaleuca cajuputi essential oil exhibit the significant inhibition into the ACE2 and PDB6LU7 proteins.…”

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

“…The features with the variance less than 0.01 were removed, followed by the standardization of the remaining features using the sklearn.preprocessing [ 66 ] module. Extreme gradient boosting (XGBoost) [ 67 ], a well-validated ML algorithm that has been widely used in the field of computer-aided drug design (CADD) [ 28 , 29 , 31 ], was utilized to construct the classification models. Some major hyper-parameters (Additional file 1 : Table S1) were tuned with the hyeropt [ 68 ] package and determined by the AUROC statistic based on the fivefold cross-validation.…”

ASFP (Artificial Intelligence based Scoring Function Platform): a web server for the development of customized scoring functions

“…Unlike traditional SFs, machine learning (ML)-based scoring functions (MLSFs) do not have particular theory-motivated functional forms, and they are developed by learning from very large volumes of protein-ligand structural and interaction data through ML algorithms, such as random forest (RF), support vector machine (SVM), artificial neural network (ANN), gradient boosting decision tree (GBDT), etc [3,[5][6][7][8]. Consequently, MLSFs have the capability to capture the non-linear relationship between protein-ligand interaction features and binding mode that are difficult to be characterized by classical SFs, thus yielding better binding strength predictions [9,10]. However, in order to develop an MLSF, we need to generate a set of features to characterize protein-ligand interactions, and furthermore we need to be familiar with ML algorithms, which may be a difficult task for non-experts.…”