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

A dataset of protein-drug complexes with experimental binding energy and crystal structure were analyzed and the performance of different docking engines and scoring functions (as well as components of these) for predicting the free energy of binding and several ligand efficiency indices were compared. The aim was not to evaluate the best docking method, but to determine the effect of different efficiency indices on the experimental and predicted free energy. Some ligand efficiency indices, such as DeltaG/W (Wiener index), DeltaG/NoC (number of carbons), and DeltaG/P (partition coefficient), improve the correlation between experimental and calculated values. This effect was shown to be valid across the different scoring functions and docking programs. It also removes the common bias of scoring functions in favor of larger ligands. For all scoring functions, the efficiency indices effectively normalize the free energy derived indices, to give values closer to experiment. Compound collection filtering can be done prior or after docking, using pharmacokinetic as well as pharmacodynamic profiles. Achieving these better correlations with experiment can improve the ability of docking scoring functions to predict active molecules in virtual screening.

There is a tendency in the literature to be critical of scoring functions when docking programs perform poorly. The assumption is that existing scoring functions need to be enhanced or new ones developed in order to improve the performance of docking programs for tasks such as pose prediction and virtual screening. However, failures can result from either sampling or scoring (or a combination of the two), although less emphasis tends to be given to the former. In this work, we use the programs GOLD and Glide on a high-quality data set to explore whether failures in pose prediction and binding affinity estimation can be attributable more to sampling or scoring. We show that identification of the correct pose (docking power) can be improved by incorporating ligand strain into the scoring function or rescoring an ensemble of diverse docking poses with MM-GBSA in a postprocessing step. We explore the use of nondefault docking settings and find that enhancing ligand sampling also improves docking power, again suggesting that sampling is more limiting than scoring for the docking programs investigated in this work. In cross-docking calculations (docking a ligand to a noncognate receptor structure) we observe a significant reduction in the accuracy of pose ranking, as expected and has been reported by others; however, we demonstrate that these alternate poses may in fact be more complementary between the ligand and the rigid receptor conformation, emphasizing that treating the receptor rigidly is an artificial constraint on the docking problem. We simulate protein flexibility by the use of multiple crystallographic conformations of a protein and demonstrate that docking results can be improved with this level of protein sampling. This work indicates the need for better sampling in docking programs, especially for the receptor. This study also highlights the variable descriptive value of RMSD as the sole arbiter of pose replication quality. It is shown that ligand poses within 2 Å of the crystallographic one can show dramatic differences in calculated relative protein-ligand energies. MM-GBSA rescoring of distinct poses overcomes some of the sensitivities of pose ranking experienced by the docking scoring functions due to protein preparation and binding site definition.

In this investigation, we describe the discovery of novel potent Pim-1 inhibitors by employing a proposed hierarchical multistage virtual screening (VS) approach, which is based on support vector machine-based (SVM-based VS or SB-VS), pharmacophore-based VS (PB-VS), and docking-based VS (DB-VS) methods. In this approach, the three VS methods are applied in an increasing order of complexity so that the first filter (SB-VS) is fast and simple, while successive ones (PB-VS and DB-VS) are more time-consuming but are applied only to a small subset of the entire database. Evaluation of this approach indicates that it can be used to screen a large chemical library rapidly with a high hit rate and a high enrichment factor. This approach was then applied to screen several large chemical libraries, including PubChem, Specs, and Enamine as well as an in-house database. From the final hits, 47 compounds were selected for further in vitro Pim-1 inhibitory assay, and 15 compounds show nanomolar level or low micromolar inhibition potency against Pim-1. In particular, four of them were found to have new scaffolds which have potential for the chemical development of Pim-1 inhibitors.

Identification of HIV-1 reverse transcriptase dual inhibitors by a combined shape-, 2D-fingerprint- and pharmacophore-based virtual screening approach

Equivariant graph neural network-based accurate and ultra-fast virtual screening of small molecules targeting miRNA-protein complex

Background: Acute kidney injury (AKI), with an increase in serum creatinine, is a common adverse drug event. Although various clinical studies have investigated whether a combination of two nephrotoxic drugs has an increased risk of AKI using traditional statistical models such as multivariable logistic regression (MLR), the evaluation metrics have not been evaluated despite the fact that traditional statistical models may over-fit the data. The aim of the present study was to detect drug-drug interactions with an increased risk of AKI by interpreting machine-learning models to avoid overfitting.Methods: We developed six machine-learning models trained using electronic medical records: MLR, logistic least absolute shrinkage and selection operator regression (LLR), random forest, extreme gradient boosting (XGB) tree, and two support vector machine models (kernel = linear function and radial basis function). In order to detect drug-drug interactions, the XGB and LLR models that showed good predictive performance were interpreted by SHapley Additive exPlanations (SHAP) and relative excess risk due to interaction (RERI), respectively.Results: Among approximately 2.5 million patients, 65,667 patients were extracted from the electronic medical records, and assigned to case (N = 5,319) and control (N = 60,348) groups. In the XGB model, a combination of loop diuretic and histamine H2 blocker [mean (|SHAP|) = 0.011] was identified as a relatively important risk factor for AKI. The combination of loop diuretic and H2 blocker showed a significant synergistic interaction on an additive scale (RERI 1.289, 95% confidence interval 0.226–5.591) also in the LLR model.Conclusion: The present population-based case-control study using interpretable machine-learning models suggested that although the relative importance of the individual and combined effects of loop diuretics and H2 blockers is lower than that of well-known risk factors such as older age and sex, concomitant use of a loop diuretic and histamine H2 blocker is associated with increased risk of AKI.

Drug discovery continues to be one of the greatest contemporary challenges and rational application of modelling approaches is the first important step to obtain lead compounds, which can be optimised further. Virtual high throughput screening (VHTS) is one of the efficient approaches to obtain lead structures for a given target. Strategic application of different screening filters like pharmacophore mapping, shape-based, ligand-based, molecular similarity etc., in combination with other drug design protocols provide invaluable insights in lead identification and optimization. Screening of large databases using these computational methods provides potential lead compounds, thus triggering a meaningful interplay between computations and experiments. In this review, we present a critical account on the relevance of molecular modelling approaches in general, lead optimization and virtual screening methods in particular for new lead identification. The importance of developing reliable scoring functions for non-bonded interactions has been highlighted, as it is an extremely important measure for the reliability of scoring function. The lead optimization and new lead design has also been illustrated with examples. The importance of employing a combination of general and target specific screening protocols has also been highlighted.

Objective: This study aims to utilize an explainable machine learning framework to identify and rank the critical protective factors that buffer against the deleterious effects of specific childhood trauma subtypes on adolescent resilience within low-socioeconomic Iraqi contexts. Methods and Materials: A cross-sectional design was employed with a sample of adolescents (mean age years; female) from low-socioeconomic districts in Iraq. Data were collected using culturally adapted and validated instruments, including the Childhood Trauma Questionnaire-Short Form (CTQ-SF), the Connor-Davidson Resilience Scale (CD-RISC), and the Resilience Scale for Adolescents (READ). To analyze the complex, non-linear relationships between variables, an eXtreme Gradient Boosting (XGBoost) machine learning model was developed. The model’s interpretability was enhanced using SHapley Additive exPlanations (SHAP) to calculate the global predictive importance and interaction effects of specific risk and protective factors. Findings: The XGBoost model demonstrated robust predictive performance, explaining a significant portion of the variance in adolescent resilience ( , ). SHAP value analysis revealed that Family Cohesion emerged as the paramount protective factor (SHAP ), while Emotional Abuse (SHAP ) and Emotional Neglect (SHAP ) were identified as the most detrimental risk factors, surpassing physical and sexual abuse in predictive weight. Furthermore, a critical non-linear threshold effect was discovered: the protective utility of peer support increased significantly only when emotional neglect scores were below a specific clinical threshold (CTQ-SF ). Conclusion: Explainable machine learning provides granular insights into trauma recovery, highlighting that emotional maltreatment profoundly damages adolescent adaptation. Interventions in low-resource settings must prioritize systemic family-based therapies to foster cohesion and adopt a phased clinical approach that addresses foundational emotional neglect before introducing peer-based support systems.

Objective: The objective of this study is to construct predictive unbiased structure-based virtual screening (SBVS) protocols to identify potent ligands for estrogen receptor alpha by combining molecular docking, protein-ligand interaction fingerprinting (PLIF), and binary quantitative structure-activity relationship (QSAR) analysis using recursive partition and regression tree method.Methods: Employing the enhanced version of a directory of useful decoys, SBVS protocols using molecular docking simulations, and PLIF were constructed and retrospectively validated. To avoid bias, SMILES format of the compounds was used. The predictive abilities of the SBVS protocols were then compared based on the enrichment factor (EF) and the F-measure values.Results: The SBVS protocols resulted in this research were SBVS_1 (employing docking scores of the best pose on every compound to rank the results and selecting compounds within 1% false positives as positive), SBVS_2 (employing decision tree resulted from the binary QSAR analysis using docking scores and PLIF bitstrings of the best pose of every compound as descriptors), and SBVS_3 (employing decision tree resulted from the binary QSAR analysis using ensemble PLIF of the selected poses from optimized docking score as the cutoff). The EF values of SBVS_1, SBVS_2, and SBVS_3 are 28.315, 576.084, and 713.472, respectively, while their F-measure values are 0.310, 0.573, and 0.769, respectively.Conclusion: Highly predictive unbiased SBVS protocols to identify potent estrogen receptor alpha ligands were constructed. Further application in prospective screening is therefore highly suggested.

Introduction: Virtual screening (VS) has emerged as an important tool in identifying bioactive compounds through computational means, by employing knowledge about the protein target or known bioactive ligands. VS has appeared as an adaptive response to the massive throughput synthesis and screening paradigm as necessity has forced the computational chemistry community to develop tools that screen against any given target and/or property millions or perhaps billions of molecules in short period of time.Areas covered: This editorial review attempts to catalog most commonly exercised VS methods, available databases for screening, advantages of VS methods along with pitfalls and technical traps with the aim to make VS as one of the most effective tools in drug discovery process. Finally, several case studies are cited where the VS technology has been applied successfully.Expert opinion: In recent times, many successful examples have been demonstrated in the field of computer-aided VS with the objective of increasing the probability of finding novel hit and lead compounds in terms of cost-effectiveness and commitment in time and material. Despite the inherent limitations, VS is still the best option now available to explore a large chemical space.

Virtual screening (VS) methods have been shown to increase success rates in many drug discovery campaigns, when they complement experimental approaches, such as high-throughput screening methods or classical medicinal chemistry approaches. Nevertheless, predictive capability of VS is not yet optimal, mainly due to limitations in the underlying physical principles describing drug binding phenomena. One approach that can improve VS methods is the aid of machine learning methods. When enough experimental data are available to train such methods, predictive capability can considerably increase. We show in this research work how a multi-objective evolutionary search strategy for feature selection, which can provide with small and accurate decision trees that can be very easily understood by chemists, can drastically increase the applicability and predictive ability of these techniques and therefore aid considerable in the drug discovery problem. With the proposed methodology, we find classification models with accuracy between 0.9934 and 1.00 and area under ROC between 0.96 and 1.00 evaluated in full training sets, and accuracy between 0.9849 and 0.9940 and area under ROC between 0.89 and 0.93 evaluated with tenfold cross-validation over 30 iterations, while substantially reducing the model size.

Eleven popular scoring functions have been tested on 100 protein-ligand complexes to evaluate their abilities to reproduce experimentally determined structures and binding affinities. They include four scoring functions implemented in the LigFit module in Cerius2 (LigScore, PLP, PMF, and LUDI), four scoring functions implemented in the CScore module in SYBYL (F-Score, G-Score, D-Score, and ChemScore), the scoring function implemented in the AutoDock program, and two stand-alone scoring functions (DrugScore and X-Score). These scoring functions are not tested in the context of a particular docking program. Instead, conformational sampling and scoring are separated into two consecutive steps. First, an exhaustive conformational sampling is performed by using the AutoDock program to generate an ensemble of docked conformations for each ligand molecule. This conformational ensemble is required to cover the entire conformational space as much as possible rather than to focus on a few energy minima. Then, each scoring function is applied to score this conformational ensemble to see if it can identify the experimentally observed conformation from all of the other decoys. Among all of the scoring functions under test, six of them, i.e., PLP, F-Score, LigScore, DrugScore, LUDI, and X-Score, yield success rates higher than the AutoDock scoring function. The success rates of these six scoring functions range from 66% to 76% if using root-mean-square deviation < or =2.0 A as the criterion. Combining any two or three of these six scoring functions into a consensus scoring scheme further improves the success rate to nearly 80% or even higher. However, when applied to reproduce the experimentally determined binding affinities of the 100 protein-ligand complexes, only X-Score, PLP, DrugScore, and G-Score are able to give correlation coefficients over 0.50. All of the 11 scoring functions are further inspected by their abilities to construct a descriptive, funnel-shaped energy surface for protein-ligand complexation. The results indicate that X-Score and DrugScore perform better than the other ones at this aspect.

The interplay between life sciences and advancing technology drives a continuous cycle of chemical data growth; these data are most often stored in open or partially open databases. In parallel, many different types of algorithms are being developed to manipulate these chemical objects and associated bioactivity data. Virtual screening methods are among the most popular computational approaches in pharmaceutical research. Today, user-friendly web-based tools are available to help scientists perform virtual screening experiments. This article provides an overview of internet resources enabling and supporting chemical biology and early drug discovery with a main emphasis on web servers dedicated to virtual ligand screening and small-molecule docking. This survey first introduces some key concepts and then presents recent and easily accessible virtual screening and related target-fishing tools as well as briefly discusses case studies enabled by some of these web services. Notwithstanding further improvements, already available web-based tools not only contribute to the design of bioactive molecules and assist drug repositioning but also help to generate new ideas and explore different hypotheses in a timely fashion while contributing to teaching in the field of drug development.

Tree-based machine learning (ML) algorithms, such as Extra Trees (ET), Random Forest (RF), Gradient Boosting Machine (GBM), and XGBoost (XGB) are among the most widely used in early drug discovery, given their versatility and performance. However, models based on these algorithms often suffer from misclassification and reduced interpretability issues, which limit their applicability in practice. To address these challenges, several approaches have been proposed, including the use of SHapley Additive Explanations (SHAP). While SHAP values are commonly used to elucidate the importance of features driving models' predictions, they can also be employed in strategies to improve their prediction performance. Building on these premises, we propose a novel approach that integrates SHAP and features value analyses to reduce misclassification in model predictions. Specifically, we benchmarked classifiers based on ET, RF, GBM, and XGB algorithms using data sets of compounds with known antiproliferative activity against three prostate cancer (PC) cell lines (i.e., PC3, LNCaP, and DU-145). The best-performing models, based on RDKit and ECFP4 descriptors with GBM and XGB algorithms, achieved MCC values above 0.58 and F1-score above 0.8 across all data sets, demonstrating satisfactory accuracy and precision. Analyses of SHAP values revealed that many misclassified compounds possess feature values that fall within the range typically associated with the opposite class. Based on these findings, we developed a misclassification-detection framework using four filtering rules, which we termed "RAW", SHAP, "RAW OR SHAP", and "RAW AND SHAP". These filtering rules successfully identified several potentially misclassified predictions, with the "RAW OR SHAP" rule retrieving up to 21%, 23%, and 63% of misclassified compounds in the PC3, DU-145, and LNCaP test sets, respectively. The developed flagging rules enable the systematic exclusion of likely misclassified compounds, even across progressively higher prediction confidence levels, thus providing a valuable approach to improve classifier performance in virtual screening applications.

Institutional delivery dropout (IDD), defined as delivery outside a health facility despite attending antenatal care (ANC), remains a significant barrier to reducing maternal mortality in Nigeria. Traditional statistical models often fall short of capturing the complex, non-linear interactions among the socio-demographic factors that drive this critical health behavior. Using a comprehensive dataset of 16,100 women from the 2018 Nigeria Demographic and Health Survey (NDHS), we applied and compared seven diverse machine learning (ML) algorithms, including models such as Support Vector Machine (SVM), Gradient Boosting (GB), and Extreme Gradient Boosting (XGBoost). The model performance was systematically evaluated using metrics such as accuracy, Area Under the Receiver Operating Characteristic curve (AUROC), F1-score, and detailed confusion matrices. Furthermore, SHapley Additive explanations (SHAP) were used to provide transparent interpretations of feature importance and predictive contributions. Gradient Boosting was the best-performing model, achieving the highest F1-score (0.755) and AUROC (0.82). SVM achieved the highest accuracy (0.740) and recall (0.780). SHAP identified education level, household wealth, and religion as strong predictors of IDD. The performance metrics reported with confidence intervals showed modest variability across the models. Machine learning approaches were effective in identifying women at an increased risk of institutional delivery dropout. SHAP analysis provides insights into the key sociodemographic predictors of IDD, highlighting the value of interpretable ML methods in maternal health research.