Characterization of small molecule binding. I. Accurate identification of strong inhibitors in virtual screening

An overview of recent advances and challenges in predicting compound-protein interaction (CPI)

Compound-protein interactions (CPIs) are critical in drug discovery for identifying therapeutic targets, drug side effects, and repurposing existing drugs. Machine learning (ML) algorithms have emerged as powerful tools for CPI prediction, offering notable advantages in cost-effectiveness and efficiency. This review provides an overview of recent advances in both structure-based and non-structure-based CPI prediction ML models, highlighting their performance and achievements. It also offers insights into CPI prediction-related datasets and evaluation benchmarks. Lastly, the article presents a comprehensive assessment of the current landscape of CPI prediction, elucidating the challenges faced and outlining emerging trends to advance the field.

Application of computational methods for class A GPCR Ligand discovery

G protein-coupled receptors (GPCR) are integral membrane proteins of considerable interest as targets for drug development due to their role in transmitting cellular signals in a multitude of biological processes. Of the six classes categorizing GPCR (A, B, C, D, E, and F), class A contains the largest number of therapeutically relevant GPCR. Despite their importance as drug targets, many challenges exist for the discovery of novel class A GPCR ligands serving as drug precursors. Though knowledge of the structural and functional characteristics of GPCR has grown significantly over the past 20 years, a large portion of GPCR lack reported, experimentally determined structures. Furthermore, many GPCR have no known endogenous and/or synthetic ligands, limiting further exploration of their biochemical, cellular, and physiological roles. While many successes in GPCR ligand discovery have resulted from experimental high-throughput screening, computational methods have played an increasingly important role in GPCR ligand identification in the past decade. Here we discuss computational techniques applied to GPCR ligand discovery. This review summarizes class A GPCR structure/function and provides an overview of many obstacles currently faced in GPCR ligand discovery. Furthermore, we discuss applications and recent successes of computational techniques used to predict GPCR structure as well as present a summary of ligand- and structure-based methods used to identify potential GPCR ligands. Finally, we discuss computational hit list generation and refinement and provide comprehensive workflows for GPCR ligand identification.

Determination of Molecule Category of Ligands Targeting the Ligand-Binding Pocket of Nuclear Receptors with Structural Elucidation and Machine Learning

The mechanism of transcriptional activation/repression of the nuclear receptors (NRs) involves two main conformations of the NR protein, namely, the active (agonistic) and inactive (antagonistic) conformations. Binding of agonists or antagonists to the ligand-binding pocket (LBP) of NRs can regulate the downstream signaling pathways with different physiological effects. However, it is still hard to determine the molecular type of a LBP-bound ligand because both the agonists and antagonists bind to the same position of the protein. Therefore, it is necessary to develop precise and efficient methods to facilitate the discrimination of agonists and antagonists targeting the LBP of NRs. Here, combining structural and energetic analyses with machine-learning (ML) algorithms, we constructed a series of structure-based ML models to determine the molecular category of the LBP-bound ligands. We show that the proposed models work robustly and with high accuracy (ACC > 0.9) for determining the category of molecules derived from docking-based and crystallized poses. Furthermore, the models are also capable of determining the molecular category of ligands with dual opposite functions on different NRs (i.e., working as an agonist in one NR target, whereas functioning as an antagonist in another) with reasonable accuracy. The proposed method is expected to facilitate the determination of the molecular properties of ligands targeting the LBP of NRs with structural interpretation.

Using diverse potentials and scoring functions for the development of improved machine-learned models for protein-ligand affinity and docking pose prediction

The advent of computational drug discovery holds the promise of significantly reducing the effort of experimentalists, along with monetary cost. More generally, predicting the binding of small organic molecules to biological macromolecules has far-reaching implications for a range of problems, including metabolomics. However, problems such as predicting the bound structure of a protein-ligand complex along with its affinity have proven to be an enormous challenge. In recent years, machine learning-based methods have proven to be more accurate than older methods, many based on simple linear regression. Nonetheless, there remains room for improvement, as these methods are often trained on a small set of features, with a single functional form for any given physical effect, and often with little mention of the rationale behind choosing one functional form over another. Moreover, it is not entirely clear why one machine learning method is favored over another. In this work, we endeavor to undertake a comprehensive effort towards developing high-accuracy, machine-learned scoring functions, systematically investigating the effects of machine learning method and choice of features, and, when possible, providing insights into the relevant physics using methods that assess feature importance. Here, we show synergism among disparate features, yielding adjusted R² with experimental binding affinities of up to 0.871 on an independent test set and enrichment for native bound structures of up to 0.913. When purely physical terms that model enthalpic and entropic effects are used in the training, we use feature importance assessments to probe the relevant physics and hopefully guide future investigators working on this and other computational chemistry problems.

Machine learning on ligand-residue interaction profiles to significantly improve binding affinity prediction

Structure-based virtual screenings (SBVSs) play an important role in drug discovery projects. However, it is still a challenge to accurately predict the binding affinity of an arbitrary molecule binds to a drug target and prioritize top ligands from an SBVS. In this study, we developed a novel method, using ligand-residue interaction profiles (IPs) to construct machine learning (ML)-based prediction models, to significantly improve the screening performance in SBVSs. Such a kind of the prediction model is called an IP scoring function (IP-SF). We systematically investigated how to improve the performance of IP-SFs from many perspectives, including the sampling methods before interaction energy calculation and different ML algorithms. Using six drug targets with each having hundreds of known ligands, we conducted a critical evaluation on the developed IP-SFs. The IP-SFs employing a gradient boosting decision tree (GBDT) algorithm in conjunction with the MIN + GB simulation protocol achieved the best overall performance. Its scoring power, ranking power and screening power significantly outperformed the Glide SF. First, compared with Glide, the average values of mean absolute error and root mean square error of GBDT/MIN + GB decreased about 38 and 36%, respectively. Second, the mean values of squared correlation coefficient and predictive index increased about 225 and 73%, respectively. Third, more encouragingly, the average value of the areas under the curve of receiver operating characteristic for six targets by GBDT, 0.87, is significantly better than that by Glide, which is only 0.71. Thus, we expected IP-SFs to have broad and promising applications in SBVSs.

Beware of the generic machine learning-based scoring functions in structure-based virtual screening

Machine learning-based scoring functions (MLSFs) have attracted extensive attention recently and are expected to be potential rescoring tools for structure-based virtual screening (SBVS). However, a major concern nowadays is whether MLSFs trained for generic uses rather than a given target can consistently be applicable for VS. In this study, a systematic assessment was carried out to re-evaluate the effectiveness of 14 reported MLSFs in VS. Overall, most of these MLSFs could hardly achieve satisfactory results for any dataset, and they could even not outperform the baseline of classical SFs such as Glide SP. An exception was observed for RFscore-VS trained on the Directory of Useful Decoys-Enhanced dataset, which showed its superiority for most targets. However, in most cases, it clearly illustrated rather limited performance on the targets that were dissimilar to the proteins in the corresponding training sets. We also used the top three docking poses rather than the top one for rescoring and retrained the models with the updated versions of the training set, but only minor improvements were observed. Taken together, generic MLSFs may have poor generalization capabilities to be applicable for the real VS campaigns. Therefore, it should be quite cautious to use this type of methods for VS.

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

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.

Combined strategies in structure-based virtual screening

The identification and optimization of lead compounds are inalienable components in drug design and discovery pipelines. As a powerful computational approach for the identification of hits with novel structural scaffolds, structure-based virtual screening (SBVS) has exhibited a remarkably increasing influence in the early stages of drug discovery. During the past decade, a variety of techniques and algorithms have been proposed and tested with different purposes in the scope of SBVS. Although SBVS has been a common and proven technology, it still shows some challenges and problems that are needed to be addressed, where the negative influence regardless of protein flexibility and the inaccurate prediction of binding affinity are the two major challenges. Here, focusing on these difficulties, we summarize a series of combined strategies or workflows developed by our group and others. Furthermore, several representative successful applications from recent publications are also discussed to demonstrate the effectiveness of the combined SBVS strategies in drug discovery campaigns.

Can machine learning consistently improve the scoring power of classical scoring functions? Insights into the role of machine learning in scoring functions

How to accurately estimate protein-ligand binding affinity remains a key challenge in computer-aided drug design (CADD). In many cases, it has been shown that the binding affinities predicted by classical scoring functions (SFs) cannot correlate well with experimentally measured biological activities. In the past few years, machine learning (ML)-based SFs have gradually emerged as potential alternatives and outperformed classical SFs in a series of studies. In this study, to better recognize the potential of classical SFs, we have conducted a comparative assessment of 25 commonly used SFs. Accordingly, the scoring power was systematically estimated by using the state-of-the-art ML methods that replaced the original multiple linear regression method to refit individual energy terms. The results show that the newly-developed ML-based SFs consistently performed better than classical ones. In particular, gradient boosting decision tree (GBDT) and random forest (RF) achieved the best predictions in most cases. The newly-developed ML-based SFs were also tested on another benchmark modified from PDBbind v2007, and the impacts of structural and sequence similarities were evaluated. The results indicated that the superiority of the ML-based SFs could be fully guaranteed when sufficient similar targets were contained in the training set. Moreover, the effect of the combinations of features from multiple SFs was explored, and the results indicated that combining NNscore2.0 with one to four other classical SFs could yield the best scoring power. However, it was not applicable to derive a generic target-specific SF or SF combination.

Characterizing Protein-Ligand Binding Using Atomistic Simulation and Machine Learning: Application to Drug Resistance in HIV-1 Protease

Over the past several decades, atomistic simulations of biomolecules, whether carried out using molecular dynamics or Monte Carlo techniques, have provided detailed insights into their function. Comparing the results of such simulations for a few closely related systems has guided our understanding of the mechanisms by which changes such as ligand binding or mutation can alter the function. The general problem of detecting and interpreting such mechanisms from simulations of many related systems, however, remains a challenge. This problem is addressed here by applying supervised and unsupervised machine learning techniques to a variety of thermodynamic observables extracted from molecular dynamics simulations of different systems. As an important test case, these methods are applied to understand the evasion by human immunodeficiency virus type-1 (HIV-1) protease of darunavir, a potent inhibitor to which resistance can develop via the simultaneous mutation of multiple amino acids. Complex mutational patterns have been observed among resistant strains, presenting a challenge to developing a mechanistic picture of resistance in the protease. In order to dissect these patterns and gain mechanistic insight into the role of specific mutations, molecular dynamics simulations were carried out on a collection of HIV-1 protease variants, chosen to include highly resistant strains and susceptible controls, in complex with darunavir. Using a machine learning approach that takes advantage of the hierarchical nature in the relationships among the sequence, structure, and function, an integrative analysis of these trajectories reveals key details of the resistance mechanism, including changes in the protein structure, hydrogen bonding, and protein-ligand contacts.

An Overview of Scoring Functions Used for Protein-Ligand Interactions in Molecular Docking

Currently, molecular docking is becoming a key tool in drug discovery and molecular modeling applications. The reliability of molecular docking depends on the accuracy of the adopted scoring function, which can guide and determine the ligand poses when thousands of possible poses of ligand are generated. The scoring function can be used to determine the binding mode and site of a ligand, predict binding affinity and identify the potential drug leads for a given protein target. Despite intensive research over the years, accurate and rapid prediction of protein-ligand interactions is still a challenge in molecular docking. For this reason, this study reviews four basic types of scoring functions, physics-based, empirical, knowledge-based, and machine learning-based scoring functions, based on an up-to-date classification scheme. We not only discuss the foundations of the four types scoring functions, suitable application areas and shortcomings, but also discuss challenges and potential future study directions.

Building Machine-Learning Scoring Functions for Structure-Based Prediction of Intermolecular Binding Affinity

Molecular docking enables large-scale prediction of whether and how small molecules bind to a macromolecular target. Machine-learning scoring functions are particularly well suited to predict the strength of this interaction. Here we describe how to build RF-Score, a scoring function utilizing the machine-learning technique known as Random Forest (RF). We also point out how to use different data, features, and regression models using either R or Python programming languages.

Empirical Scoring Functions for Structure-Based Virtual Screening: Applications, Critical Aspects, and Challenges

Structure-based virtual screening (VS) is a widely used approach that employs the knowledge of the three-dimensional structure of the target of interest in the design of new lead compounds from large-scale molecular docking experiments. Through the prediction of the binding mode and affinity of a small molecule within the binding site of the target of interest, it is possible to understand important properties related to the binding process. Empirical scoring functions are widely used for pose and affinity prediction. Although pose prediction is performed with satisfactory accuracy, the correct prediction of binding affinity is still a challenging task and crucial for the success of structure-based VS experiments. There are several efforts in distinct fronts to develop even more sophisticated and accurate models for filtering and ranking large libraries of compounds. This paper will cover some recent successful applications and methodological advances, including strategies to explore the ligand entropy and solvent effects, training with sophisticated machine-learning techniques, and the use of quantum mechanics. Particular emphasis will be given to the discussion of critical aspects and further directions for the development of more accurate empirical scoring functions.

The Impact of Protein Structure and Sequence Similarity on the Accuracy of Machine-Learning Scoring Functions for Binding Affinity Prediction

It has recently been claimed that the outstanding performance of machine-learning scoring functions (SFs) is exclusively due to the presence of training complexes with highly similar proteins to those in the test set. Here, we revisit this question using 24 similarity-based training sets, a widely used test set, and four SFs. Three of these SFs employ machine learning instead of the classical linear regression approach of the fourth SF (X-Score which has the best test set performance out of 16 classical SFs). We have found that random forest (RF)-based RF-Score-v3 outperforms X-Score even when 68% of the most similar proteins are removed from the training set. In addition, unlike X-Score, RF-Score-v3 is able to keep learning with an increasing training set size, becoming substantially more predictive than X-Score when the full 1105 complexes are used for training. These results show that machine-learning SFs owe a substantial part of their performance to training on complexes with dissimilar proteins to those in the test set, against what has been previously concluded using the same data. Given that a growing amount of structural and interaction data will be available from academic and industrial sources, this performance gap between machine-learning SFs and classical SFs is expected to enlarge in the future.

Strategies of Virtual Screening in Medicinal Chemistry

Virtual screening represents an effective computational strategy to rise-up the chances of finding new bioactive compounds by accelerating the time needed to move from an initial intuition to market. Classically, the most pursued approaches rely on ligand- and structure-based studies, the former employed when structural data information about the target is missing while the latter employed when X-ray/NMR solved or homology models are instead available for the target. The authors will focus on the most advanced techniques applied in this area. In particular, they will survey the key concepts of virtual screening by discussing how to properly select chemical libraries, how to make database curation, how to applying and- and structure-based techniques, how to wisely use post-processing methods. Emphasis will be also given to the most meaningful databases used in VS protocols. For the ease of discussion several examples will be presented.

Performance of machine-learning scoring functions in structure-based virtual screening

Classical scoring functions have reached a plateau in their performance in virtual screening and binding affinity prediction. Recently, machine-learning scoring functions trained on protein-ligand complexes have shown great promise in small tailored studies. They have also raised controversy, specifically concerning model overfitting and applicability to novel targets. Here we provide a new ready-to-use scoring function (RF-Score-VS) trained on 15 426 active and 893 897 inactive molecules docked to a set of 102 targets. We use the full DUD-E data sets along with three docking tools, five classical and three machine-learning scoring functions for model building and performance assessment. Our results show RF-Score-VS can substantially improve virtual screening performance: RF-Score-VS top 1% provides 55.6% hit rate, whereas that of Vina only 16.2% (for smaller percent the difference is even more encouraging: RF-Score-VS top 0.1% achieves 88.6% hit rate for 27.5% using Vina). In addition, RF-Score-VS provides much better prediction of measured binding affinity than Vina (Pearson correlation of 0.56 and −0.18, respectively). Lastly, we test RF-Score-VS on an independent test set from the DEKOIS benchmark and observed comparable results. We provide full data sets to facilitate further research in this area (http://github.com/oddt/rfscorevs) as well as ready-to-use RF-Score-VS (http://github.com/oddt/rfscorevs_binary).

Prediction of luciferase inhibitors by the high-performance MIEC-GBDT approach based on interaction energetic patterns

The MIEC-GBDT model can be used as a powerful tool to identify potential interference compounds in luciferase-based high-throughput screening.

Improving scoring-docking-screening powers of protein-ligand scoring functions using random forest

The development of new protein-ligand scoring functions using machine learning algorithms, such as random forest, has been of significant interest. By efficiently utilizing expanded feature sets and a large set of experimental data, random forest based scoring functions (RFbScore) can achieve better correlations to experimental protein-ligand binding data with known crystal structures; however, more extensive tests indicate that such enhancement in scoring power comes with significant under-performance in docking and screening power tests compared to traditional scoring functions. In this work, to improve scoring-docking-screening powers of protein-ligand docking functions simultaneously, we have introduced a Δ_vina RF parameterization and feature selection framework based on random forest. Our developed scoring function Δ_vina RF₂₀ , which employs 20 descriptors in addition to the AutoDock Vina score, can achieve superior performance in all power tests of both CASF-2013 and CASF-2007 benchmarks compared to classical scoring functions. The Δ_vina RF₂₀ scoring function and its code are freely available on the web at: https://www.nyu.edu/projects/yzhang/DeltaVina. © 2016 Wiley Periodicals, Inc.

Constructing and Validating High-Performance MIEC-SVM Models in Virtual Screening for Kinases: A Better Way for Actives Discovery

The MIEC-SVM approach, which combines molecular interaction energy components (MIEC) derived from free energy decomposition and support vector machine (SVM), has been found effective in capturing the energetic patterns of protein-peptide recognition. However, the performance of this approach in identifying small molecule inhibitors of drug targets has not been well assessed and validated by experiments. Thereafter, by combining different model construction protocols, the issues related to developing best MIEC-SVM models were firstly discussed upon three kinase targets (ABL, ALK, and BRAF). As for the investigated targets, the optimized MIEC-SVM models performed much better than the models based on the default SVM parameters and Autodock for the tested datasets. Then, the proposed strategy was utilized to screen the Specs database for discovering potential inhibitors of the ALK kinase. The experimental results showed that the optimized MIEC-SVM model, which identified 7 actives with IC50 < 10 μM from 50 purchased compounds (namely hit rate of 14%, and 4 in nM level) and performed much better than Autodock (3 actives with IC50 < 10 μM from 50 purchased compounds, namely hit rate of 6%, and 2 in nM level), suggesting that the proposed strategy is a powerful tool in structure-based virtual screening.

MIEC-SVM: automated pipeline for protein peptide/ligand interaction prediction

MOTIVATION

MIEC-SVM is a structure-based method for predicting protein recognition specificity. Here, we present an automated MIEC-SVM pipeline providing an integrated and user-friendly workflow for construction and application of the MIEC-SVM models. This pipeline can handle standard amino acids and those with post-translational modifications (PTMs) or small molecules. Moreover, multi-threading and support to Sun Grid Engine (SGE) are implemented to significantly boost the computational efficiency.

AVAILABILITY AND IMPLEMENTATION

The program is available at http://wanglab.ucsd.edu/MIEC-SVM CONTACT: : wei-wang@ucsd.edu

SUPPLEMENTARY INFORMATION

Supplementary data available at Bioinformatics online.

Machine-learning scoring functions to improve structure-based binding affinity prediction and virtual screening

Docking tools to predict whether and how a small molecule binds to a target can be applied if a structural model of such target is available. The reliability of docking depends, however, on the accuracy of the adopted scoring function (SF). Despite intense research over the years, improving the accuracy of SFs for structure-based binding affinity prediction or virtual screening has proven to be a challenging task for any class of method. New SFs based on modern machine-learning regression models, which do not impose a predetermined functional form and thus are able to exploit effectively much larger amounts of experimental data, have recently been introduced. These machine-learning SFs have been shown to outperform a wide range of classical SFs at both binding affinity prediction and virtual screening. The emerging picture from these studies is that the classical approach of using linear regression with a small number of expert-selected structural features can be strongly improved by a machine-learning approach based on nonlinear regression allied with comprehensive data-driven feature selection. Furthermore, the performance of classical SFs does not grow with larger training datasets and hence this performance gap is expected to widen as more training data becomes available in the future. Other topics covered in this review include predicting the reliability of a SF on a particular target class, generating synthetic data to improve predictive performance and modeling guidelines for SF development. WIREs Comput Mol Sci 2015, 5:405-424. doi: 10.1002/wcms.1225 For further resources related to this article, please visit the WIREs website.

Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest

Docking scoring functions can be used to predict the strength of protein-ligand binding. It is widely believed that training a scoring function with low-quality data is detrimental for its predictive performance. Nevertheless, there is a surprising lack of systematic validation experiments in support of this hypothesis. In this study, we investigated to which extent training a scoring function with data containing low-quality structural and binding data is detrimental for predictive performance. We actually found that low-quality data is not only non-detrimental, but beneficial for the predictive performance of machine-learning scoring functions, though the improvement is less important than that coming from high-quality data. Furthermore, we observed that classical scoring functions are not able to effectively exploit data beyond an early threshold, regardless of its quality. This demonstrates that exploiting a larger data volume is more important for the performance of machine-learning scoring functions than restricting to a smaller set of higher data quality.

Structure-based virtual screening for drug discovery: principles, applications and recent advances

Structure-based drug discovery (SBDD) is becoming an essential tool in assisting fast and cost-efficient lead discovery and optimization. The application of rational, structure-based drug design is proven to be more efficient than the traditional way of drug discovery since it aims to understand the molecular basis of a disease and utilizes the knowledge of the three-dimensional structure of the biological target in the process. In this review, we focus on the principles and applications of Virtual Screening (VS) within the context of SBDD and examine different procedures ranging from the initial stages of the process that include receptor and library pre-processing, to docking, scoring and post-processing of topscoring hits. Recent improvements in structure-based virtual screening (SBVS) efficiency through ensemble docking, induced fit and consensus docking are also discussed. The review highlights advances in the field within the framework of several success studies that have led to nM inhibition directly from VS and provides recent trends in library design as well as discusses limitations of the method. Applications of SBVS in the design of substrates for engineered proteins that enable the discovery of new metabolic and signal transduction pathways and the design of inhibitors of multifunctional proteins are also reviewed. Finally, we contribute two promising VS protocols recently developed by us that aim to increase inhibitor selectivity. In the first protocol, we describe the discovery of micromolar inhibitors through SBVS designed to inhibit the mutant H1047R PI3Kα kinase. Second, we discuss a strategy for the identification of selective binders for the RXRα nuclear receptor. In this protocol, a set of target structures is constructed for ensemble docking based on binding site shape characterization and clustering, aiming to enhance the hit rate of selective inhibitors for the desired protein target through the SBVS process.

Improvements, trends, and new ideas in molecular docking: 2012-2013 in review

Molecular docking is a computational method for predicting the placement of ligands in the binding sites of their receptor(s). In this review, we discuss the methodological developments that occurred in the docking field in 2012 and 2013, with a particular focus on the more difficult aspects of this computational discipline. The main challenges and therefore focal points for developments in docking, covered in this review, are receptor flexibility, solvation, scoring, and virtual screening. We specifically deal with such aspects of molecular docking and its applications as selection criteria for constructing receptor ensembles, target dependence of scoring functions, integration of higher-level theory into scoring, implicit and explicit handling of solvation in the binding process, and comparison and evaluation of docking and scoring methods.

Improving AutoDock Vina Using Random Forest: The Growing Accuracy of Binding Affinity Prediction by the Effective Exploitation of Larger Data Sets

There is a growing body of evidence showing that machine learning regression results in more accurate structure-based prediction of protein-ligand binding affinity. Docking methods that aim at optimizing the affinity of ligands for a target rely on how accurate their predicted ranking is. However, despite their proven advantages, machine-learning scoring functions are still not widely applied. This seems to be due to insufficient understanding of their properties and the lack of user-friendly software implementing them. Here we present a study where the accuracy of AutoDock Vina, arguably the most commonly-used docking software, is strongly improved by following a machine learning approach. We also analyse the factors that are responsible for this improvement and their generality. Most importantly, with the help of a proposed benchmark, we demonstrate that this improvement will be larger as more data becomes available for training Random Forest models, as regression models implying additive functional forms do not improve with more training data. We discuss how the latter opens the door to new opportunities in scoring function development. In order to facilitate the translation of this advance to enhance structure-based molecular design, we provide software to directly re-score Vina-generated poses and thus strongly improve their predicted binding affinity. The software is available at http://istar.cse.cuhk.edu.hk/rf-score-3.tgz and http://crcm. marseille.inserm.fr/fileadmin/rf-score-3.tgz.