Prediction of estrogen receptor agonists and characterization of associated molecular descriptors by statistical learning methods

Comparison of Machine Learning Models on Performance of Single- and Dual-Type Electrochromic Devices

This study shows that the model fitting based on machine learning (ML) from experimental data can successfully predict the electrochromic characteristics of single- and dual-type flexible electrochromic devices (ECDs) by using tungsten trioxide (WO3) and WO3/vanadium pentoxide (V2O5), respectively. Seven different regression methods were used for experimental observations, which belong to single and dual ECDs where 80% percent was used as training data and the remaining was taken as testing data. Among the seven different regression methods, K-nearest neighbor (KNN) achieves the best results with higher coefficient of determination (R 2) score and lower root-mean-squared error (RMSE) for the bleaching state of ECDs. Furthermore, higher R 2 score and lower RMSE for the coloration state of ECDs were achieved with Gaussian process regressor. The robustness result of the ML modeling demonstrates the reliability of prediction outcomes. These results can be proposed as promising models for different energy-saving flexible electronic systems.

Prediction of in vitro and in vivo oestrogen receptor activity using hierarchical clustering

In this study, hierarchical clustering classification models were developed to predict in vitro and in vivo oestrogen receptor (ER) activity. Classification models were developed for binding, agonist, and antagonist in vitro ER activity and for mouse in vivo uterotrophic ER binding. In vitro classification models yielded balanced accuracies ranging from 0.65 to 0.85 for the external prediction set. In vivo ER classification models yielded balanced accuracies ranging from 0.72 to 0.83. If used as additional biological descriptors for in vivo models, in vitro scores were found to increase the prediction accuracy of in vivo ER models. If in vitro activity was used directly as a surrogate for in vivo activity, the results were poor (balanced accuracy ranged from 0.49 to 0.72). Under-sampling negative compounds in the training set was found to increase the coverage (fraction of chemicals which can be predicted) and increase prediction sensitivity.

Checking the STEP-Associated Trafficking and Internalization of Glutamate Receptors for Reduced Cognitive Deficits: A Machine Learning Approach-Based Cheminformatics Study and Its Application for Drug Repurposing

BACKGROUND

Alzheimer's disease, a lethal neurodegenerative disorder that leads to progressive memory loss, is the most common form of dementia. Owing to the complexity of the disease, its root cause still remains unclear. The existing anti-Alzheimer's drugs are unable to cure the disease while the current therapeutic options have provided only limited help in restoring moderate memory and remain ineffective at restricting the disease's progression. The striatal-enriched protein tyrosine phosphatase (STEP) has been shown to be involved in the internalization of the receptor, N-methyl D-aspartate (NMDR) and thus is associated with the disease. The present study was performed using machine learning algorithms, docking protocol and molecular dynamics (MD) simulations to develop STEP inhibitors, which could be novel anti-Alzheimer's molecules.

METHODS

The present study deals with the generation of computational predictive models based on chemical descriptors of compounds using machine learning approaches followed by substructure fragment analysis. To perform this analysis, the 2D molecular descriptors were generated and machine learning algorithms (Naïve Bayes, Random Forest and Sequential Minimization Optimization) were utilized. The binding mechanisms and the molecular interactions between the predicted active compounds and the target protein were modelled using docking methods. Further, the stability of the protein-ligand complex was evaluated using MD simulation studies. The substructure fragment analysis was performed using Substructure fingerprint (SubFp), which was further explored using a predefined dictionary.

RESULTS

The present study demonstrates that the computational methodology used can be employed to examine the biological activities of small molecules and prioritize them for experimental screening. Large unscreened chemical libraries can be screened to identify potential novel hits and accelerate the drug discovery process. Additionally, the chemical libraries can be searched for significant substructure patterns as reported in the present study, thus possibly contributing to the activity of these molecules.

Machine-learning approaches in drug discovery: methods and applications

During the past decade, virtual screening (VS) has evolved from traditional similarity searching, which utilizes single reference compounds, into an advanced application domain for data mining and machine-learning approaches, which require large and representative training-set compounds to learn robust decision rules. The explosive growth in the amount of public domain-available chemical and biological data has generated huge effort to design, analyze, and apply novel learning methodologies. Here, I focus on machine-learning techniques within the context of ligand-based VS (LBVS). In addition, I analyze several relevant VS studies from recent publications, providing a detailed view of the current state-of-the-art in this field and highlighting not only the problematic issues, but also the successes and opportunities for further advances.

Competitive molecular docking approach for predicting estrogen receptor subtype α agonists and antagonists

Background

Endocrine disrupting chemicals (EDCs) are exogenous compounds that interfere with the endocrine system of vertebrates, often through direct or indirect interactions with nuclear receptor proteins. Estrogen receptors (ERs) are particularly important protein targets and many EDCs are ER binders, capable of altering normal homeostatic transcription and signaling pathways. An estrogenic xenobiotic can bind ER as either an agonist or antagonist to increase or inhibit transcription, respectively. The receptor conformations in the complexes of ER bound with agonists and antagonists are different and dependent on interactions with co-regulator proteins that vary across tissue type. Assessment of chemical endocrine disruption potential depends not only on binding affinity to ERs, but also on changes that may alter the receptor conformation and its ability to subsequently bind DNA response elements and initiate transcription. Using both agonist and antagonist conformations of the ERα, we developed an in silico approach that can be used to differentiate agonist versus antagonist status of potential binders.

Methods

The approach combined separate molecular docking models for ER agonist and antagonist conformations. The ability of this approach to differentiate agonists and antagonists was first evaluated using true agonists and antagonists extracted from the crystal structures available in the protein data bank (PDB), and then further validated using a larger set of ligands from the literature. The usefulness of the approach was demonstrated with enrichment analysis in data sets with a large number of decoy ligands.

Results

The performance of individual agonist and antagonist docking models was found comparable to similar models in the literature. When combined in a competitive docking approach, they provided the ability to discriminate agonists from antagonists with good accuracy, as well as the ability to efficiently select true agonists and antagonists from decoys during enrichment analysis.

Conclusion

This approach enables evaluation of potential ER biological function changes caused by chemicals bound to the receptor which, in turn, allows the assessment of a chemical's endocrine disrupting potential. The approach can be used not only by regulatory authorities to perform risk assessments on potential EDCs but also by the industry in drug discovery projects to screen for potential agonists and antagonists.

Design of novel leads: ligand based computational modeling studies on non-nucleoside reverse transcriptase inhibitors (NNRTIs) of HIV-1

Researchers are on the constant lookout for new antiviral agents for the treatment of AIDS. In the present work, ligand based modeling studies are performed on analogues of substituted phenyl-thio-thymines, which act as non-nucleoside reverse transcriptase inhibitors (NNRTIs) and novel leads are extracted. Using alignment-dependent descriptors, based on group center overlap (SALL, HDALL, HAALL and RALL), an alignment-independent descriptor (S log P), a topological descriptor (Balaban index (J)) and a 3D descriptor dipole moment (μ) and shape based descriptors (Kappa 2 index ((2)κ)), a correlation is derived with inhibitory activity. Linear and non-linear techniques have been used to achieve the goal. Support Vector Machine (SVM, R = 0.929, R(2) = 0.863) and Back Propagation Neural Network (BPNN, R = 0.928, R(2) = 0.861) methods yielded near similar results and outperformed Multiple Linear Regression (MLR, R = 0.915, R(2) = 0.837). The predictive ability of the models are cross-validated using a test dataset (SVM: R = 0.846, R(2) = 0.716, BPNN: R = 0.841, R(2) = 0.707 and MLR: R = 0.833, R(2) = 0.694). It is concluded that the hydrophobicity (S log P) and the polarity (μ) of a ligand and the presence of hydrogen donor (HDALL) moieties are the deciding factors in improving antiviral activity and pharmaco-therapeutic properties. Based on the above findings, a virtual dataset is created to extract probable leads with reasonable antiviral activity as well as better pharmacophoric properties.

Machine learning methods in chemoinformatics

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure-activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers.

The influence of the inactives subset generation on the performance of machine learning methods

BACKGROUND

A growing popularity of machine learning methods application in virtual screening, in both classification and regression tasks, can be observed in the past few years. However, their effectiveness is strongly dependent on many different factors.

RESULTS

In this study, the influence of the way of forming the set of inactives on the classification process was examined: random and diverse selection from the ZINC database, MDDR database and libraries generated according to the DUD methodology. All learning methods were tested in two modes: using one test set, the same for each method of inactive molecules generation and using test sets with inactives prepared in an analogous way as for training. The experiments were carried out for 5 different protein targets, 3 fingerprints for molecules representation and 7 classification algorithms with varying parameters. It appeared that the process of inactive set formation had a substantial impact on the machine learning methods performance.

CONCLUSIONS

The level of chemical space limitation determined the ability of tested classifiers to select potentially active molecules in virtual screening tasks, as for example DUDs (widely applied in docking experiments) did not provide proper selection of active molecules from databases with diverse structures. The study clearly showed that inactive compounds forming training set should be representative to the highest possible extent for libraries that undergo screening.

Discovery of estrogen receptor modulators: a review of virtual screening and SAR efforts

IMPORTANCE OF THE FIELD

Virtual screening (VS) coupled with structural biology is a significantly important approach to increase the number and enhance the success of projects in lead identification stage of drug discovery process. Recent advances and future directions in estrogen therapy have resulted in great demand for identifying the potential estrogen receptor (ER) modulators with more activity and selectivity.

AREAS COVERED IN THIS REVIEW

This review presents the current state of the art in VS and structure-activity relationship of ER modulators in recent discovery, and discusses the strengths and weaknesses of the technology.

WHAT THE READER WILL GAIN

Readers will gain an overview of the current platforms of in silico screening for discovery of ER modulators; they will learn which structural information is significantly correlated with the bioactivity of ER modulators and what novel strategies should be considered for the creation of more effective chemical structures.

TAKE HOME MESSAGE

With the goal of reducing toxicity and/or improving efficacy, challenges to the successful modeling of endocrine agents are proposed, providing new paradigms for the design of ER inhibitors.

Predicting biological activity: computational approach using novel distance based molecular descriptors

Four novel distance based molecular descriptors termed as superpendentic eccentric distance sum indices 1-4 (denoted by:∫P-1EDS, ∫P-2EDS, ∫P-3EDS and ∫P-4EDS) as well as their topochemical counterparts (denoted by:∫cP-1EDS, ∫cP-2EDS, ∫cP-3EDS and ∫cP-4EDS) have been conceptualized and developed in the present study. The sensitivity towards branching, discriminating power, and degeneracy of the proposed novel descriptors were investigated. Utility of these indices was investigated for development of models through decision tree and moving average analysis for the prediction of human corticotropin releasing factor-1 receptor binding affinity of substituted pyrazines. A wide variety of 46 2D and 3D molecular descriptors including proposed indices was employed for development of models through decision tree and moving average analysis. The calculation of most of these descriptors for each compound of the dataset was performed using online E-Dragon software (version 1.0). An in-house computer programme was also employed to calculate additional topological descriptors which did not figure in E-Dragon software. The decision tree classified and correctly predicted the input data with an impressive accuracy of 92% in the training set and 71% during cross-validation. A total of three descriptors, identified by decision tree, were subsequently utilized for development of suitable models using moving average analysis. These models predicted human corticotropin releasing factor-1 receptor binding affinity with an accuracy of ≥85%. The statistical significance of models was assessed through sensitivity, specificity and Matthew's correlation coefficient. High discriminating power, high sensitivity towards branching amalgamated with negligible degeneracy offer proposed descriptors a vast potential for use in the quantitative structure-activity/property/toxicity relationships so as to facilitate drug design.

Descriptor analysis of estrogen receptor β-selective ligands using 2-phenylquinoline, tetrahydrofluorenone and 3-hydroxy 6H-benzo[c]chromen-6-one scaffolds

Estrogen receptor beta (ERβ) selective ligands have attracted much attention recently in the design of anti-cancer drugs that are devoid of the common side effects of estrogen. Structural studies of estrogen receptor alpha (ERα) and β revealed that there were considerable differences in their ligand-binding cavity and in their volume. Hence, the present study has hypothesized that size and shape descriptors can influence the affinity/selectivity of the ligands towards ERβ. To prove the same, quantitative structure-activity relationship (QSAR) analyses were carried out using multiple regression analysis on 2-phenylquinoline, tetrahydrofluorenone and 3-hydroxy-6H-benzo[c]chromen-6-one series. Results indicate that increased lipophilicity, decrease in ellipsoidal volume and width of substituents, presence of halogen atoms was essential for the ligands to have high affinity/selectivity towards ERβ. QSAR models obtained were both internally and externally validated. The study delineates that the size and shape descriptors are best modulators of ERβ affinity/selectivity. Docking studies were performed to support our QSAR results.

Classification of bioaccumulative and non-bioaccumulative chemicals using statistical learning approaches

The present work aimed at developing in silico models allowing for a reliable prediction of bioaccumulative compounds and non-bioaccumulative compounds based on the definition of Bioconcentration Factor (BCF) using a diverse data set of 238 organic molecules. The partial least squares analysis (PLS), C4.5, support vector machine (SVM), and random forest (RF) algorithms were applied, and their performance classifying these compounds in terms of their quantitative structure-activity relationships (QSAR) was evaluated and verified with 5-fold cross-validation and an independent evaluation data set. The obtained results show that the overall prediction accuracies (Q) of the optimal PLS, C4.5, SVM and RF models are 84.5-87.7% for the internal cross-validation, with prediction accuracy (CO) of 86.3-91.1% in the external test sets, and C4.5 is slightly better than the three other methods which presents a Q of 87.7%, and a CO of 91.1% for the test sets. All these results prove the reliabilities of the in silico models, which should be valuable for the environmental risk assessment of the substances.

Prediction of binding affinity for estrogen receptor alpha modulators using statistical learning approaches

The estrogen receptor (ER), an important drug target for the therapy of breast cancers, received a great deal of attention during recent years. This work aimed at finding more potent and selective ER modulators through the investigations of multiple ligand-receptor interactions by exploring the relationship between the experimental and predicted pIC50 values using in silico methods. A Bayesian-regularized neural network combined with principal component analysis has been conducted on a set of ERalpha modulators (127 molecules), resulting in the correlation coefficients of 0.91 +/- 0.02, 0.87 +/- 0.04 and 0.90 +/- 0.02 for the training set (64 molecules), cross-validation set (32 molecules) and independent test (31 molecules), respectively. Meanwhile, a multiple linear regression (MLR) method has also been applied in order to explore the most important variables related to the biological activities. The proposed MLR model obtains a reasonable predictivity of pIC50 (R = 0.72, Q = 0.79) and makes use of four molecular descriptors, namely, Xvch6, nelem, SsssCH and SaaN. All these results prove the reliabilities of the in silico models, which should be useful not only for the screening but also for the rational design of novel ERalpha modulators with improved potency.

Evaluation of virtual screening performance of support vector machines trained by sparsely distributed active compounds

Virtual screening performance of support vector machines (SVM) depends on the diversity of training active and inactive compounds. While diverse inactive compounds can be routinely generated, the number and diversity of known actives are typically low. We evaluated the performance of SVM trained by sparsely distributed actives in six MDDR biological target classes composed of a high number of known actives (983-1645) of high, intermediate, and low structural diversity (muscarinic M1 receptor agonists, NMDA receptor antagonists, thrombin inhibitors, HIV protease inhibitors, cephalosporins, and renin inhibitors). SVM trained by regularly sparse data sets of 100 actives show improved yields at substantially reduced false-hit rates compared to those of published studies and those of Tanimoto-based similarity searching method based on the same data sets and molecular descriptors. SVM trained by very sparse data sets of 40 actives (2.4%-4.1% of the known actives) predicted 17.5-39.5%, 23.0-48.1%, and 70.2-92.4% of the remaining 943-1605 actives in the high, intermediate, and low diversity classes, respectively, 13.8-68.7% of which are outside the training compound families. SVM predicted 99.97% and 97.1% of the 9.997 M PUBCHEM and 167K remaining MDDR compounds as inactive and 2.6%-8.3% of the 19,495-38,483 MDDR compounds similar to the known actives as active. These suggest that SVM has substantial capability in identifying novel active compounds from sparse active data sets at low false-hit rates.

A support vector machines approach for virtual screening of active compounds of single and multiple mechanisms from large libraries at an improved hit-rate and enrichment factor

Support vector machines (SVM) and other machine-learning (ML) methods have been explored as ligand-based virtual screening (VS) tools for facilitating lead discovery. While exhibiting good hit selection performance, in screening large compound libraries, these methods tend to produce lower hit-rate than those of the best performing VS tools, partly because their training-sets contain limited spectrum of inactive compounds. We tested whether the performance of SVM can be improved by using training-sets of diverse inactive compounds. In retrospective database screening of active compounds of single mechanism (HIV protease inhibitors, DHFR inhibitors, dopamine antagonists) and multiple mechanisms (CNS active agents) from large libraries of 2.986 million compounds, the yields, hit-rates, and enrichment factors of our SVM models are 52.4-78.0%, 4.7-73.8%, and 214-10,543, respectively, compared to those of 62-95%, 0.65-35%, and 20-1200 by structure-based VS and 55-81%, 0.2-0.7%, and 110-795 by other ligand-based VS tools in screening libraries of >or=1 million compounds. The hit-rates are comparable and the enrichment factors are substantially better than the best results of other VS tools. 24.3-87.6% of the predicted hits are outside the known hit families. SVM appears to be potentially useful for facilitating lead discovery in VS of large compound libraries.

Machine learning approaches for predicting compounds that interact with therapeutic and ADMET related proteins

Computational methods for predicting compounds of specific pharmacodynamic and ADMET (absorption, distribution, metabolism, excretion and toxicity) property are useful for facilitating drug discovery and evaluation. Recently, machine learning methods such as neural networks and support vector machines have been explored for predicting inhibitors, antagonists, blockers, agonists, activators and substrates of proteins related to specific therapeutic and ADMET property. These methods are particularly useful for compounds of diverse structures to complement QSAR methods, and for cases of unavailable receptor 3D structure to complement structure-based methods. A number of studies have demonstrated the potential of these methods for predicting such compounds as substrates of P-glycoprotein and cytochrome P450 CYP isoenzymes, inhibitors of protein kinases and CYP isoenzymes, and agonists of serotonin receptor and estrogen receptor. This article is intended to review the strategies, current progresses and underlying difficulties in using machine learning methods for predicting these protein binders and as potential virtual screening tools. Algorithms for proper representation of the structural and physicochemical properties of compounds are also evaluated.

Prediction of factor Xa inhibitors by machine learning methods

Factor Xa (FXa) inhibitors have been explored as anticoagulants for treatment and prevention of thrombotic diseases. Molecular docking, pharmacophore, quantitative structure-activity relationships, and support vector machines (SVM) have been used for computer prediction of FXa inhibitors. These methods achieve promising prediction accuracies of 69-80% for FXa inhibitors and 85-99% for non-inhibitors. Prediction performance, particularly for inhibitors, may be further improved by exploring methods applicable to more diverse range of compounds and by using more appropriate set of molecular descriptors. We tested the capability of several machine learning methods (C4.5 decision tree, k-nearest neighbor, probabilistic neural network, and support vector machine) by using a much more diverse set of 1098 compounds (360 inhibitors and 738 non-inhibitors) than those in other studies. A feature selection method was used for selecting molecular descriptors appropriate for distinguishing FXa inhibitors and non-inhibitors. The prediction accuracies of these methods are 89.1-97.5% for FXa inhibitors and 92.3-98.1% for non-inhibitors. In particular, compared to other studies, support vector machine gives a substantially improved accuracy of 94.6% for FXa non-inhibitors and maintains a comparable accuracy of 98.1% for inhibitors, based-on a more rigorous test with more diverse range of compounds. Our study suggests that machine learning methods such as SVM are useful for facilitating the prediction of FXa inhibitors.

In silico screening of estrogen-like chemicals based on different nonlinear classification models

Increasing concern is being shown by the scientific community, government regulators, and the public about endocrine-disrupting chemicals that are adversely affecting human and wildlife health through a variety of mechanisms. There is a great need for an effective means of rapidly assessing endocrine-disrupting activity, especially estrogen-simulating activity, because of the large number of such chemicals in the environment. In this study, quantitative structure activity relationship (QSAR) models were developed to quickly and effectively identify possible estrogen-like chemicals based on 232 structurally-diverse chemicals (training set) by using several nonlinear classification methodologies (least-square support vector machine (LS-SVM), counter-propagation artificial neural network (CP-ANN), and k nearest neighbour (kNN)) based on molecular structural descriptors. The models were externally validated by 87 chemicals (prediction set) not included in the training set. All three methods can give satisfactory prediction results both for training and prediction sets, and the most accurate model was obtained by the LS-SVM approach through the comparison of performance. In addition, our model was also applied to about 58,000 discrete organic chemicals; about 76% were predicted not to bind to Estrogen Receptor. The obtained results indicate that the proposed QSAR models are robust, widely applicable and could provide a feasible and practical tool for the rapid screening of potential estrogens.

In Silico Prediction of Pregnane X Receptor Activators by Machine Learning Approache

Pregnane X receptor (PXR) regulates drug metabolism and is involved in drug-drug interactions. Prediction of PXR activators is important for evaluating drug metabolism and toxicity. Computational pharmacophore and quantitative structure-activity relationship models have been developed for predicting PXR activators. Because of the structural diversity of PXR activators, more efforts are needed for exploring methods applicable to a broader spectrum of compounds. We explored three machine learning methods (MLMs) for predicting PXR activators, which were trained and tested by using significantly higher number of compounds, 128 PXR activators (98 human) and 77 PXR non-activators, than those of previous studies. The recursive feature-selection method was used to select molecular descriptors relevant to PXR activator prediction, which are consistent with conclusions from other computational and structural studies. In a 10-fold cross-validation test, our MLM systems correctly predicted 81.2 to 84.0% of PXR activators, 80.8 to 85.0% of hPXR activators, 61.2 to 70.3% of PXR nonactivators, and 67.7 to 73.6% of hPXR nonactivators. Our systems also correctly predicted 73.3 to 86.7% of 15 newly published hPXR activators. MLMs seem to be useful for predicting PXR activators and for providing clues to physicochemical features of PXR activation.