Search

This user guide describes the rationale behind, and the modus operandi of a Unix script-driven package for evolutionary searching of optimal Support Vector Machine model parameters as computed by the libsvm package, leading to support vector machine models of maximal predictive power and robustness. Unlike common libsvm parameterizing engines, the current distribution includes the key choice of best-suited sets of attributes/descriptors, in addition to the classical libsvm operational parameters (kernel choice, kernel parameters, cost, and so forth), allowing a unified search in an enlarged problem space. It relies on an aggressive, repeated cross-validation scheme to ensure a rigorous assessment of model quality. Primarily designed for chemoinformatics applications, it also supports the inclusion of decoy instances, for which the explained property (bioactivity) is, strictly speaking, unknown but presumably “inactive”, thus additionally testing the robustness of a model to noise. The package was developed with parallel computing in mind, supporting execution on both multi-core workstations as well as compute cluster environments. It can be downloaded from http://infochim.u-strasbg.fr/spip.php?rubrique178.

Abstract: In this article we consider the application of the Transductive Ridge Regression (TRR) approach to structure‐activity modeling. An original procedure of the TRR parameters optimization is suggested. Calculations performed on 3 different datasets involving two types of descriptors demonstrated that TRR outperforms its non‐transductive analogue (Ridge Regression) in more than 90 % of cases. The most significant transductive effect was observed for small datasets. This suggests that transduction may be particularly useful when the data are expensive or difficult to collect. [ABSTRACT FROM AUTHOR]

Generative Topographic Mapping (GTM) is a dimensionality reduction method, which is widely used for both data visualization and structure‐activity modeling. Large dimensionality of the initial data space may require significant computational resources and slow down the GTM construction. Therefore, it may be meaningful to reduce the number of descriptors used for encoding molecular structures. The Principal Component Analysis (PCA), a standard preprocessing tool, suffers from the information loss upon the dimensionality reduction. As an alternative, we propose to use substructure vector embedding provided by the mol2vec technique. In addition to the data dimensionality reduction, this technology also accounts for proximity of substructures in molecular graphs. In this study, dimensionality of large descriptor spaces of ISIDA fragment descriptors or Morgan fingerprints were reduced using either the PCA or the mol2vec method. The latter significantly speeds up GTM training without compromising its predictive power in bioactivity classification tasks. [ABSTRACT FROM AUTHOR]

In this paper we demonstrate that Generative Topographic Mapping (GTM), a machine learning method traditionally used for data visualisation, can be efficiently applied to QSAR modelling using probability distribution functions (PDF) computed in the latent 2-dimensional space. Several different scenarios of the activity assessment were considered: (i) the 'activity landscape' approach based on direct use of PDF, (ii) QSAR models involving GTM-generated on descriptors derived from PDF, and, (iii) the k-Nearest Neighbours approach in 2D latent space. Benchmarking calculations were performed on five different datasets: stability constants of metal cations Ca2+, Gd3+ and Lu3+ complexes with organic ligands in water, aqueous solubility and activity of thrombin inhibitors. It has been shown that the performance of GTM-based regression models is similar to that obtained with some popular machine-learning methods (random forest, k-NN, M5P regression tree and PLS) and ISIDA fragment descriptors. By comparing GTM activity landscapes built both on predicted and experimental activities, we may visually assess the model's performance and identify the areas in the chemical space corresponding to reliable predictions. The applicability domain used in this work is based on data likelihood. Its application has significantly improved the model performances for 4 out of 5 datasets. [ABSTRACT FROM AUTHOR]

This user guide describes the rationale behind, and the modus operandi of a Unix script-driven package for evolutionary searching of optimal Support Vector Machine model parameters as computed by the libsvm package, leading to support vector machine models of maximal predictive power and robustness. Unlike common libsvm parameterizing engines, the current distribution includes the key choice of best-suited sets of attributes/descriptors, in addition to the classical libsvm operational parameters (kernel choice, kernel parameters, cost, and so forth), allowing a unified search in an enlarged problem space. It relies on an aggressive, repeated cross-validation scheme to ensure a rigorous assessment of model quality. Primarily designed for chemoinformatics applications, it also supports the inclusion of decoy instances, for which the explained property (bioactivity) is, strictly speaking, unknown but presumably "inactive", thus additionally testing the robustness of a model to noise. The package was developed with parallel computing in mind, supporting execution on both multi-core workstations as well as compute cluster environments. It can be downloaded from http://infochim.u-strasbg.fr/spip.php?rubrique178. [ABSTRACT FROM AUTHOR]

Semi-supervised methods dealing with a combination of labeled and unlabeled data become more and more popular in machine-learning area, but not still used in chemoinformatics. Here, we demonstrate that Transductive Support Vector Machines (TSVM) - a semi-supervised large-margin classification method - can be particularly useful to build the models on small and unbalanced datasets which often represent a difficult problem in QSAR. Both TSVM and ordinary SVM have been applied to build classification models on 10 DUD datasets. The 'transductive effect' (the difference in predictive performance between transductive and ordinary support vector machines) was investigated as a function of: (a) active/inactive ratio, (b) descriptor weighting, and (c) the training and test sets size and composition. [ABSTRACT FROM AUTHOR]

Chemical reactions always involve several molecules of two types, reactants and products. Existing data mining techniques, eg. Quantitative Structure Activity Relationship (QSAR) methods, deal with individual molecules only. In this article, we propose to use a Condensed Graph of Reaction (CGR) to merge all molecules involved in a reaction into one molecular graph. This allows one to consider reactions as pseudo-molecules and to develop QSAR models based on fragment descriptors. Then ISIDA (In SIlico Design and Analysis) fragment descriptors built from CGRs are used to generate models for the rate constant of SN2 reactions in water, using three usual attribute-value regression algorithms (linear regression, support vector machine, and regression trees). This approach is compared favorably to two state-of-the-art relational data mining techniques. [ABSTRACT FROM AUTHOR]

The selection of experimental conditions leading to a reasonable yield is an important and essential element for the automated development of a synthesis plan and the subsequent synthesis of the target compound. The classical QSPR approach, requiring one-to-one correspondence between chemical structure and a target property, can be used for optimal reaction conditions prediction only on a limited scale when only one condition component (e.g., catalyst or solvent) is considered. However, a particular reaction can proceed under several different conditions. In this paper, we describe the Likelihood Ranking Model representing an artificial neural network that outputs a list of different conditions ranked according to their suitability to a given chemical transformation. Benchmarking calculations demonstrated that our model outperformed some popular approaches to the theoretical assessment of reaction conditions, such as k Nearest Neighbors, and a recurrent artificial neural network performance prediction of condition components (reagents, solvents, catalysts, and temperature). The ability of the Likelihood Ranking model trained on a hydrogenation reactions dataset, (~42,000 reactions) from Reaxys® database, to propose conditions that led to the desired product was validated experimentally on a set of three reactions with rich selectivity issues. [ABSTRACT FROM AUTHOR]

In this study, quantitative structure-activity relationship (QSAR) analysis was conducted on 20 homologous compounds of benzimidazole derivatives. The structures of the benzimidazole derivatives were optimized using the semiempirical Parameterized Model 3 method of HyperChem for Windows 8.0 to obtain 14 descriptors. Then, multiple linear regression (MLR) analysis was performed using the backward method. The results of the MLR analysis obtained four new QSAR equation models. Based on statistical criteria, model 1 was determined as the best QSAR equation model in predicting the theoretical IC50 values of the new benzimidazole derivatives. As many as 20 new compounds of benzimidazole derivatives were modeled, of which 13 new compounds (23, 24, 25, 26, 27, 28, 29, 30, 31, 37, 38, 39, and 40 compounds) were recommended for synthesis in the laboratory because these compounds of benzimidazole derivatives havethey theoretically had higher antimalarial activity than chloroquine. [ABSTRACT FROM AUTHOR]

Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules. This provides a starting point for generating similar molecules to a given input molecule, but has limited flexibility regarding user-defined property profiles. Here, we evaluate the effect of reinforcement learning on transformer-based molecular generative models. The generative model can be considered as a pre-trained model with knowledge of the chemical space close to an input compound, while reinforcement learning can be viewed as a tuning phase, steering the model towards chemical space with user-specific desirable properties. The evaluation of two distinct tasks—molecular optimization and scaffold discovery—suggest that reinforcement learning could guide the transformer-based generative model towards the generation of more compounds of interest. Additionally, the impact of pre-trained models, learning steps and learning rates are investigated. Scientific contribution Our study investigates the effect of reinforcement learning on a transformer-based generative model initially trained for generating molecules similar to starting molecules. The reinforcement learning framework is applied to facilitate multiparameter optimisation of starting molecules. This approach allows for more flexibility for optimizing user-specific property profiles and helps finding more ideas of interest. [ABSTRACT FROM AUTHOR]

Oral drug absorption is the primary route for drug administration. However, this process hinges on multiple factors, including the drug's physicochemical properties, formulation characteristics, and gastrointestinal physiology. Given its intricacy and the exorbitant costs associated with experimentation, the trial-and-error method proves prohibitively expensive. Theoretical models have emerged as a cost-effective alternative by assimilating data from diverse experiments and theoretical considerations. These models fall into three categories: (i) data-driven models, encompassing classical pharmacokinetics, quantitative-structure models (QSAR), and machine/deep learning; (ii) mechanism-based models, which include quasi-equilibrium, steady-state, and physiologically-based pharmacokinetics models; and (iii) first principles models, including molecular dynamics and continuum models. This review provides an overview of recent modeling endeavors across these categories while evaluating their respective advantages and limitations. Additionally, a primer on partial differential equations and their numerical solutions is included in the appendix, recognizing their utility in modeling physiological systems despite their mathematical complexity limiting widespread application in this field. [ABSTRACT FROM AUTHOR]

Acetylcholinesterase (AChE) is one of the main drug targets for treating Alzheimer's disease. This current study relies on multiple molecular modeling approaches to develop new potent inhibitors of AChE. We explored a 2D QSAR study using the statistical method of multiple linear regression based on a set of substituted 5-phenyl-1,3,4-oxadiazole and N-benzylpiperidine analogs, which were recently synthesized and proved their inhibitory activities against acetylcholinesterase (AChE). The molecular descriptors, polar surface area, dipole moment, and molecular weight are the key structural properties governing AChE inhibition activity. The MLR model was selected based on its statistical parameters: R2 = 0.701, R2test = 0.76, Q2CV = 0.638, and RMSE = 0.336, demonstrating its predictive reliability. Randomization tests, VIF tests, and applicability domain tests were adopted to verify the model's robustness. As a result, 11 new molecules were designed with higher anti-Alzheimer's activities than the model molecule. We demonstrated their improved pharmacokinetic properties through an in silico ADMET study. A molecular docking study was conducted to explore their AChE inhibition mechanisms and binding affinities in the active site. The binding scores of compounds M1, M2, and M6 were (−12.6 kcal/mol), (−13 kcal/mol), and (−12.4 kcal/mol), respectively, which are higher than the standard inhibitor Donepezil with a binding score of (−10.8 kcal/mol). Molecular dynamics simulations over 100 ns were used to validate the molecular docking results, indicating that compounds M1 and M2 remain stable in the active site, confirming their potential as promising anti-AChE inhibitors. [ABSTRACT FROM AUTHOR]

Histone deacetylase 6 (HDAC6) is a promising drug target for the treatment of human diseases such as cancer, neurodegenerative diseases (in particular, Alzheimer's disease), and multiple sclerosis. Considerable attention is paid to the development of selective non-toxic HDAC6 inhibitors. To this end, we successfully form a set of 3854 compounds and proposed adequate regression QSAR models for HDAC6 inhibitors. The models have been developed using the PubChem, Klekota-Roth, 2D atom pair fingerprints, and RDkit descriptors and the gradient boosting, support vector machines, neural network, and k-nearest neighbours methods. The models are integrated into the developed HT_PREDICT application, which is freely available at . In vitro studies have confirmed the predictive ability of the proposed QSAR models integrated into the HT_PREDICT web application. In addition, the virtual screening performed with the HT_PREDICT web application allowed us to propose two promising inhibitors for further investigations. [ABSTRACT FROM AUTHOR]

Metabolomics has gained much attention due to its potential to reveal molecular disease mechanisms and present viable biomarkers. This work uses a panel of untargeted serum metabolomes from 602 children from the COPSAC2010 mother–child cohort. The annotated part of the metabolome consists of 517 chemical compounds curated using automated procedures. We created a filtering method for the quantified metabolites using predicted quantitative structure–bioactivity relationships for the Tox21 database on nuclear receptors and stress response in cell lines. The metabolites measured in the children's serums are predicted to affect specific targeted models, known for their significance in inflammation, immune function, and health outcomes. The targets from Tox21 have been used as targets with quantitative structure–activity relationships (QSARs). They were trained for ~7000 structures, saved as models, and then applied to the annotated metabolites to predict their potential bioactivities. The models were selected based on strict accuracy criteria surpassing random effects. After application, 52 metabolites showed potential bioactivity based on structural similarity with known active compounds from the Tox21 set. The filtered compounds were subsequently used and weighted by their bioactive potential to show an association with early childhood hs-CRP levels at six months in a linear model supporting a physiological adverse effect on systemic low-grade inflammation. [ABSTRACT FROM AUTHOR]

Transfer learning is a machine learning technique that works well with chemical endpoints, with several papers confirming its efficiency. Although effective, because the choice of source/assistant tasks is non-trivial, the application of this technique is severely limited by the domain knowledge of the modeller. Considering this limitation, we developed a purely data-driven approach for source task selection that abstracts the need for domain knowledge. To achieve this, we created a supervised learning setting in which transfer outcome (positive/negative) is the variable to be predicted, and a set of six transferability metrics, calculated based on information from target and source datasets, are the features for prediction. We used the ChEMBL database to generate 100,000 transfers using random pairing, and with these transfers, we trained and evaluated our transferability prediction model (TP-Model). Our TP-Model achieved a 135-fold increase in precision while achieving a sensitivity of 92%, demonstrating a clear superiority against random search. In addition, we observed that transfer learning could provide considerable performance increases when applicable, with an average Matthews Correlation Coefficient (MCC) increase of 0.19 when using a single source and an average MCC increase of 0.44 when using multiple sources. [ABSTRACT FROM AUTHOR]

Mycobacterium tuberculosis is the bacterial strain that causes tuberculosis (TB). However, multidrug-resistant and extensively drug-resistant tuberculosis are significant obstacles to effective treatment. As a result, novel therapies against various strains of M. tuberculosis have been developed. Drug development is a lengthy procedure that includes identifying target protein and isolation, preclinical testing of the drug, and various phases of a clinical trial, etc., can take decades for a molecule to reach the market. Computational approaches such as QSAR, molecular docking techniques, and pharmacophore modeling have aided drug development. In this review article, we have discussed the various techniques in tuberculosis drug discovery by briefly introducing them and their importance. Also, the different databases, methods, approaches, and software used in conducting QSAR, pharmacophore modeling, and molecular docking have been discussed. The other targets targeted by these techniques in tuberculosis drug discovery have also been discussed, with important molecules discovered using these computational approaches. This review article also presents the list of drugs in a clinical trial for tuberculosis found drugs. Finally, we concluded with the challenges and future perspectives of these techniques in drug discovery. [ABSTRACT FROM AUTHOR]

Histone deacetylase 2 inhibitors (HDAC2) are developed as effective drugs for the treatment of various diseases. Using various types of molecular descriptors, several adequate Quantitative Structure–Activity Relationship regression models for acute toxicity (LD50, rats, orally) of HDAC2 inhibitors have been proposed. The created adequate models are integrated into the developed HDAC2 SCAN application, freely available at https://hdac2scan.streamlit.app/. The HDAC2 SCAN application can be used for virtual screening. [ABSTRACT FROM AUTHOR]

The risk evaluation for pharmacological therapy during pregnancy is critical for maternal and fetal health. The initial risk assessment stage, the risk measurement, begins with pregnancy‐labeling categories (A, B, C, D, and X) for pharmaceuticals defined by the US Food and Drug Administration (FDA). Recently, in silico methods have been preferred in toxicology studies to eliminate ethical issues before conducting clinical toxicology studies and animal experiments. Quantitative structure–activity relationship (QSAR) modeling is one of the in silico methodologies. The research focuses on creating a QSAR model that predicts the five FDA pregnancy categories of medications. Our dataset included 868 pharmaceuticals, containing nearly every pharmacological group collected from the FDA. 2D‐molecular descriptors were calculated using PaDEL software. Twenty‐four QSAR models were developed, and the best four models were discussed. The results of the models were compared according to sensitivity, accuracy, F‐score, specificity, receiver operating characteristic (ROC) values, and Matthews correlation coefficient. Considering the statistical results, random forest is the best model for determining the pregnancy risk category of drugs. The accuracy of the model was 76.49% for internal and 93.58% for external validation. According to the kappa statistics, there is an average agreement of 0.583 for internal validation and a perfect agreement of 0.893 for external validation. Because the error rates of the model are very close to 0, the model is highly accurate. Consequently, our novel QSAR model gives guidance on the safe use of pharmaceuticals during pregnancy without requiring animal tests or clinical trials on pregnant women. In this study, we created a quantitative structure–activity relationship (QSAR) model to predict the FDA pregnancy categories of 868 pharmaceuticals from various pharmacological groups. Our statistical analysis showed that the random forest model performed the best, with 76.46% accuracy for internal and 93.58% for external validation. Our QSAR model provides safe guidance for using medications during pregnancy without requiring animal tests or clinical trials. [ABSTRACT FROM AUTHOR]

Environmental protection and sustainability is the development goal that countries all over the world are pursuing. Ionic liquids (ILs), as a new type of green material, have a great application prospect. And the quantitative structure–activity relationship (QSAR) is significant for the research of ILs. To better understand the role played by QSAR in the research of ILs, 4139 literatures published in the WOS database from 2002 to 2022 were used for bibliometric analysis, and different types of knowledge maps were mapped to obtain the current status and trends of IL research applied QSAR. The distribution pattern of the literature output chronology, country, institution, author cooperation, and major source journals can be obtained through the research of the distribution of literature. Through core literature, dual-map overlays, and evolutionary path analysis, the research knowledge base was obtained mainly including ionic liquid toxicological properties research, environmental protection and sustainability, ionic liquid design, and mild steel corrosion inhibition; through the co-occurrence and evolution of keywords, the current research hotspots are basic properties of ILs, corrosion inhibition of mild steel, the effect of toxicity on the environment, QSAR modeling methods, solvent application of ILs, and drug design. [ABSTRACT FROM AUTHOR]

Mycobacterium tuberculosis is the bacterial strain that causes tuberculosis (TB). However, multidrug-resistant and extensively drug-resistant tuberculosis are significant obstacles to effective treatment. As a result, novel therapies against various strains of M. tuberculosis have been developed. Drug development is a lengthy procedure that includes identifying target protein and isolation, preclinical testing of the drug, and various phases of a clinical trial, etc., can take decades for a molecule to reach the market. Computational approaches such as QSAR, molecular docking techniques, and pharmacophore modeling have aided drug development. In this review article, we have discussed the various techniques in tuberculosis drug discovery by briefly introducing them and their importance. Also, the different databases, methods, approaches, and software used in conducting QSAR, pharmacophore modeling, and molecular docking have been discussed. The other targets targeted by these techniques in tuberculosis drug discovery have also been discussed, with important molecules discovered using these computational approaches. This review article also presents the list of drugs in a clinical trial for tuberculosis found drugs. Finally, we concluded with the challenges and future perspectives of these techniques in drug discovery. [ABSTRACT FROM AUTHOR]

Human soluble epoxide hydrolase (sEH), a dual-functioning homodimeric enzyme with hydrolase and phosphatase activities, is known for its pivotal role in the hydrolysis of epoxyeicosatrienoic acids. Inhibitors targeting sEH have shown promising potential in the treatment of various life-threatening diseases. In this study, we employed a range of in silico modeling approaches to investigate a diverse dataset of structurally distinct sEH inhibitors. Our primary aim was to develop predictive and validated models while gaining insights into the structural requirements necessary for achieving higher inhibitory potential. To accomplish this, we initially calculated molecular descriptors using nine different descriptor-calculating tools, coupled with stochastic and non-stochastic feature selection strategies, to identify the most statistically significant linear 2D-QSAR model. The resulting model highlighted the critical roles played by topological characteristics, 2D pharmacophore features, and specific physicochemical properties in enhancing inhibitory potential. In addition to conventional 2D-QSAR modeling, we implemented the Transformer-CNN methodology to develop QSAR models, enabling us to obtain structural interpretations based on the Layer-wise Relevance Propagation (LRP) algorithm. Moreover, a comprehensive 3D-QSAR analysis provided additional insights into the structural requirements of these compounds as potent sEH inhibitors. To validate the findings from the QSAR modeling studies, we performed molecular dynamics (MD) simulations using selected compounds from the dataset. The simulation results offered crucial insights into receptor–ligand interactions, supporting the predictions obtained from the QSAR models. Collectively, our work serves as an essential guideline for the rational design of novel sEH inhibitors with enhanced therapeutic potential. Importantly, all the in silico studies were performed using open-access tools to ensure reproducibility and accessibility. [ABSTRACT FROM AUTHOR]

Drug candidates identified by the pharmaceutical industry typically have unique structural characteristics to ensure they interact strongly and specifically with their biological targets. Identifying these characteristics is a key challenge for developing new drugs, and quantitative structure-activity relationship (QSAR) analysis has generally been used to perform this task. QSAR models with good predictive power improve the cost and time efficiencies invested in compound development. Generating these good models depends on how well differences between "active" and "inactive" compound groups can be conveyed to the model to be learned. Efforts to solve this difference issue have been made, including generating a "molecular descriptor" that compressively expresses the structural characteristics of compounds. From the same perspective, we succeeded in developing the Activity Differences-Quantitative Structure-Activity Relationship (ADis-QSAR) model by generating molecular descriptors that more explicitly convey features of the group through a pair system that performs direct connections between active and inactive groups. We used popular machine learning algorithms, such as Support Vector Machine, Random Forest, XGBoost and Multi-Layer Perceptron for model learning and evaluated the model using scores such as accuracy, area under curve, precision and specificity. The results showed that the Support Vector Machine performed better than the others. Notably, the ADis-QSAR model showed significant improvements in meaningful scores such as precision and specificity compared to the baseline model, even in datasets with dissimilar chemical spaces. This model reduces the risk of selecting false positive compounds, improving the efficiency of drug development. [ABSTRACT FROM AUTHOR]

Breast cancer ranks as the second leading cause of death among women, but early screening and self-awareness can help prevent it. Hormone therapy drugs that target estrogen levels offer potential treatments. However, conventional drug discovery entails extensive, costly processes. This study presents a framework for analyzing the quantitative structure–activity relationship (QSAR) of estrogen receptor alpha inhibitors. Our approach utilizes supervised learning, integrating self-attention Transformer and molecular graph information, to predict estrogen receptor alpha inhibitors. We established five classification models for predicting these inhibitors in breast cancer. Among these models, our proposed MATH model achieved remarkable precision, recall, F1 score, and specificity, with values of 0.952, 0.972, 0.960, and 0.922, respectively, alongside an ROC AUC of 0.977. MATH exhibited robust performance, suggesting its potential to assist pharmaceutical and health researchers in identifying candidate compounds for estrogen alpha inhibitors and guiding drug discovery pathways. [ABSTRACT FROM AUTHOR]

The HDAC6 (histone deacetylase 6) enzyme plays a key role in many biological processes, including cell division, apoptosis, and immune response. To date, HDAC6 inhibitors are being developed as effective drugs for the treatment of various diseases. In this work, adequate QSAR models of HDAC6 inhibitors are proposed. They are integrated into the developed application HDAC6 Detector, which is freely available at . The web application HDAC6 Detector can be used to perform virtual screening of HDAC6 inhibitors by dividing the compounds into active and inactive ones relative to the reference vorinostat compound (IC50 = 10.4 nM). The web application implements a structural interpretation of the developed QSAR models. In addition, the application can evaluate the compliance of a compound with Lipinski's rule. The developed models are used for virtual screening of a series of 12 new hydroxamic acids, namely, the derivatives of 3-hydroxyquinazoline-4(3H)-ones and 2-aryl-2,3-dihydroquinazoline-4(1H)-ones. In vitro evaluation of the inhibitory activity of this series of compounds against HDAC6 allowed us to confirm the results of virtual screening and to select promising compounds V-6 and V-11, the IC50 of which is 0.99 and 0.81 nM, respectively. [ABSTRACT FROM AUTHOR]

Explainable machine learning is increasingly used in drug discovery to help rationalize compound property predictions. Feature attribution techniques are popular choices to identify which molecular substructures are responsible for a predicted property change. However, established molecular feature attribution methods have so far displayed low performance for popular deep learning algorithms such as graph neural networks (GNNs), especially when compared with simpler modeling alternatives such as random forests coupled with atom masking. To mitigate this problem, a modification of the regression objective for GNNs is proposed to specifically account for common core structures between pairs of molecules. The presented approach shows higher accuracy on a recently-proposed explainability benchmark. This methodology has the potential to assist with model explainability in drug discovery pipelines, particularly in lead optimization efforts where specific chemical series are investigated. [ABSTRACT FROM AUTHOR]

In modern drug discovery, the combination of chemoinformatics and quantitative structure–activity relationship (QSAR) modeling has emerged as a formidable alliance, enabling researchers to harness the vast potential of machine learning (ML) techniques for predictive molecular design and analysis. This review delves into the fundamental aspects of chemoinformatics, elucidating the intricate nature of chemical data and the crucial role of molecular descriptors in unveiling the underlying molecular properties. Molecular descriptors, including 2D fingerprints and topological indices, in conjunction with the structure–activity relationships (SARs), are pivotal in unlocking the pathway to small-molecule drug discovery. Technical intricacies of developing robust ML-QSAR models, including feature selection, model validation, and performance evaluation, are discussed herewith. Various ML algorithms, such as regression analysis and support vector machines, are showcased in the text for their ability to predict and comprehend the relationships between molecular structures and biological activities. This review serves as a comprehensive guide for researchers, providing an understanding of the synergy between chemoinformatics, QSAR, and ML. Due to embracing these cutting-edge technologies, predictive molecular analysis holds promise for expediting the discovery of novel therapeutic agents in the pharmaceutical sciences. [ABSTRACT FROM AUTHOR]

In de novo molecular design, quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) models are important to estimate activity and property values, respectively, for virtual molecular structures. To operate QSAR and QSPR models appropriately, applicability domains (ADs) of the models must be defined because estimated values are unreliable for virtual molecular structures that are dissimilar to structures of training compounds. We describe several methods to construct AD models, and then introduce a structure generator to change molecular structures that exist outside ADs to conform to ADs. [ABSTRACT FROM AUTHOR]

Predicting the likely biological activity (or property) of compounds is a fundamental and challenging task in the drug discovery process. Current computational methodologies aim to improve their predictive accuracies by using deep learning (DL) approaches. However, non‐DL based approaches for small‐ and medium‐sized chemical datasets have demonstrated to be most suitable for. In this approach, an initial universe of molecular descriptors (MDs) is first calculated, then different feature selection algorithms are applied, and finally, one or several predictive models are built. Herein we demonstrate that this traditional approach may miss relevant information by assuming that the initial universe of MDs codifies all relevant aspects for the respective learning task. We argue that this limitation is mainly because of the constrained intervals of the parameters used in the algorithms that compute MDs, parameters that define the Descriptor Configuration Space (DCS). We propose to relax these constraints in an open CDS approach, so that a larger universe of MDs can be initially considered. We model the generation of MDs as a multicriteria optimization problem and tackle it with a variant of the standard genetic algorithm. As a novel component, the fitness function is computed by aggregating four criteria via the Choquet integral. Experimental results show that the proposed approach generates a meaningful DCS by improving state‐of‐the‐art approaches in most of the benchmarking chemical datasets accounted for. [ABSTRACT FROM AUTHOR]

The development of organelle-specific fluorescent probes has been impeded by the absence of a comprehensive understanding of the relationship between the physicochemical properties of fluorescent probes and their selectivity towards specific organelles. Although a few machine learning models have suggested several physicochemical parameters that control the target organelle of the probes and have attempted to predict the target organelles, they have been challenged by low accuracy and a limited range of applicable organelles. Herein, we report a multi-organelle prediction QSAR model that is capable of predicting the destination of probes among nine categories, including cytosol, endoplasmic reticulum, Golgi body, lipid droplet, lysosome, mitochondria, nucleus, plasma membrane, and no entry. The model is trained using the Random Forest algorithm with a dataset of 350 organelle-specific fluorescent probes and 786 descriptors, and it is able to predict the target organelles of fluorescent probes with an accuracy of 75%. The MDI analysis of the model identifies 38 key parameters that have a significant impact on the organelle selectivity of the probes, including LogD, pKa, hydrophilic-lipophilic balance (HLB), and topological polar surface area (TPSA). This prediction model may be useful in developing new organelle-specific fluorescent probes by providing crucial variables that determine the destination of the probes. [ABSTRACT FROM AUTHOR]

Coronaviruses induce severe upper respiratory tract infections, which can spread to the lungs. The nucleocapsid protein (N protein) plays an important role in genome replication, transcription, and virion assembly in SARS-CoV-2, the virus causing COVID-19, and in other coronaviruses. Glycogen synthase kinase 3 (GSK3) activation phosphorylates the viral N protein. To combat COVID-19 and future coronavirus outbreaks, interference with the dependence of N protein on GSK3 may be a viable strategy. Toward this end, this study aimed to construct robust machine learning models to identify GSK3 inhibitors from Food and Drug Administration-approved and investigational drug libraries using the quantitative structure-activity relationship approach. A non-redundant dataset consisting of 495 and 3070 compounds for GSK3α and GSK3β, respectively, was acquired from the ChEMBL database. Twelve sets of molecular descriptors were used to define these inhibitors, and machine learning algorithms were selected using the LazyPredict package. Histogram-based gradient boosting and light gradient boosting machine algorithms were used to develop predictive models that were evaluated based on the root mean square error and R-squared value. Finally, the top two drugs (selinexor and ruboxistaurin) were selected for molecular dynamics simulation based on the highest predicted activity (negative log of the half-maximal inhibitory concentration, pIC50 value) to further investigate the structural stability of the protein-ligand complexes. This artificial intelligence-based virtual high-throughput screening approach is an effective strategy for accelerating drug discovery and finding novel pharmacological targets while reducing the cost and time. [ABSTRACT FROM AUTHOR]

Microtubules are highly dynamic polymers of α,β-tubulin dimers which play an essential role in numerous cellular processes such as cell proliferation and intracellular transport, making them an attractive target for cancer and neurodegeneration research. To date, a large number of known tubulin binders were derived from natural products, while only one was developed by rational structure-based drug design. Several of these tubulin binders show promising in vitro profiles while presenting unacceptable off-target effects when tested in patients. Therefore, there is a continuing demand for the discovery of safer and more efficient tubulin-targeting agents. Since tubulin structural data is readily available, the employment of computer-aided design techniques can be a key element to focus on the relevant chemical space and guide the design process. Due to the high diversity and quantity of structural data available, we compiled here a guide to the accessible tubulin-ligand structures. Furthermore, we review different ligand and structure-based methods recently used for the successful selection and design of new tubulin-targeting agents. [ABSTRACT FROM AUTHOR]

The availability of experimental nanotoxicity data is in general limited which warrants both the use of in silico methods for data gap filling and exploring novel methods for effective modeling. Read-Across Structure-Activity Relationship (RASAR) is an emerging cheminformatic approach that combines the usefulness of a QSAR model and similarity-based Read-Across predictions. In this work, we have generated simple, interpretable, and transferable quantitative-RASAR (q-RASAR) models which can efficiently predict the cytotoxicity of TiO2-based multi-component nanoparticles. A data set of 29 TiO2-based nanoparticles with specific amounts of noble metal precursors was rationally divided into training and test sets, and the Read-Across-based predictions for the test set were generated. The optimized hyperparameters and the similarity approach, which yield the best predictions, were used to calculate the similarity and error-based RASAR descriptors. A data fusion of the RASAR descriptors with the chemical descriptors was done followed by the best subset feature selection. The final set of selected descriptors was used to develop the q-RASAR models, which were validated using the stringent OECD criteria. Finally, a random forest model was also developed with the selected descriptors, which could efficiently predict the cytotoxicity of TiO2-based multi-component nanoparticles superseding previously reported models in the prediction quality thus showing the merits of the q-RASAR approach. To further evaluate the usefulness of the approach, we have applied the q-RASAR approach also to a second cytotoxicity data set of 34 heterogeneous TiO2-based nanoparticles which further confirmed the enhancement of external prediction quality of QSAR models after incorporation of RASAR descriptors. [ABSTRACT FROM AUTHOR]

In this study, a series of novel quinolinone-based thiosemicarbazones were designed in silico and their activities tested in vitro against Mycobacterium tuberculosis (M. tuberculosis). Quantitative structure-activity relationship (QSAR) studies were performed using quinolinone and thiosemicarbazide as pharmacophoric nuclei; the best model showed statistical parameters of R2 = 0.83; F = 47.96; s = 0.31, and was validated by several different methods. The van der Waals volume, electron density, and electronegativity model results suggested a pivotal role in antituberculosis (anti-TB) activity. Subsequently, from this model a new series of quinolinone-thiosemicarbazone 11a–e was designed and docked against two tuberculosis protein targets: enoyl-acyl carrier protein reductase (InhA) and decaprenylphosphoryl-β-D-ribose-2'-oxidase (DprE1). Molecular dynamics simulation over 200 ns showed a binding energy of −71.3 to −12.7 Kcal/mol, suggesting likely inhibition. In vitro antimycobacterial activity of quinolinone-thiosemicarbazone for 11a–e was evaluated against M. bovis, M. tuberculosis H37Rv, and six different strains of drug-resistant M. tuberculosis. All compounds exhibited good to excellent activity against all the families of M. tuberculosis. Several of the here synthesized compounds were more effective than the standard drugs (isoniazid, oxafloxacin), 11d and 11e being the most active products. The results suggest that these compounds may contribute as lead compounds in the research of new potential antimycobacterial agents. [ABSTRACT FROM AUTHOR]

A growing body of preclinical evidence recognized selective sirtuin 2 (SIRT2) inhibitors as novel therapeutics for treatment of age-related diseases. However, none of the SIRT2 inhibitors have reached clinical trials yet. Transformative potential of machine learning (ML) in early stages of drug discovery has been witnessed by widespread adoption of these techniques in recent years. Despite great potential, there is a lack of robust and large-scale ML models for discovery of novel SIRT2 inhibitors. In order to support virtual screening (VS), lead optimization, or facilitate the selection of SIRT2 inhibitors for experimental evaluation, a machine-learning-based tool titled SIRT2i_Predictor was developed. The tool was built on a panel of high-quality ML regression and classification-based models for prediction of inhibitor potency and SIRT1-3 isoform selectivity. State-of-the-art ML algorithms were used to train the models on a large and diverse dataset containing 1797 compounds. Benchmarking against structure-based VS protocol indicated comparable coverage of chemical space with great gain in speed. The tool was applied to screen the in-house database of compounds, corroborating the utility in the prioritization of compounds for costly in vitro screening campaigns. The easy-to-use web-based interface makes SIRT2i_Predictor a convenient tool for the wider community. The SIRT2i_Predictor's source code is made available online. [ABSTRACT FROM AUTHOR]

Cervical cancer is one of the most aggressive and important cancer types in the female population, due to its low survival rate. Actually, the search for new bioactive compounds, like gallic and cinnamic acid, is one of the most employed options to finding a treatment. In the present study, 134 phenolic compounds with cytotoxic activity over HeLa cell line were used to generate a descriptive (R2 ${{R}^{2}}$ =0.76) and predictive (Q2 ${{Q}^{2}}$ =0.69 and Qext2 ${{Q}_{{\rm e}{\rm x}{\rm t}}^{2}}$ =0.62) QSAR model. Structural, electronic, steric, and hydrophobic features are represented as different molecular descriptors in our QSAR model. From this model, nine gallate‐cinnamate ester derivatives (N1–N9) were designed and synthesized. Furthermore, in vitro cytotoxic activity was evaluated against HeLa and non‐tumorigenic cells. Derivatives N6, N5, N1, and N9 were the most active molecules with IC50ExpHeLa values from 7.26 to 11.95 μM. Finally, the binding of the synthesized compounds to the colchicine binding site on tubulin was evaluated by molecular docking as a possible action mechanism. N1, N5 and N6 can be considered as templates for the design of new cervical anticancer compounds. [ABSTRACT FROM AUTHOR]

Predicting acute oral toxicity LD50 of chemicals in rats is a challenge since many factors affect toxicity data. In this paper, 40 descriptors were successfully used to develop a quantitative structure–activity relationship model for 8448 rat acute oral toxicity logLD50 by applying the random forest (RF) algorithm. To develop the optimal RF model, a training set (5914 chemicals) was used to establish models, a validation set (1267 chemicals) used to tune RF parameters and a test set (1267 chemicals) used to assess the performance of RF models. It yielded correlation coefficients R of 0.9695 and rms errors (log unit) of 0.3171 for the training set, R = 0.8322 and rms = 0.2889 for the validation set and R = 0.8335 and rms = 0.3060 for the test set. More than 99% of rat acute oral toxicity logLD50 in the dataset can be accurately predicted, although the dataset is large. [ABSTRACT FROM AUTHOR]

Predictive QSAR models for the search of new adenosine A2A receptor antagonists were developed by using OCHEM platform. The predictive ability of the regression models has coefficient of determination q2 = 0.65−0.71 with cross‐validation and independent test set. The inhibition activities of novel fused 7‐deazaxanthine compounds were predicted by the developed QSAR models. A preparative method for the synthesis of pyrimido[5′,4′:4,5]pyrrolo[1,2‐a][1,4]diazepine derivatives was developed, and 11 new adenosine A2A receptor antagonists were obtained. Preliminary investigations into the toxicology of fused 7‐deazaxanthine compounds toward commonly used model organism to assess toxicity invertebrate cladoceran D. magna were also described. [ABSTRACT FROM AUTHOR]

Histone deacetylase inhibitors are the most important class of drugs for the treatment of oncology and other diseases due to their effect on cell growth, differentiation, and apoptosis. Among the known 18 histone deacetylases, histone deacetylase 6 (HDAC6) that is involved in oncogenesis, cell survival, and cancer cell metastasis is most important. A number of adequate classification models of the quantitative structure–activity relationship (QSAR) are proposed using 2D RDKit molecular descriptors and simplex descriptors, as well as methods of random forest (RF), gradient boosting (GBM), and support vectors (SVM). A structural interpretation is carried out for the models constructed using simplex descriptors which makes it possible to describe the molecular fragments that increase and decrease the activity of HDAC6 inhibitors. The results of the structural interpretation are used for the rational molecular design of potential HDAC6 inhibitors, for which the absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are also evaluated. The models constructed using 2D RDKit descriptors are free to access on the GitHub platform at the following URL: https://github.com/ovttiras/HDAC6-inhibitors. [ABSTRACT FROM AUTHOR]

Malaria accounts for over two million deaths globally. To flatten this curve, there is a need to develop new and high potent drugs against Plasmodium falciparum. Some major challenges include the dearth of suitable animal models for anti-P. falciparum assays, resistance to first-line drugs, lack of vaccines and the complex life cycle of Plasmodium. Gladly, newer approaches to antimalarial drug discovery have emerged due to the release of large datasets by pharmaceutical companies. This review provides insights into these new approaches to drug discovery covering different machine learning tools, which enhance the development of new compounds. It provides a systematic review on the use and prospects of machine learning in predicting, classifying and clustering IC50 values of bioactive compounds against P. falciparum. The authors identified many machine learning tools yet to be applied for this purpose. However, Random Forest and Support Vector Machines have been extensively applied though on a limited dataset of compounds. [ABSTRACT FROM AUTHOR]