The importance of the domain of applicability in QSAR modeling

Chemical space exploration with Molpher: Generating and assessing a glucocorticoid receptor ligand library

Computational exploration of chemical space is crucial in modern cheminformatics research for accelerating the discovery of new biologically active compounds. In this study, we present a detailed analysis of the chemical library of potential glucocorticoid receptor (GR) ligands generated by the molecular generator, Molpher. To generate the targeted GR library and construct the classification models, structures from the ChEMBL database as well as from the internal IMG library, which was experimentally screened for biological activity in the primary luciferase reporter cell assay, were utilized. The composition of the targeted GR ligand library was compared with a reference library that randomly samples chemical space. A random forest model was used to determine the biological activity of ligands, incorporating its applicability domain using conformal prediction. It was demonstrated that the GR library is significantly enriched with GR ligands compared to the random library. Furthermore, a prospective analysis demonstrated that Molpher successfully designed compounds, which were subsequently experimentally confirmed to be active on the GR. A collection of 34 potential new GR ligands was also identified. Moreover, an important contribution of this study is the establishment of a comprehensive workflow for evaluating computationally generated ligands, particularly those with potential activity against targets that are challenging to dock.

Deriving general structure-activity/selectivity relationship patterns for different subfamilies of cyclin-dependent kinase inhibitors using machine learning methods

Cyclin-dependent kinases (CDKs) play essential roles in regulating the cell cycle and are among the most critical targets for cancer therapy and drug discovery. The primary objective of this research is to derive general structure-activity relationship (SAR) patterns for modeling the selectivity and activity levels of CDK inhibitors using machine learning methods. To accomplish this, 8592 small molecules with different binding affinities to CDK1, CDK2, CDK4, CDK5, and CDK9 were collected from Binding DB, and a diverse set of descriptors was calculated for each molecule. The supervised Kohonen networks (SKN) and counter propagation artificial neural networks (CPANN) models were trained to predict the activity levels and therapeutic targets of the molecules. The validity of models was confirmed through tenfold cross-validation and external test sets. Using selected sets of molecular descriptors (e.g. hydrophilicity and total polar surface area) we derived activity and selectivity maps to elucidate local regions in chemical space for active and selective CDK inhibitors. The SKN models exhibited prediction accuracies ranging from 0.75 to 0.94 for the external test sets. The developed multivariate classifiers were used for ligand-based virtual screening of 2 million random molecules of the PubChem database, yielding areas under the receiver operating characteristic curves ranging from 0.72 to 1.00 for the SKN model. Considering the persistent challenge of achieving CDK selectivity, this research significantly contributes to addressing the issue and underscores the paramount importance of developing drugs with minimized side effects.

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

Explainable Graph Neural Networks with Data Augmentation for Predicting pKa of C-H Acids

The pKa of C-H acids is an important parameter in the fields of organic synthesis, drug discovery, and materials science. However, the prediction of pKa is still a great challenge due to the limit of experimental data and the lack of chemical insight. Here, a new model for predicting the pKa values of C-H acids is proposed on the basis of graph neural networks (GNNs) and data augmentation. A message passing unit (MPU) was used to extract the topological and target-related information from the molecular graph data, and a readout layer was utilized to retrieve the information on the ionization site C atom. The retrieved information then was adopted to predict pKa by a fully connected network. Furthermore, to increase the diversity of the training data, a knowledge-infused data augmentation technique was established by replacing the H atoms in a molecule with substituents exhibiting different electronic effects. The MPU was pretrained with the augmented data. The efficacy of data augmentation was confirmed by visualizing the distribution of compounds with different substituents and by classifying compounds. The explainability of the model was studied by examining the change of pKa values when a specific atom was masked. This explainability was used to identify the key substituents for pKa. The model was evaluated on two data sets from the iBonD database. Dataset1 includes the experimental pKa values of C-H acids measured in DMSO, while dataset2 comprises the pKa values measured in water. The results show that the knowledge-infused data augmentation technique greatly improves the predictive accuracy of the model, especially when the number of samples is small.

AttentiveSkin: To Predict Skin Corrosion/Irritation Potentials of Chemicals via Explainable Machine Learning Methods

Skin Corrosion/Irritation (Corr./Irrit.) has long been a health hazard in the Globally Harmonized System (GHS). Several in silico models have been built to predict Skin Corr./Irrit. as an alternative to the increasingly restricted animal testing. However, current studies are limited by data amount/quality and model availability. To address these issues, we compiled a traceable consensus GHS data set comprising 731 Corr., 1283 Irrit., and 1205 negative (Neg.) samples from 6 governmental databases and 2 external data sets. Then, a series of binary classifiers were developed with five machine learning (ML) algorithms and six molecular representations. For 10-fold cross-validation, the best Corr. vs Neg. classifier achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 97.1%, while the best Irrit. vs Neg. classifier achieved an AUC of 84.7%. Compared with existing in silico tools on external validation, our Attentive FP classifiers showed the highest metrics on Corr. vs Neg. and the second highest accuracy on Irrit. vs Neg. The SHapley Additive exPlanation approach was further applied to figure out important molecular features, and the attention weights were visualized to perform interpretable prediction. Structural alerts associated with Skin Corr./Irrit. were also identified. The interpretable Attentive FP classifiers were integrated into the software AttentiveSkin at https://github.com/BeeBeeWong/AttentiveSkin. The conventional ML classifiers are also provided on our platform admetSAR at http://lmmd.ecust.edu.cn/admetsar2/. Considering the data deficiency and the limited model availability of Skin Corr./Irrit., we believe that our data set and models could facilitate chemical safety assessment and relevant studies.

Integration of the Natural Language Processing of Structural Information Simplified Molecular-Input Line-Entry System Can Improve the In Vitro Prediction of Human Skin Sensitizers

Natural language processing (NLP) technology has recently used to predict substance properties based on their Simplified Molecular-Input Line-Entry System (SMILES). We aimed to develop a model predicting human skin sensitizers by integrating text features derived from SMILES with in vitro test outcomes. The dataset on SMILES, physicochemical properties, in vitro tests (DPRA, KeratinoSensTM, h-CLAT, and SENS-IS assays), and human potency categories for 122 substances sourced from the Cosmetics Europe database. The ChemBERTa model was employed to analyze the SMILES of substances. The last hidden layer embedding of ChemBERTa was tested with other features. Given the modest dataset size, we trained five XGBoost models using subsets of the training data, and subsequently employed bagging to create the final model. Notably, the features computed from SMILES played a pivotal role in the model for distinguishing sensitizers and non-sensitizers. The final model demonstrated a classification accuracy of 80% and an AUC-ROC of 0.82, effectively discriminating sensitizers from non-sensitizers. Furthermore, the model exhibited an accuracy of 82% and an AUC-ROC of 0.82 in classifying strong and weak sensitizers. In summary, we demonstrated that the integration of NLP of SMILES with in vitro test results can enhance the prediction of health hazard associated with chemicals.

Machine learning and traditional QSAR modeling methods: a case study of known PXR activators

Pregnane X receptor (PXR), extensively expressed in human tissues related to digestion and metabolism, is responsible for recognizing and detoxifying diverse xenobiotics encountered by humans. To comprehend the promiscuous nature of PXR and its ability to bind a variety of ligands, computational approaches, viz., quantitative structure-activity relationship (QSAR) models, aid in the rapid dereplication of potential toxicological agents and mitigate the number of animals used to establish a meaningful regulatory decision. Recent advancements in machine learning techniques accommodating larger datasets are expected to aid in developing effective predictive models for complex mixtures (viz., dietary supplements) before undertaking in-depth experiments. Five hundred structurally diverse PXR ligands were used to develop traditional two-dimensional (2D) QSAR, machine-learning-based 2D-QSAR, field-based three-dimensional (3D) QSAR, and machine-learning-based 3D-QSAR models to establish the utility of predictive machine learning methods. Additionally, the applicability domain of the agonists was established to ensure the generation of robust QSAR models. A prediction set of dietary PXR agonists was used to externally-validate generated QSAR models. QSAR data analysis revealed that machine-learning 3D-QSAR techniques were more accurate in predicting the activity of external terpenes with an external validation squared correlation coefficient (R2) of 0.70 versus an R2 of 0.52 in machine-learning 2D-QSAR. Additionally, a visual summary of the binding pocket of PXR was assembled from the field 3D-QSAR models. By developing multiple QSAR models in this study, a robust groundwork for assessing PXR agonism from various chemical backbones has been established in anticipation of the identification of potential causative agents in complex mixtures.

Developing a hybrid model for predicting the reaction kinetics between chlorine and micropollutants in water

Understanding the reactivities of chlorine towards micropollutants is crucial for assessing the fate of micropollutants in water chlorination. In this study, we integrated machine learning with kinetic modeling to predict the reaction kinetics between micropollutants and chlorine in deionized water and real surface water. We first established a framework to predict the apparent second-order rate constants for micropollutants with chlorine by combining Morgan molecular fingerprints with machine learning algorithms. The framework was tuned using Bayesian optimization and showed high prediction accuracy. It was validated through experiments and used to predict the unreported apparent second-order rate constants for 103 emerging micropollutants with chlorine. The framework also improved the understanding of the structure-dependence of micropollutants' reactivity with chlorine. We incorporated the predicted apparent second-order rate constants into the Kintecus software to establish a hybrid model to profile the time-dependent changes of micropollutant concentrations by chlorination. The hybrid model was validated by experiments conducted in real surface water in the presence of natural organic matter. The hybrid model could predict how much micropollutants were degraded by chlorination with varied chlorine contact times and/or initial chlorine dosages. This study advances fundamental understanding of the reaction kinetics between chlorine and emerging micropollutants, and also offers a valuable tool to assess the fate of micropollutants during chlorination of drinking water.

Developing a SARS-CoV-2 main protease binding prediction random forest model for drug repurposing for COVID-19 treatment

The coronavirus disease 2019 (COVID-19) global pandemic resulted in millions of people becoming infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and close to seven million deaths worldwide. It is essential to further explore and design effective COVID-19 treatment drugs that target the main protease of SARS-CoV-2, a major target for COVID-19 drugs. In this study, machine learning was applied for predicting the SARS-CoV-2 main protease binding of Food and Drug Administration (FDA)-approved drugs to assist in the identification of potential repurposing candidates for COVID-19 treatment. Ligands bound to the SARS-CoV-2 main protease in the Protein Data Bank and compounds experimentally tested in SARS-CoV-2 main protease binding assays in the literature were curated. These chemicals were divided into training (516 chemicals) and testing (360 chemicals) data sets. To identify SARS-CoV-2 main protease binders as potential candidates for repurposing to treat COVID-19, 1188 FDA-approved drugs from the Liver Toxicity Knowledge Base were obtained. A random forest algorithm was used for constructing predictive models based on molecular descriptors calculated using Mold2 software. Model performance was evaluated using 100 iterations of fivefold cross-validations which resulted in 78.8% balanced accuracy. The random forest model that was constructed from the whole training dataset was used to predict SARS-CoV-2 main protease binding on the testing set and the FDA-approved drugs. Model applicability domain and prediction confidence on drugs predicted as the main protease binders discovered 10 FDA-approved drugs as potential candidates for repurposing to treat COVID-19. Our results demonstrate that machine learning is an efficient method for drug repurposing and, thus, may accelerate drug development targeting SARS-CoV-2.

In silico modeling-based new alternative methods to predict drug and herb-induced liver injury: A review

New approach methods (NAMs) have been developed to predict a wide range of toxicities through innovative technologies. Liver injury is one of the most extensively studied endpoints due to its severity and frequency, occurring among populations that consume drugs or dietary supplements. In this review, we focus on recent developments of in silico modeling for liver injury prediction using deep learning and in vitro data based on adverse outcome pathways (AOPs). Despite these models being mainly developed using datasets generated from drug-like molecules, they were also applied to the prediction of hepatotoxicity caused by herbal products. As deep learning has achieved great success in many different fields, advanced machine learning algorithms have been actively applied to improve the accuracy of in silico models. Additionally, the development of liver AOPs, combined with big data in toxicology, has been valuable in developing in silico models with enhanced predictive performance and interpretability. Specifically, one approach involves developing structure-based models for predicting molecular initiating events of liver AOPs, while others use in vitro data with structure information as model inputs for making predictions. Even though liver injury remains a difficult endpoint to predict, advancements in machine learning algorithms and the expansion of in vitro databases with relevant biological knowledge have made a huge impact on improving in silico modeling for drug-induced liver injury prediction.

Virtual Screening of Different Subclasses of Lignans with Anticancer Potential and Based on Genetic Profile

Cancer is a multifactorial disease that continues to increase. Lignans are known to be important anticancer agents. However, due to the structural diversity of lignans, it is difficult to associate anticancer activity with a particular subclass. Therefore, the present study sought to evaluate the association of lignan subclasses with antitumor activity, considering the genetic profile of the variants of the selected targets. To do so, predictive models were built against the targets tyrosine-protein kinase ABL (ABL), epidermal growth factor receptor erbB1 (EGFR), histone deacetylase (HDAC), serine/threonine-protein kinase mTOR (mTOR) and poly [ADP-ribose] polymerase-1 (PARP1). Then, single nucleotide polymorphisms were mapped, target mutations were designed, and molecular docking was performed with the lignans with the best predicted biological activity. The results showed more anticancer activity in the dibenzocyclooctadiene, furofuran and aryltetralin subclasses. The lignans with the best predictive values of biological activity showed varying binding energy results in the presence of certain genetic variants.

Improvement of multi-task learning by data enrichment: application for drug discovery

Multi-task learning in deep neural networks has become a topic of growing importance in many research fields, including drug discovery. However, applying multi-task learning poses new challenges in improving prediction performance. This study investigated the potential of training data enrichment to enhance multi-task model prediction quality in drug discovery. The study evaluated four scenarios with varying degrees of information capacity of the training data and applied two types of test data to evaluate prediction performance. We used three datasets: ViralChEMBL, which consisted of binary activities of compounds against viral species, was applied for the classification task; pQSAR(159) and pQSAR(4267), which consisted of bio-activities of compounds and assays from the research of the profile-QSAR method, were applied for regression tasks. We built multi-task models based on the feed-forward DNNs using the PyTorch framework. Our findings showed that training data enrichment could be an effective means of enhancing prediction performance in multi-task learning, but the degree of improvement depends on the quality of the training data. The more unique compounds and targets the training data included, the more new compound-target interactions are required for prediction improvement. Also, we found out that even using multi-task learning, one could not predict the interactions of compounds that are highly dissimilar from those used for model training. The study provides some recommendations for effectively employing multi-task learning in drug discovery to improve prediction accuracy and facilitate the discovery of novel drug candidates.

Development of QSPR-ANN models for the estimation of critical properties of pure hydrocarbons

The current work aimed to predict three critical properties: critical temperature (Tc), critical volume (Vc), and critical pressure (Pc) of pure hydrocarbons. A multi-layer perceptron artificial neural network (MLP-ANN) has been adopted as a nonlinear modeling technique and computational approach based on a few relevant molecular descriptors. A set of diverse data points was used to build three QSPR-ANN models, including 223 points for Tc, Vc, and 221 for Pc. The entire database was randomly split into two subsets: 80% for the training set and 20% for the testing set. A large number of 1666 molecular descriptors were calculated and then reduced by a statistical methodology based on several phases to retain them into a reasonable number of relevant descriptors, wherein about 99% of initial descriptors were excluded. Thus, the Quasi-Newton backpropagation (BFGS) algorithm was applied to train the ANN structure. The results of three QSPR-ANN models showed good precision, confirmed by the high values of determination coefficient (R²) ranging from 0.9990 to 0.9945, and the low values of calculated errors, such as the Mean Absolute Percentage Error (MAPE) that ranged from 2.2497 to 0.7424% for the best three models of Tc, Vc, and Pc. The weight sensitivity analysis method was applied to know the contribution of each input descriptor individually or by class on each appropriate QSPR-ANN model. Moreover, the applicability domain (AD) method was also used with a strict limit of standardized residual values (d_i = ±2). However, the results were promising, with nearly 88% of the data points validated within the AD range. Finally, the results of the proposed QSPR-ANN models were compared with other well-known QSPR or ANN models for each property. Consequently, our three models provided satisfactory results, outperforming most of the models mentioned in this comparison. This computational approach can be applied in petroleum engineering and other related fields to accurately determine the critical properties of pure hydrocarbons: Tc, Vc, and Pc.

Design of New Dispersants Using Machine Learning and Visual Analytics

Artificial intelligence (AI) is an emerging technology that is revolutionizing the discovery of new materials. One key application of AI is virtual screening of chemical libraries, which enables the accelerated discovery of materials with desired properties. In this study, we developed computational models to predict the dispersancy efficiency of oil and lubricant additives, a critical property in their design that can be estimated through a quantity named blotter spot. We propose a comprehensive approach that combines machine learning techniques with visual analytics strategies in an interactive tool that supports domain experts' decision-making. We evaluated the proposed models quantitatively and illustrated their benefits through a case study. Specifically, we analyzed a series of virtual polyisobutylene succinimide (PIBSI) molecules derived from a known reference substrate. Our best-performing probabilistic model was Bayesian Additive Regression Trees (BART), which achieved a mean absolute error of 5.50±0.34 and a root mean square error of 7.56±0.47, as estimated through 5-fold cross-validation. To facilitate future research, we have made the dataset, including the potential dispersants used for modeling, publicly available. Our approach can help accelerate the discovery of new oil and lubricant additives, and our interactive tool can aid domain experts in making informed decisions based on blotter spot and other key properties.

Predictive Modeling of PROTAC Cell Permeability with Machine Learning

Approaches for predicting proteolysis targeting chimera (PROTAC) cell permeability are of major interest to reduce resource-demanding synthesis and testing of low-permeable PROTACs. We report a comprehensive investigation of the scope and limitations of machine learning-based binary classification models developed using 17 simple descriptors for large and structurally diverse sets of cereblon (CRBN) and von Hippel-Lindau (VHL) PROTACs. For the VHL PROTAC set, kappa nearest neighbor and random forest models performed best and predicted the permeability of a blinded test set with >80% accuracy (k ≥ 0.57). Models retrained by combining the original training and the blinded test set performed equally well for a second blinded VHL set. However, models for CRBN PROTACs were less successful, mainly due to the imbalanced nature of the CRBN datasets. All descriptors contributed to the models, but size and lipophilicity were the most important. We conclude that properly trained machine learning models can be integrated as effective filters in the PROTAC design process.

Data-Driven Multi-Objective Optimization Tactics for Catalytic Asymmetric Reactions Using Bisphosphine Ligands

Optimization of the catalyst structure to simultaneously improve multiple reaction objectives (e.g., yield, enantioselectivity, and regioselectivity) remains a formidable challenge. Herein, we describe a machine learning workflow for the multi-objective optimization of catalytic reactions that employ chiral bisphosphine ligands. This was demonstrated through the optimization of two sequential reactions required in the asymmetric synthesis of an active pharmaceutical ingredient. To accomplish this, a density functional theory-derived database of >550 bisphosphine ligands was constructed, and a designer chemical space mapping technique was established. The protocol used classification methods to identify active catalysts, followed by linear regression to model reaction selectivity. This led to the prediction and validation of significantly improved ligands for all reaction outputs, suggesting a general strategy that can be readily implemented for reaction optimizations where performance is controlled by bisphosphine ligands.

TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity

Herein, a robust and reproducible eXplainable Artificial Intelligence (XAI) approach is presented, which allows prediction of developmental toxicity, a challenging human-health endpoint in toxicology. The application of XAI as an alternative method is of the utmost importance with developmental toxicity being one of the most animal-intensive areas of regulatory toxicology. In this work, the established CAESAR (Computer Assisted Evaluation of industrial chemical Substances According to Regulations) training set made of 234 chemicals for model learning is employed. Two test sets, including as a whole 585 chemicals, were instead used for validation and generalization purposes. The proposed framework favorably compares with the state-of-the-art approaches in terms of accuracy, sensitivity, and specificity, thus resulting in a reliable support system for developmental toxicity ensuring informativeness, uncertainty estimation, generalization, and transparency. Based on the eXtreme Gradient Boosting (XGB) algorithm, our predictive model provides easy interpretative keys based on specific molecular descriptors and structural alerts enabling one to distinguish toxic and nontoxic chemicals. Inspired by the Organisation for Economic Co-operation and Development (OECD) principles for the validation of Quantitative Structure-Activity Relationships (QSARs) for regulatory purposes, the results are summarized in a standard report in portable document format, enclosing also details concerned with a density-based model applicability domain and SHAP (SHapley Additive exPlanations) explainability, the latter particularly useful to better understand the effective roles played by molecular features. Notably, our model has been implemented in TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), a free of charge web platform available at http://tiresia.uniba.it.

In silico prediction of siRNA ionizable-lipid nanoparticles In vivo efficacy: Machine learning modeling based on formulation and molecular descriptors

In silico prediction of the in vivo efficacy of siRNA ionizable-lipid nanoparticles is desirable as it can save time and resources dedicated to wet-lab experimentation. This study aims to computationally predict siRNA nanoparticles in vivo efficacy. A data set containing 120 entries was prepared by combining molecular descriptors of the ionizable lipids together with two nanoparticles formulation characteristics. Input descriptor combinations were selected by an evolutionary algorithm. Artificial neural networks, support vector machines and partial least squares regression were used for QSAR modeling. Depending on how the data set is split, two training sets and two external validation sets were prepared. Training and validation sets contained 90 and 30 entries respectively. The results showed the successful predictions of validation set log (siRNA dose) with R_val ²= 0.86-0.89 and 0.75-80 for validation sets one and two, respectively. Artificial neural networks resulted in the best R_val ² for both validation sets. For predictions that have high bias, improvement of R_val ² from 0.47 to 0.96 was achieved by selecting the training set lipids lying within the applicability domain. In conclusion, in vivo performance of siRNA nanoparticles was successfully predicted by combining cheminformatics with machine learning techniques.

Design and Synthesis of Novel Double-Ring Conjugated Enones as Potent Anti-rheumatoid Arthritis Agents

Rheumatoid arthritis (RA) is a chronic and systemic disease of inflammatory synovitis with unknown etiology. In previous studies, we found that the double-ring conjugated enone structure has anti-rheumatoid arthritis activity and could effectively inhibit the proliferation of rat synovial cells in vitro and has good anti-inflammatory activity in vivo. Herein, we further modified the structure, which was a novel double-ring conjugated enone, to study its anti-rheumatoid arthritis activity. Results showed that the most potent compound 32 could effectively inhibit the proliferation of rat synovial cells in vitro and has better anti-inflammatory activity compared with that of the positive control methotrexate, as shown by in vivo activity evaluation. More interestingly, compound 32 could effectively inhibit the increase of TNF-α, IL-1β, and IL-6 induced by LPS and regulate the expression of TLR4, MyD88, NF-κB, and IκB in the signaling pathway of TLR4/NF-κB. Our results provided a promising starting point for the development of highly effective small molecules for the treatment of RA.

MolPredictX: Online Biological Activity Predictions by Machine Learning Models

Here we report the development of MolPredictX, an innovate and freely accessible web interface for biological activity predictions of query molecules. MolPredictX utilizes in-house QSAR models to provide 27 qualitative predictions (active or inactive), and quantitative probabilities for bioactivity against parasitic (Trypanosoma and Leishmania), viral (Dengue, Sars-CoV and Hepatitis C), pathogenic yeast (Candida albicans), bacterial (Salmonella enterica and Escherichia coli), and Alzheimer disease enzymes. In this article, we introduce the methodology and usability of this webtool, highlighting its potential role in the development of new drugs against a variety of diseases. MolPredictX is undergoing continuous development and is freely available at https://www.molpredictx.ufpb.br/.

Exposure forecasting - ExpoCast - for data-poor chemicals in commerce and the environment

Estimates of exposure are critical to prioritize and assess chemicals based on risk posed to public health and the environment. The U.S. Environmental Protection Agency (EPA) is responsible for regulating thousands of chemicals in commerce and the environment for which exposure data are limited. Since 2009 the EPA's ExpoCast ("Exposure Forecasting") project has sought to develop the data, tools, and evaluation approaches required to generate rapid and scientifically defensible exposure predictions for the full universe of existing and proposed commercial chemicals. This review article aims to summarize issues in exposure science that have been addressed through initiatives affiliated with ExpoCast. ExpoCast research has generally focused on chemical exposure as a statistical systems problem intended to inform thousands of chemicals. The project exists as a companion to EPA's ToxCast ("Toxicity Forecasting") project which has used in vitro high-throughput screening technologies to characterize potential hazard posed by thousands of chemicals for which there are limited toxicity data. Rapid prediction of chemical exposures and in vitro-in vivo extrapolation (IVIVE) of ToxCast data allow for prioritization based upon risk of adverse outcomes due to environmental chemical exposure. ExpoCast has developed (1) integrated modeling approaches to reliably predict exposure and IVIVE dose, (2) highly efficient screening tools for chemical prioritization, (3) efficient and affordable tools for generating new exposure and dose data, and (4) easily accessible exposure databases. The development of new exposure models and databases along with the application of technologies like non-targeted analysis and machine learning have transformed exposure science for data-poor chemicals. By developing high-throughput tools for chemical exposure analytics and translating those tools into public health decisions ExpoCast research has served as a crucible for identifying and addressing exposure science knowledge gaps.

Dual Inhibitors of AChE and BACE-1 for Reducing Aβ in Alzheimer's Disease: From In Silico to In Vivo

Alzheimer's disease (AD) is a complex and widespread condition, still not fully understood and with no cure yet. Amyloid beta (Aβ) peptide is suspected to be a major cause of AD, and therefore, simultaneously blocking its formation and aggregation by inhibition of the enzymes BACE-1 (β-secretase) and AChE (acetylcholinesterase) by a single inhibitor may be an effective therapeutic approach, as compared to blocking one of these targets or by combining two drugs, one for each of these targets. We used our ISE algorithm to model each of the AChE peripheral site inhibitors and BACE-1 inhibitors, on the basis of published data, and constructed classification models for each. Subsequently, we screened large molecular databases with both models. Top scored molecules were docked into AChE and BACE-1 crystal structures, and 36 Molecules with the best weighted scores (based on ISE indexes and docking results) were sent for inhibition studies on the two enzymes. Two of them inhibited both AChE (IC₅₀ between 4-7 μM) and BACE-1 (IC₅₀ between 50-65 μM). Two additional molecules inhibited only AChE, and another two molecules inhibited only BACE-1. Preliminary testing of inhibition by F681-0222 (molecule 2) on APPswe/PS1dE9 transgenic mice shows a reduction in brain tissue of soluble Aβ42.

Hierarchical Clustering and Target-Independent QSAR for Antileishmanial Oxazole and Oxadiazole Derivatives

Leishmaniasis is a neglected tropical disease that kills more than 20,000 people each year. The chemotherapy available for the treatment of the disease is limited, and novel approaches to discover novel drugs are urgently needed. Herein, 2D- and 4D-quantitative structure–activity relationship (QSAR) models were developed for a series of oxazole and oxadiazole derivatives that are active against Leishmania infantum, the causative agent of visceral leishmaniasis. A clustering strategy based on structural similarity was applied with molecular fingerprints to divide the complete set of compounds into two groups. Hierarchical clustering was followed by the development of 2D- (R2 = 0.90, R2pred = 0.82) and 4D-QSAR models (R2 = 0.80, R2pred = 0.64), which showed improved statistical robustness and predictive ability.

Review of in silico studies dedicated to the nuclear receptor family: Therapeutic prospects and toxicological concerns

Being in the center of both therapeutic and toxicological concerns, NRs are widely studied for drug discovery application but also to unravel the potential toxicity of environmental compounds such as pesticides, cosmetics or additives. High throughput screening campaigns (HTS) are largely used to detect compounds able to interact with this protein family for both therapeutic and toxicological purposes. These methods lead to a large amount of data requiring the use of computational approaches for a robust and correct analysis and interpretation. The output data can be used to build predictive models to forecast the behavior of new chemicals based on their in vitro activities. This atrticle is a review of the studies published in the last decade and dedicated to NR ligands in silico prediction for both therapeutic and toxicological purposes. Over 100 articles concerning 14 NR subfamilies were carefully read and analyzed in order to retrieve the most commonly used computational methods to develop predictive models, to retrieve the databases deployed in the model building process and to pinpoint some of the limitations they faced.

Deep Neural Networks for QSAR

Quantitative structure-activity relationship (QSAR) models are routinely applied computational tools in the drug discovery process. QSAR models are regression or classification models that predict the biological activities of molecules based on the features derived from their molecular structures. These models are usually used to prioritize a list of candidate molecules for future laboratory experiments and to help chemists gain better insights into how structural changes affect a molecule's biological activities. Developing accurate and interpretable QSAR models is therefore of the utmost importance in the drug discovery process. Deep neural networks, which are powerful supervised learning algorithms, have shown great promise for addressing regression and classification problems in various research fields, including the pharmaceutical industry. In this chapter, we briefly review the applications of deep neural networks in QSAR modeling and describe commonly used techniques to improve model performance.

Some important inhibitors and mechanisms of rheumatoid arthritis

Rheumatoid arthritis is a chronic disease that seriously affects human health and quality of life, and it is one of the main causes of labor loss and disability. Many countries have listed rheumatoid arthritis as one of the national a key diseases to tackle. The pathogenesis of RA in humans is still unknown, and medical researchers believe that the pathogenesis of RA may be the result of a combination of genetic and environmental factors. RA is an incurable condition that can only be controlled and treated with conventional drugs. In this paper, the pathologic features and pathogenesis of RA were introduced, and the research progress of new anti-rheumatoid arthritis chemical drugs in recent years was reviewed.

Artificial Intelligence in Compound Design

Artificial intelligence has seen an incredibly fast development in recent years. Many novel technologies for property prediction of drug molecules as well as for the design of novel molecules were introduced by different research groups. These artificial intelligence-based design methods can be applied for suggesting novel chemical motifs in lead generation or scaffold hopping as well as for optimization of desired property profiles during lead optimization. In lead generation, broad sampling of the chemical space for identification of novel motifs is required, while in the lead optimization phase, a detailed exploration of the chemical neighborhood of a current lead series is advantageous. These different requirements for successful design outcomes render different combinations of artificial intelligence technologies useful. Overall, we observe that a combination of different approaches with tailored scoring and evaluation schemes appears beneficial for efficient artificial intelligence-based compound design.

Prioritization of Mycotoxins Based on Their Genotoxic Potential with an In Silico-In Vitro Strategy

Humans are widely exposed to a great variety of mycotoxins and their mixtures. Therefore, it is important to design strategies that allow prioritizing mycotoxins based on their toxic potential in a time and cost-effective manner. A strategy combining in silico tools (Phase 1), including an expert knowledge-based (DEREK Nexus®, Lhasa Limited, Leeds, UK) and a statistical-based platform (VEGA QSAR©, Mario Negri Institute, Milan, Italy), followed by the in vitro SOS/umu test (Phase 2), was applied to a set of 12 mycotoxins clustered according to their structure into three groups. Phase 1 allowed us to clearly classify group 1 (aflatoxin and sterigmatocystin) as mutagenic and group 3 (ochratoxin A, zearalenone and fumonisin B1) as non-mutagenic. For group 2 (trichothecenes), contradictory conclusions were obtained between the two in silico tools, being out of the applicability domain of many models. Phase 2 confirmed the results obtained in the previous phase for groups 1 and 3. It also provided extra information regarding the role of metabolic activation in aflatoxin B1 and sterigmatocystin mutagenicity. Regarding group 2, equivocal results were obtained in few experiments; however, the group was finally classified as non-mutagenic. The strategy used correlated with the published Ames tests, which detect point mutations. Few alerts for chromosome aberrations could be detected. The SOS/umu test appeared as a good screening test for mutagenicity that can be used in the absence and presence of metabolic activation and independently of Phase 1, although the in silico-in vitro combination gave more information for decision making.

Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty

Measurements of protein–ligand interactions have reproducibility limits due to experimental errors. Any model based on such assays will consequentially have such unavoidable errors influencing their performance which should ideally be factored into modelling and output predictions, such as the actual standard deviation of experimental measurements (σ) or the associated comparability of activity values between the aggregated heterogenous activity units (i.e., K_i versus IC₅₀ values) during dataset assimilation. However, experimental errors are usually a neglected aspect of model generation. In order to improve upon the current state-of-the-art, we herein present a novel approach toward predicting protein–ligand interactions using a Probabilistic Random Forest (PRF) classifier. The PRF algorithm was applied toward in silico protein target prediction across ~ 550 tasks from ChEMBL and PubChem. Predictions were evaluated by taking into account various scenarios of experimental standard deviations in both training and test sets and performance was assessed using fivefold stratified shuffled splits for validation. The largest benefit in incorporating the experimental deviation in PRF was observed for data points close to the binary threshold boundary, when such information was not considered in any way in the original RF algorithm. For example, in cases when σ ranged between 0.4–0.6 log units and when ideal probability estimates between 0.4–0.6, the PRF outperformed RF with a median absolute error margin of ~ 17%. In comparison, the baseline RF outperformed PRF for cases with high confidence to belong to the active class (far from the binary decision threshold), although the RF models gave errors smaller than the experimental uncertainty, which could indicate that they were overtrained and/or over-confident. Finally, the PRF models trained with putative inactives decreased the performance compared to PRF models without putative inactives and this could be because putative inactives were not assigned an experimental pXC₅₀ value, and therefore they were considered inactives with a low uncertainty (which in practice might not be true). In conclusion, PRF can be useful for target prediction models in particular for data where class boundaries overlap with the measurement uncertainty, and where a substantial part of the training data is located close to the classification threshold.

Interrogation of Bacillus anthracis SrtA active site loop forming open/close lid conformations through extensive MD simulations for understanding binding selectivity of SrtA inhibitors

Bacillus anthracis is a gram positive, deadly spore forming bacteria causing anthrax and these bacteria having the complex mechanism in the cell wall envelope, which can adopt the changes in environmental conditions. In this, the membrane bound cell wall proteins are said to progressive drug target for the inhibition of Bacillus anthracis. Among the cell wall proteins, the SrtA is one of the important mechanistic protein, which mediate the ligation with LPXTG motif by forming the amide bonds. The SrtA plays the vital role in cell signalling, cell wall formation, and biofilm formations. Inhibition of SrtA leads to rupture of the cell wall and biofilm formation, and that leads to inhibition of Bacillus anthracis and thus, SrtA is core important enzyme to study the inhibition mechanism. In this study, we have examined 28 compounds, which have the inhibitory activity against the Bacillus anthracis SrtA for developing the 3D-QSAR and also, compounds binding selectivity with both open and closed SrtA conformations, obtained from 100 ns of MD simulations. The binding site loop deviate in forming the open and closed gate mechanism is investigated to understand the inhibitory profile of reported compounds, and results show the closed state active site conformations are required for ligand binding specificity. Overall, the present study may offer an opportunity for better understanding of the mechanism of action and can be aided to further designing of a novel and highly potent SrtA inhibitors.

Predicting aqueous solubility by QSPR modeling

The aqueous solubility is predicted here using quantitative structure property relationship (QSPR) models. In this study, we examine whether descriptors that individually yield favorable models for the prediction of the Gibbs energy of solvation and sublimation can be used in combination with octanol-water partition coefficient to produce QSPR models for the prediction of aqueous solubility. Based on this strategy, applied to seven distinct datasets, all models exhibited an R² greater than 0.7 and Q² greater than 0.6 for the estimation of aqueous solubility. We also determined how uncoupling the descriptors used to create QSPR models in the prediction of Gibbs energy of sublimation yielded an improved model. Model refinement using an artificial neural network applying the same descriptors generated significantly better models with improved R² and standard deviation.

Chemoinformatics Studies on a Series of Imidazoles as Cruzain Inhibitors

Natural products based on imidazole scaffolds have inspired the discovery of a wide variety of bioactive compounds. Herein, a series of imidazoles that act as competitive and potent cruzain inhibitors was investigated using a combination of ligand- and structure-based drug design strategies. Quantitative structure-activity relationships (QSARs) were generated along with the investigation of enzyme-inhibitor molecular interactions. Predictive hologram QSAR (HQSAR, r²_pred = 0.80) and AutoQSAR (q² = 0.90) models were built, and key structural properties that underpin cruzain inhibition were identified. Moreover, comparative molecular field analysis (CoMFA, r²_pred = 0.81) and comparative molecular similarity indices analysis (CoMSIA, r²_pred = 0.73) revealed 3D molecular features that strongly affect the activity of the inhibitors. These findings were examined along with molecular docking studies and were highly compatible with the intermolecular contacts that take place between cruzain and the inhibitors. The results gathered herein revealed the main factors that determine the activity of the imidazoles studied and provide novel knowledge for the design of improved cruzain inhibitors.

QSAR Modeling, Molecular Docking and Molecular Dynamics Simulations Studies of Lysine-Specific Demethylase 1 (LSD1) Inhibitors as Anticancer Agents

BACKGROUND

Histone Lysine Demetylases1 (LSD1) is a promising medication to treat cancer, which plays a crucial role in epigenetic modulation of gene expression. Inhibition of LSD1with small molecules has emerged as a vital mechanism to treat cancer.

OBJECTIVE

In the present research, molecular modeling investigations, such as CoMFA, CoMFA-RF, CoMSIA and HQSAR, molecular docking and Molecular Dynamics (MD) simulations were carried out on some tranylcypromine derivatives as LSD1 inhibitors.

METHODS

The QSAR models were carried out on a series of Tranylcypromine derivatives as data set via the SYBYL-X2.1.1 program. Molecular docking and MD simulations were carried out by the MOE software and the SYBYL program, respectively. The internal and external predictability performances related to the generated models for these LSD1 inhibitors were justified by evaluating cross-validated correlation coefficient (q²), noncross- validated correlation coefficient (r²_ncv) and predicted correlation coefficient (r²_pred) of the training and test set molecules, respectively.

RESULTS

The CoMFA (q², 0.670; r²_ncv, 0.930; r²_pred, 0.968), CoMFA-RF (q², 0.694; r²_ncr, 0.926; r²_pred, 0.927), CoMSIA (q², 0.834; r²_ncv, 0.956; r²_pred, 0.958) and HQSAR models (q², 0.854; r²_ncv, 0.900; r²_pred, 0.728) for training as well as the test set of LSD1 inhibition resulted in significant findings.

CONCLUSION

These QSAR models were found to be perfect and strong with better predictability. Contour maps of all models were generated and it was proven by molecular docking studies and molecular dynamics simulation that the hydrophobic, electrostatic and hydrogen bonding fields are crucial in these models for improving the binding affinity and determining the structure-activity relationship. These theoretical results are possibly beneficial to design new strong LSD1 inhibitors with enhanced activity to treat cancer.

MAIP: a web service for predicting blood-stage malaria inhibitors

Malaria is a disease affecting hundreds of millions of people across the world, mainly in developing countries and especially in sub-Saharan Africa. It is the cause of hundreds of thousands of deaths each year and there is an ever-present need to identify and develop effective new therapies to tackle the disease and overcome increasing drug resistance. Here, we extend a previous study in which a number of partners collaborated to develop a consensus in silico model that can be used to identify novel molecules that may have antimalarial properties. The performance of machine learning methods generally improves with the number of data points available for training. One practical challenge in building large training sets is that the data are often proprietary and cannot be straightforwardly integrated. Here, this was addressed by sharing QSAR models, each built on a private data set. We describe the development of an open-source software platform for creating such models, a comprehensive evaluation of methods to create a single consensus model and a web platform called MAIP available at https://www.ebi.ac.uk/chembl/maip/ . MAIP is freely available for the wider community to make large-scale predictions of potential malaria inhibiting compounds. This project also highlights some of the practical challenges in reproducing published computational methods and the opportunities that open-source software can offer to the community.

Recent advances in quantitative structure-activity relationship models of antimalarial drugs

INTRODUCTION

Due to emerging resistance to the first-line artemisinin-based antimalarials and lack of efficient vaccines and limited chemotherapeutic alternatives, there is an urgent need to develop new antimalarial compounds. In this regard, quantitative structure-activity relationship (QSAR) modeling can provide essential information about required physicochemical properties and structural parameters of antimalarial drug candidates.

AREAS COVERED

The authors provide an overview of recent advances of QSAR models covering different classes of antimalarial compounds as well as molecular docking studies of compounds acting on different antimalarial targets reported in the last 5 years (2015-2019) to explore the mode of interactions between the molecules and the receptors. We have tried to cover most of the QSAR models of antimalarials (along with results from some other related computational methods) reported during 2015-2019.

EXPERT OPINION

Many QSAR reports for antimalarial compounds are based on small number of data points. This review infers that most of the present work deals with analog-based QSAR approach with a limited applicability domain (a very few cases with wide domain) whereas novel target-based computational approach is reported in very few cases, which leads to huge voids of computational work based on novel antimalarial targets.

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

By combining metal nodes with organic linkers we can potentially synthesize millions of possible metal-organic frameworks (MOFs). The fact that we have so many materials opens many exciting avenues but also create new challenges. We simply have too many materials to be processed using conventional, brute force, methods. In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations. The first part of the review gives an introduction to the principles of big-data science. We show how to select appropriate training sets, survey approaches that are used to represent these materials in feature space, and review different learning architectures, as well as evaluation and interpretation strategies. In the second part, we review how the different approaches of machine learning have been applied to porous materials. In particular, we discuss applications in the field of gas storage and separation, the stability of these materials, their electronic properties, and their synthesis. Given the increasing interest of the scientific community in machine learning, we expect this list to rapidly expand in the coming years.

Retip: Retention Time Prediction for Compound Annotation in Untargeted Metabolomics

Unidentified peaks remain a major problem in untargeted metabolomics by LC-MS/MS. Confidence in peak annotations increases by combining MS/MS matching and retention time. We here show how retention times can be predicted from molecular structures. Two large, publicly available data sets were used for model training in machine learning: the Fiehn hydrophilic interaction liquid chromatography data set (HILIC) of 981 primary metabolites and biogenic amines,and the RIKEN plant specialized metabolome annotation (PlaSMA) database of 852 secondary metabolites that uses reversed-phase liquid chromatography (RPLC). Five different machine learning algorithms have been integrated into the Retip R package: the random forest, Bayesian-regularized neural network, XGBoost, light gradient-boosting machine (LightGBM), and Keras algorithms for building the retention time prediction models. A complete workflow for retention time prediction was developed in R. It can be freely downloaded from the GitHub repository (https://www.retip.app). Keras outperformed other machine learning algorithms in the test set with minimum overfitting, verified by small error differences between training, test, and validation sets. Keras yielded a mean absolute error of 0.78 min for HILIC and 0.57 min for RPLC. Retip is integrated into the mass spectrometry software tools MS-DIAL and MS-FINDER, allowing a complete compound annotation workflow. In a test application on mouse blood plasma samples, we found a 68% reduction in the number of candidate structures when searching all isomers in MS-FINDER compound identification software. Retention time prediction increases the identification rate in liquid chromatography and subsequently leads to an improved biological interpretation of metabolomics data.

Molecular docking-based classification and systematic QSAR analysis of indoles as Pim kinase inhibitors

Pim kinase enzyme has an essential role in the treatment of prostate, colon and acute myeloid leukaemia cancers. The indoles inhibitors were docked in the enzyme's active pocket in order to survey the inhibition mechanism and extract the ligands' conformations. The docking outcome shows that the active inhibitors have strong van der Waals interactions with residues of Ile185, Leu44, Leu120 and Leu174, hydrogen bonds with residues of Asp128, Arg122 and Glu171 and π-π interaction with the residue of Phe49. The sum of these interactions is ~80 kcal mol^-1 contributing ~90% of total binding free energies. Using docking-based molecular descriptors, the unsupervised and supervised classifications were successfully carried out with the accuracy of 0.82 and 0.95, respectively, to categorize the active/inactive Pim kinase inhibitors. The vigorous quantitative assessment was performed using different machine learning techniques. The constructed QSAR model [(r ² _cal, r ² _p, r ² _m and Q ² _LOO) > 0.80 and (SE _cal, SE_p and SE _LOO) < 0.22] indicates that the molecular descriptors of nN, RDF20v and E1v can describe both the inhibition activities and the inhibition mechanism. The adequate evaluations of the molecular docking, classifications and QSAR analysis show that the current approaches can be used as valuable tools to design more effective new Pim kinase inhibitors for cancer treatment.

In-Silico QSAR Modelling of Predicted Rho Kinase Inhibitors Against Cardio Vascular Diseases

BACKGROUND

Rho-kinase is an essential downstream target of GTP-binding protein RhoA, and plays a crucial role in the calcium-sensitization pathway. Rho-kinase pathway is critically involved in phosphorylation state of myosin light chain, leading to increased contraction of smooth muscles. Inhibition of this pathway has turned out to be a promising target for several indications such as cardiovascular diseases, glaucoma and inflammatory diseases.

METHODS

The present work focuses on a division-based 2D quantitative structure-activity relationship (QSAR) analysis along with a docking study to predict structural features that may be essential for the enhancement of selectivity and potency of the target compounds. Furthermore, a set of indoles and azaindoles were also projected based on the regression equation as novel developments. Molecular docking was applied for exploring the binding sites of the newly predicted set of compounds with the receptor.

RESULTS

Results of the docked conformations suggested that introduction of non-bulky and substituted groups in the hinge region of ROCK-II ATP binding pocket would improve the activity by decreasing the bulkiness or length of the compounds.

CONCLUSION

ADME studies were performed to ascertain the novelty and drug-like properties of the designed molecules, respectively.

Towards reproducible computational drug discovery

The reproducibility of experiments has been a long standing impediment for further scientific progress. Computational methods have been instrumental in drug discovery efforts owing to its multifaceted utilization for data collection, pre-processing, analysis and inference. This article provides an in-depth coverage on the reproducibility of computational drug discovery. This review explores the following topics: (1) the current state-of-the-art on reproducible research, (2) research documentation (e.g. electronic laboratory notebook, Jupyter notebook, etc.), (3) science of reproducible research (i.e. comparison and contrast with related concepts as replicability, reusability and reliability), (4) model development in computational drug discovery, (5) computational issues on model development and deployment, (6) use case scenarios for streamlining the computational drug discovery protocol. In computational disciplines, it has become common practice to share data and programming codes used for numerical calculations as to not only facilitate reproducibility, but also to foster collaborations (i.e. to drive the project further by introducing new ideas, growing the data, augmenting the code, etc.). It is therefore inevitable that the field of computational drug design would adopt an open approach towards the collection, curation and sharing of data/code.