alvaDesc: A Tool to Calculate and Analyze Molecular Descriptors and Fingerprints

Targeting bacterial growth in biofilm conditions: rational design of novel inhibitors to mitigate clinical and food contamination using QSAR

Antimicrobial resistance (AMR) is a pressing global issue exacerbated by the abuse of antibiotics and the formation of bacterial biofilms, which cause up to 80% of human bacterial infections. This study presents a computational strategy to address AMR by developing three novel quantitative structure-activity relationship (QSAR) models based on molecular topology to identify potential anti-biofilm and antibacterial agents. The models aim to determine the chemo-topological pattern of Gram (+) antibacterial, Gram (-) antibacterial, and biofilm formation inhibition activity. The models were applied to the virtual screening of a commercial chemical database, resulting in the selection of 58 compounds. Subsequent in vitro assays showed that three of these compounds exhibited the most promising antibacterial activity, with potential applications in enhancing food and medical device safety.

Machine learning-based q-RASAR predictions of the bioconcentration factor of organic molecules estimated following the organisation for economic co-operation and development guideline 305

In this study, we utilized an innovative quantitative read-across (RA) structure-activity relationship (q-RASAR) approach to predict the bioconcentration factor (BCF) values of a diverse range of organic compounds, based on a dataset of 575 compounds tested using Organisation for Economic Co-operation and Development Test Guideline 305 for bioaccumulation in fish. Initially, we constructed the q-RASAR model using the partial least squares regression method, yielding promising statistical results for the training set (R2 =0.71, Q2LOO=0.68, mean absolute error [MAE]training=0.54). The model was further validated using the test set (Q2F1=0.77, Q2F2=0.75, MAEtest=0.51). Subsequently, we explored the q-RASAR method using other regression-based supervised machine-learning algorithms, demonstrating favourable results for the training and test sets. All models exhibited R2 and Q2F1 values exceeding 0.7, Q2LOO values greater than 0.6, and low MAE values, indicating high model quality and predictive capability for new, unidentified chemical substances. These findings represent the significance of the RASAR method in enhancing predictivity for new unknown chemicals due to the incorporation of similarity functions in the RASAR descriptors, independent of a specific algorithm.

Insights into predicting small molecule retention times in liquid chromatography using deep learning

In untargeted metabolomics, structures of small molecules are annotated using liquid chromatography-mass spectrometry by leveraging information from the molecular retention time (RT) in the chromatogram and m/z (formerly called ''mass-to-charge ratio'') in the mass spectrum. However, correct identification of metabolites is challenging due to the vast array of small molecules. Therefore, various in silico tools for mass spectrometry peak alignment and compound prediction have been developed; however, the list of candidate compounds remains extensive. Accurate RT prediction is important to exclude false candidates and facilitate metabolite annotation. Recent advancements in artificial intelligence (AI) have led to significant breakthroughs in the use of deep learning models in various fields. Release of a large RT dataset has mitigated the bottlenecks limiting the application of deep learning models, thereby improving their application in RT prediction tasks. This review lists the databases that can be used to expand training datasets and concerns the issue about molecular representation inconsistencies in datasets. It also discusses the application of AI technology for RT prediction, particularly in the 5 years following the release of the METLIN small molecule RT dataset. This review provides a comprehensive overview of the AI applications used for RT prediction, highlighting the progress and remaining challenges. SCIENTIFIC CONTRIBUTION: This article focuses on the advancements in small molecule retention time prediction in computational metabolomics over the past five years, with a particular emphasis on the application of AI technologies in this field. It reviews the publicly available datasets for small molecule retention time, the molecular representation methods, the AI algorithms applied in recent studies. Furthermore, it discusses the effectiveness of these models in assisting with the annotation of small molecule structures and the challenges that must be addressed to achieve practical applications.

Computer-aided nanodrug discovery: recent progress and future prospects

Nanodrugs, which utilise nanomaterials in disease prevention and therapy, have attracted considerable interest since their initial conceptualisation in the 1990s. Substantial efforts have been made to develop nanodrugs for overcoming the limitations of conventional drugs, such as low targeting efficacy, high dosage and toxicity, and potential drug resistance. Despite the significant progress that has been made in nanodrug discovery, the precise design or screening of nanomaterials with desired biomedical functions prior to experimentation remains a significant challenge. This is particularly the case with regard to personalised precision nanodrugs, which require the simultaneous optimisation of the structures, compositions, and surface functionalities of nanodrugs. The development of powerful computer clusters and algorithms has made it possible to overcome this challenge through in silico methods, which provide a comprehensive understanding of the medical functions of nanodrugs in relation to their physicochemical properties. In addition, machine learning techniques have been widely employed in nanodrug research, significantly accelerating the understanding of bio-nano interactions and the development of nanodrugs. This review will present a summary of the computational advances in nanodrug discovery, focusing on the understanding of how the key interfacial interactions, namely, surface adsorption, supramolecular recognition, surface catalysis, and chemical conversion, affect the therapeutic efficacy of nanodrugs. Furthermore, this review will discuss the challenges and opportunities in computer-aided nanodrug discovery, with particular emphasis on the integrated "computation + machine learning + experimentation" strategy that can potentially accelerate the discovery of precision nanodrugs.

First report on regression-based QSAR addressing pesticide dissipation half-life in plants: A step towards sustainable public health

The excessive use of pesticides (an important group of chemicals) in the agricultural as well as public sectors raises a health concern. Pesticides affect humans and other living organisms via the food chain. Therefore, it is very necessary to calculate the dissipation half-life of pesticides in plants. Experimental prediction of pesticide dissipation half-lives requires complex environmental conditions, high cost, and a long time. Thus, in-silico half-life predictions are suitable and the best alternative. Herein, a total of six PLS (partial least squares) models namely, M1 (overall), M2 (fruit), M3 (plant interior), M4 (leaf), M5 (plant surface), and M6 (whole plant) alongside two MLR (multiple linear regression) models i.e. M7 (fruit surface) and model M8 (straw) were generated using dissipation half-lives (log10(T1/2)) of pesticides in plants and their different parts. Models were constructed in strict accordance with the guidelines outlined by the Organization for Economic Co-operation and Development (OECD) and extensively validated using globally accepted validation metrics (determination coefficient (R2) = 0.610-0.795, leave-one-out (LOO) cross-validated correlation coefficient (Q2LOO) = 0.520-0.660, MAE-FITTED TRAIN (mean absolute error fitted train) = 0.119-0.148, MAE-LOOTRAIN = 0.132-0.177, predictive R2 or Q2F1 = 0.538-0.567, Q2F2 = 0.500-0.565, MAETEST = 0.122-0.232), confirming their accuracy, reliability, predictivity, and robustness. Lipophilicity, the presence of a cyclomatic ring, suphur, aromatic amine fragments, and chlorine atom fragments are responsible (+ve contribution) for high dissipation half-lives of pesticides in plants. In contrast, hydrophilicity, pyrazine fragments, and rotatable bonds reduce (-ve negative contribution) the dissipation half-lives of pesticides in plants. To address the real-world applicability, the models were employed to screen the PPDB (Pesticide Properties Database) database, which revealed the top 10 pesticides with the highest log(T1/2) in the whole plant and respective parts of the plant body. The present work will aid in developing safer and novel pesticides, regulatory risk assessment, various risk assessments for the sustenance of public health, screening of databases, and data-gap filling.

Predicting and screening high-performance polyimide membranes using negative correlation based deep ensemble methods

Polyimide polymer membranes have become critical materials in gas separation and storage applications due to their high selectivity and excellent permeability. However, with over 107 known types of polyimides, relying solely on experimental research means potential high-performance candidates are likely to be overlooked. This study employs a deep learning method optimized by negative correlation ensemble techniques to predict the gas permeability and selectivity of polyimide structures, enabling rapid and efficient material screening. We propose a deep neural network model based on negative correlation deep ensemble methods (DNN-NCL), using Morgan molecular fingerprints as input. The DNN-NCL model achieves an R2 value of approximately 0.95 on the test set, which is a 4% improvement over recent model performance, and effectively mitigates overfitting with a maximum discrepancy of less than 0.03 between the training and test sets. High-throughput screening of over 8 million hypothetical polymers identified hundreds of promising candidates for gas separation membranes, with 14 structures exceeding the Robeson upper bound for CO2/N2 separation. Visualization of high-throughput predictions shows that although the Robeson upper bound was never explicitly used as a model constraint, the majority of predictions are compressed below this limit, demonstrating the deep learning model's ability to reflect real-world physical conditions. Reverse analysis of model predictions using SHAP analysis achieved interpretability of the deep learning model's predictions and identified three key functional groups deemed important by the deep neural network for gas permeability: carbonyl, thiophene, and ester groups. This established a bridge between the structure and properties of polyimide materials. Additionally, we confirmed that two polyimide structures predicted by the model to have excellent CO2/N2 selectivity, namely 6-methylpyrimidin-5-amine and 1,4,5,6-tetrahydropyrimidin-2-amine, have been experimentally validated in previous studies. This research demonstrates the feasibility of using deep learning methods to explore the vast chemical space of polyimides, providing a powerful tool for discovering high-performance gas separation membranes.

Machine learning models and performance dependency on 2D chemical descriptor space for retention time prediction of pharmaceuticals

The predictive modeling of liquid chromatography methods can be an invaluable asset, potentially saving countless hours of labor while also reducing solvent consumption and waste. Tasks such as physicochemical screening and preliminary method screening systems where large amounts of chromatography data are collected from fast and routine operations are particularly well suited for both leveraging large datasets and benefiting from predictive models. Therefore, the generation of predictive models for retention time is an active area of development. However, for these predictive models to gain acceptance, researchers first must have confidence in model performance and the computational cost of building them should be minimal. In this study, a simple and cost-effective workflow for the development of machine learning models to predict retention time using only Molecular Operating Environment 2D descriptors as input for support vector regression is developed. Furthermore, we investigated the relative performance of models based on molecular descriptor space by utilizing uniform manifold approximation and projection and clustering with Gaussian mixture models to identify chemically distinct clusters. Results outlined herein demonstrate that local models trained on clusters in chemical space perform equivalently when compared to models trained on all data. Through 10-fold cross-validation on a comprehensive set containing 67,950 of our company's proprietary analytes, these models achieved coefficients of determination of 0.84 and 3 % error in terms of retention time. This promising statistical significance is found to translate from cross-validation to prospective prediction on an external test set of pharmaceutically relevant analytes. The observed equivalency of global and local modeling of large datasets is retained with METLIN's SMRT dataset, thereby confirming the wider applicability of the developed machine learning workflows for global models.

In-silico mechanistic analysis of adsorption of Iodinated Contrast Media agents on graphene surface

The study aims at assessing the potential of graphene-based adsorbents to reduce environmental impacts of Iodinated Contrast Media Agents (ICMs). We analyze an extensive collection of ICMs. A modeling approach resting on molecular docking and Density Functional Theory simulations is employed to examine the adsorption process at the molecular level. The study also relies on a Quantitative Structure-Activity Relationship (QSAR) modeling framework to correlate molecular properties with the adsorption energy (Ead) of ICMs, thus enabling identification of the key mechanisms underpinning adsorption and of the key factors contributing to it. A collection of distinct QSAR-based models is developed upon relying on Multiple Linear Regression and a standard genetic algorithm method. Having at our disposal multiple models enables us to take into account the uncertainty associated with model formulation. Maximum Likelihood and formal model identification/discrimination criteria (such as Bayesian and/or information theoretic criteria) are then employed to complement the traditional QSAR modeling phase. This has the advantage of (a) providing a rigorous ranking of the alternative models included in the selected set and (b) quantifying the relative degree of likelihood of each of these models through a weight or posterior probability. The resulting workflow of analysis enables one to seamlessly embed DFT and QSAR studies within a theoretical framework of analysis that explicitly takes into account model and parameter uncertainty. Our results suggest that graphene-based surfaces constitute a promising adsorbent for ICMs removal, π-π stacking being the primary mechanism behind ICM adsorption. Furthermore, our findings offer valuable insights into the potential of graphene-based adsorbent materials for effectively removing ICMs from water systems. They contribute to ascertain the significance of various factors (such as, e.g., the distribution of atomic van der Waals volumes, overall molecular complexity, the presence and arrangement of Iodine atoms, and the presence of polar functional groups) on the adsorption process.

In Silico and In Vitro Studies of Terpenes from the Fabaceae Family Using the Phenotypic Screening Model against the SARS-CoV-2 Virus

In 2019, the emergence of the seventh known coronavirus to cause severe illness in humans triggered a global effort towards the development of new drugs and vaccines for the SARS-CoV-2 virus. These efforts are still ongoing in 2024, including the present work where we conducted a ligand-based virtual screening of terpenes with potential anti-SARS-CoV-2 activity. We constructed a Quantitative Structure-Activity Relationship (QSAR) model from compounds with known activity against SARS-CoV-2 with a model accuracy of 0.71. We utilized this model to predict the activity of a series of 217 terpenes isolated from the Fabaceae family. Four compounds, predominantly triterpenoids from the lupane series, were subjected to an in vitro phenotypic screening in Vero CCL-81 cells to assess their inhibitory activity against SARS-CoV-2. The compounds which showed high rates of SARS-CoV-2 inhibition along with substantial cell viability underwent molecular docking at the SARS-CoV-2 main protease, papain-like protease, spike protein and RNA-dependent RNA polymerase. Overall, virtual screening through our QSAR model successfully identified compounds with the highest probability of activity, as validated using the in vitro study. This confirms the potential of the identified triterpenoids as promising candidates for anti-SARS-CoV-2 therapeutics.

Modelling lethality and teratogenicity of zebrafish (Danio rerio) due to β-lactam antibiotics employing the QSTR approach

Nowadays, β-lactam antibiotics are one of the most consumed OTC (over-the-counter) medicines in the world. Its frequent use against several infectious diseases leads to the development of antibiotic resistance. Another unavoidable risk factor of β-lactam antibiotics is environmental toxicity. Numerous terrestrial as well as aquatic species have suffered due to the excessive use of these pharmaceuticals. In this present study, we have performed a toxicity assessment employing a novel in silico technique like quantitative structure-toxicity relationships (QSTRs) to explore toxicity against zebrafish (Danio rerio). We have developed single as well as inter-endpoint QSTR models for the β-lactam compounds to explore important structural attributes responsible for their toxicity, employing median lethal (LC50) and median teratogenic concentration (TC50) as the endpoints. We have shown how an inter-endpoint model can extrapolate unavailable endpoint values with the help of other available endpoint values. To verify the models' robustness, predictivity, and goodness-of-fit, several universally popular metrics for both internal and external validation were extensively employed in model validation (single endpoint models: r2 = 0.631 - 0.75, Q2F1 = 0.607 - 0.684; inter-endpoint models: r2 = 0.768 - 0.84, Q2F1 = 0.678 - 0.76). Again, these models were engaged in the prediction of these two responses for a true external set of β-lactam molecules without response values to prove the reproducibility of these models.

Comparative optimization of polysaccharide-based nanoformulations for cardiac RNAi therapy

Ionotropic gelation is widely used to fabricate targeting nanoparticles (NPs) with polysaccharides, leveraging their recognition by specific lectins. Despite the fabrication scheme simply involves self-assembly of differently charged components in a straightforward manner, the identification of a potent combinatory formulation is usually limited by structural diversity in compound collections and trivial screen process, imposing crucial challenges for efficient formulation design and optimization. Herein, we report a diversity-oriented combinatory formulation screen scheme to identify potent gene delivery cargo in the context of precision cardiac therapy. Distinct categories of cationic compounds are tested to construct RNA delivery system with an ionic polysaccharide framework, utilizing a high-throughput microfluidics workstation coupled with streamlined NPs characterization system in an automatic, step-wise manner. Sequential computational aided interpretation provides insights in formulation optimization in a broader scenario, highlighting the usefulness of compound library diversity. As a result, the out-of-bag NPs, termed as GluCARDIA NPs, are utilized for loading therapeutic RNA to ameliorate cardiac reperfusion damages and promote the long-term prognosis. Overall, this work presents a generalizable formulation design strategy for polysaccharides, offering design principles for combinatory formulation screen and insights for efficient formulation identification and optimization.

In silico screening of LRRK2 WDR domain inhibitors using deep docking and free energy simulations

The Critical Assessment of Computational Hit-Finding Experiments (CACHE) Challenge series is focused on identifying small molecule inhibitors of protein targets using computational methods. Each challenge contains two phases, hit-finding and follow-up optimization, each of which is followed by experimental validation of the computational predictions. For the CACHE Challenge #1, the Leucine-Rich Repeat Kinase 2 (LRRK2) WD40 Repeat (WDR) domain was selected as the target for in silico hit-finding and optimization. Mutations in LRRK2 are the most common genetic cause of the familial form of Parkinson's disease. The LRRK2 WDR domain is an understudied drug target with no known molecular inhibitors. Herein we detail the first phase of our winning submission to the CACHE Challenge #1. We developed a framework for the high-throughput structure-based virtual screening of a chemically diverse small molecule space. Hit identification was performed using the large-scale Deep Docking (DD) protocol followed by absolute binding free energy (ABFE) simulations. ABFEs were computed using an automated molecular dynamics (MD)-based thermodynamic integration (TI) approach. 4.1 billion ligands from Enamine REAL were screened with DD followed by ABFEs computed by MD TI for 793 ligands. 76 ligands were prioritized for experimental validation, with 59 compounds successfully synthesized and 5 compounds identified as hits, yielding a 8.5% hit rate. Our results demonstrate the efficacy of the combined DD and ABFE approaches for hit identification for a target with no previously known hits. This approach is widely applicable for the efficient screening of ultra-large chemical libraries as well as rigorous protein-ligand binding affinity estimation leveraging modern computational resources.

Chemometrics-driven prediction and prioritization of diverse pesticides on chickens for addressing hazardous effects on public health

The extensive use of various pesticides in the agriculture field badly affects both chickens and humans, primarily through residues in food products and environmental exposure. This study offers the first quantitative structure-toxicity relationship (QSTR) and quantitative read-across-structure toxicity relationship (q-RASTR) models encompassing the LOEL and NOEL endpoints for acute toxicity in chicken, a widely consumed protein. The study's significance lies in the direct link between chemical toxicity in chicken, human intake, and environmental damage. Both the QSTR and the similarity-based read-across algorithms are applied concurrently to improve the predictability of the models. The q-RASTR models were generated by combining read-across derived similarity and error-based parameters, alongside structural and physicochemical descriptors. Machine Learning approaches (SVM and RR) were also employed with the optimization of relevant hyperparameters based on the cross-validation approach, and the final test set prediction results were compared. The PLS-based q-RASTR models for NOEL and LOEL endpoints showed good statistical performance, as traced from the external validation metrics Q2F1: 0.762-0.844; Q2F2: 0.759-0.831 and MAEtest: 0.195-0.214. The developed models were further used to screen the Pesticide Properties DataBase (PPDB) for potential toxicants in chickens. Thus, established models can address eco-toxicological data gaps and development of novel and safe eco-friendly pesticides.

Predicting the Predicted: A Comparison of Machine Learning-Based Collision Cross-Section Prediction Models for Small Molecules

The application of machine learning (ML) to -omics research is growing at an exponential rate owing to the increasing availability of large amounts of data for model training. Specifically, in metabolomics, ML has enabled the prediction of tandem mass spectrometry and retention time data. More recently, due to the advent of ion mobility, new ML models have been introduced for collision cross-section (CCS) prediction, but those have been trained with different and relatively small data sets covering a few thousands of small molecules, which hampers their systematic comparison. Here, we compared four existing ML-based CCS prediction models and their capacity to predict CCS values using the recently introduced METLIN-CCS data set. We also compared them with simple linear models and with ML models that used fingerprints as regressors. We analyzed the role of structural diversity of the data on which the ML models are trained with and explored the practical application of these models for metabolite annotation using CCS values. Results showed a limited capability of the existing models to achieve the necessary accuracy to be adopted for routine metabolomics analysis. We showed that for a particular molecule, this accuracy could only be improved when models were trained with a large number of structurally similar counterparts. Therefore, we suggest that current annotation capabilities will only be significantly altered with models trained with heterogeneous data sets composed of large homogeneous hubs of structurally similar molecules to those being predicted.

Quantitative read-across structure-activity relationship (q-RASAR): A novel approach to estimate the subchronic oral safety (NOAEL) of diverse organic chemicals in rats

We have developed a quantitative safety prediction model for subchronic repeated doses of diverse organic chemicals on rats using the novel quantitative read-across structure-activity relationship (q-RASAR) approach, which uses similarity-based descriptors for predictive model generation. The experimental -Log (NOAEL) values have been used here as a potential indicator of oral subchronic safety on rats as it determines the maximum dose level for which no observed adverse effects of chemicals are found. A total of 186 data points of diverse organic chemicals have been used for the model generation using structural and physicochemical (0D-2D) descriptors. The read-across-derived similarity, error, and concordance measures (RASAR descriptors) have been extracted from the preliminary 0D-2D descriptors. Then, the combined pool of RASAR and the identified 0D-2D descriptors of the training set were employed to develop the final models by using the partial least squares (PLS) algorithm. The developed PLS model was rigorously validated by various internal and external validation metrics as suggested by the Organization for Economic Co-operation and Development (OECD). The final q-RASAR model is proven to be statistically sound, robust and externally predictive (R2 = 0.85, Q2LOO = 0.82 and Q2F1 = 0.94), superseding the internal as well as external predictivity of the corresponding quantitative structure-activity relationship (QSAR) model as well as previously reported subchronic repeated dose toxicity model found in the literature. In a nutshell, the q-RASAR is an effective approach that has the potential to be used as a good alternative way to improve external predictivity, interpretability, and transferability for subchronic oral safety prediction as well as ecotoxicity risk identification.

Unveiling G-protein coupled receptor kinase-5 inhibitors for chronic degenerative diseases: Multilayered prioritization employing explainable machine learning-driven multi-class QSAR, ligand-based pharmacophore and free energy-inspired molecular simulation

GRK5 holds a pivotal role in cellular signaling pathways, with its overexpression in cardiomyocytes, neuronal cells, and tumor cells strongly associated with various chronic degenerative diseases, which highlights the urgent need for potential inhibitors. In this study, multiclass classification-based QSAR models were developed using diverse machine learning algorithms. These models were built from curated compounds with experimentally derived GRK5 inhibitory activity. Additionally, a pharmacophore model was constructed using active compounds from the dataset. Among the models, the SVM-based approach proved most effective and was initially used to screen DrugBank compounds within the applicability domain. Compounds showing significant GRK5 inhibitory potential underwent evaluation for key pharmacophoric features. Prospective compounds were subjected to molecular docking to assess binding affinity towards GRK5's key active site amino acid residues. Stability at the binding site was analyzed through 200 ns molecular dynamics simulations. MM-GBSA analysis quantified individual free energy components contributing to the total binding energy with respect to binding site residues. Metadynamics analysis, including PCA, FEL, and PDF, provided crucial insights into conformational changes of both apo and holo forms of GRK5 at defined energy states. The study identifies DB02844 (S-Adenosyl-1,8-Diamino-3-Thiooctane) and DB13155 (Esculin) as promising GRK5 inhibitors, warranting further in vitro and in vivo validation studies.

Machine Learning Models Identify Inhibitors of New Delhi Metallo-β-lactamase

The worldwide spread of the metallo-β-lactamases (MBL), especially New Delhi metallo-β-lactamase-1 (NDM-1), is threatening the efficacy of β-lactams, which are the most potent and prescribed class of antibiotics in the clinic. Currently, FDA-approved MBL inhibitors are lacking in the clinic even though many strategies have been used in inhibitor development, including quantitative high-throughput screening (qHTS), fragment-based drug discovery (FBDD), and molecular docking. Herein, a machine learning-based prediction tool is described, which was generated using results from HTS of a large chemical library and previously published inhibition data. The prediction tool was then used for virtual screening of the NIH Genesis library, which was subsequently screened using qHTS. A novel MBL inhibitor was identified and shown to lower minimum inhibitory concentrations (MICs) of Meropenem for a panel of E. coli and K. pneumoniae clinical isolates expressing NDM-1. The mechanism of inhibition of this novel scaffold was probed utilizing equilibrium dialyses with metal analyses, native state electrospray ionization mass spectrometry, UV-vis spectrophotometry, and molecular docking. The uncovered inhibitor, compound 72922413, was shown to be 9-hydroxy-3-[(5-hydroxy-1-oxa-9-azaspiro[5.5]undec-9-yl)carbonyl]-4H-pyrido[1,2-a]pyrimidin-4-one.

The first report on the assessment of maximum acceptable daily intake (MADI) of pesticides for humans using intelligent consensus predictions

Direct or indirect consumption of pesticides and their related products by humans and other living organisms without safe dosing may pose a health risk. The risk may arise after a short/long time which depends on the nature and amount of chemicals consumed. Therefore, the maximum acceptable daily intake of chemicals must be calculated to prevent these risks. In the present work, regression-based quantitative structure-activity relationship (QSAR) models were developed using 39 pesticides with maximum acceptable daily intake (MADI) for humans as the endpoint. From the statistical results (R2 = 0.674-0.712, QLOO2 = 0.553-0.580, Q(F1)2 = 0.544-0.611, and Q(F2)2 = 0.531-0.599), it can be inferred that the developed models were robust, reliable, reproducible, accurate, and predictive. Intelligent Consensus Prediction (ICP) was employed to improve the external predictivity (Q(F1)2 =0.579-0.657 and Q(F2)2 = 0.563-0.647) of the models. Some of the chemical markers responsible for toxicity enhancement are the presence of unsaturated bonds, lipophilicity, presence of C< (double bond-single bond-single bonded carbon), and the presence of sulphur and phosphate bonds at the topological distances 1 and 6, while the presence of hydrophilic groups and short chain fragments reduces the toxicity. The Pesticide Properties Database (PPDB) (1694 pesticides) was also screened with the developed models. Hence, this research work will be helpful for the toxicity assessment of pesticides before their synthesis, the development of eco-friendly and safer pesticides, and data-gap filling reducing the time, cost, and animal experimentation. Thus, this study might hold promise for future potential MADI assessment of pesticides and provide a meaningful contribution to the field of risk assessment.

Machine Learning-Based Prediction of Reduction Potentials for PtIV Complexes

Some of the well-known drawbacks of clinically approved PtII complexes can be overcome using six-coordinate PtIV complexes as inert prodrugs, which release the corresponding four-coordinate active PtII species upon reduction by cellular reducing agents. Therefore, the key factor of PtIV prodrug mechanism of action is their tendency to be reduced which, when the involved mechanism is of outer-sphere type, is measured by the value of the reduction potential. Machine learning (ML) models can be used to effectively capture intricate relationships within PtIV complex data, leading to highly accurate predictions of reduction potentials and other properties, and offering significant insights into their electrochemical behavior and potential applications. In this study, a machine learning-based approach for predicting the reduction potentials of PtIV complexes based on relevant molecular descriptors is presented. Leveraging a data set of experimentally determined reduction potentials and a diverse range of molecular descriptors, the proposed model demonstrates remarkable predictive accuracy (MSE = 0.016 V2, RMSE = 0.13 V, R2 = 0.92). Ab initio calculations and a set of different machine learning algorithms and feature engineering techniques have been employed to systematically explore the relationship between molecular structure and similarity and reduction potential. Specifically, it has been investigated whether the reduction potential of these compounds can be described by combining ML models across different combinations of constitutional, topological, and electronic molecular descriptors. Our results not only provide insights into the crucial factors influencing reduction potentials but also offer a rapid and effective tool for the rational design of PtIV complexes with tailored electrochemical properties for pharmaceutical applications. This approach has the potential to significantly expedite the development and screening of novel PtIV prodrug candidates. The analysis of principal components and key features extracted from the model highlights the significance of structural descriptors of the 2D Atom Pairs type and the lowest unoccupied molecular orbital energy. Specifically, with just 20 appropriately selected descriptors, a notable separation of complexes based on their reduction potential value is achieved.

Chemometric modeling of pharmaceuticals for partitioning between sludge and aqueous phase during the wastewater treatment process

Computational techniques, such as quantitative structure-property relationships (QSPRs), can play a significant role in exploring the important chemical features essential for the degree of sorption or sludge/water partition coefficient (Kd) towards sewage sludge of wastewater treatment process to evaluate the environmental consequence and risk of pharmaceuticals. The current research work aims to construct a predictive QSPR model for the sorption of 148 diverse active pharmaceutical ingredients (APIs) in sewage sludge during wastewater treatment. For the development of the model, we employed easily computable 2D descriptors as independent variables. The model has been developed following the Organization for Economic Cooperation and Development's (OECD) guidelines. It has undergone internal and external validation using a variety of methodologies, as well as been tested for its applicability domain. A measure of hydrophobicity, i.e., MLOGP2, showed the most promising contribution in modeling the sorption coefficient of APIs. Among other parameters, the number of tertiary aromatic amines, the presence of electronegative atoms like N, O, and Cl, the size of a molecule, the number of aromatic hydroxyl groups, the presence of substituted aromatic nitrogen atoms and alkyl-substituted tertiary carbon atoms were also found to be influential for the regulation of solid water partition coefficient of APIs during the wastewater treatment process. The statistical validity tests performed on the developed partial least squares (PLS) model showed that it is statistically evident, robust, and predictive (R2Train = 0.750, Q2LOO = 0.683, Q2F1 = 0.655, Q2F2 (or R2Test) = 0.651). In addition, the predictivity of the constructed model was further inspected by using the "prediction reliability indicator" tool for 14 external APIs.

AlvaBuilder: A Software for De Novo Molecular Design

AlvaBuilder is a software tool for de novo molecular design and can be used to generate novel molecules having desirable characteristics. Such characteristics can be defined using a simple step by step graphical interface, and they can be based on molecular descriptors, on predictions of QSAR/QSPR models, and on matching molecular fragments or used to design compounds similar to a given one. The molecules generated are always syntactically valid since they are composed by combining fragments of molecules taken from a training data set chosen by the user. In this paper, we demonstrate how the software can be used to design new compounds for a defined case study. AlvaBuilder is available at https://www.alvascience.com/alvabuilder/.

A comparative study of the predictive performance of different descriptor calculation tools: Molecular-based elution order modeling and interpretation of retention mechanism for isomeric compounds from METLIN database

In the pharmaceutical industry, the need for analytical standards is a bottleneck for comprehensive evaluation and quality control of intermediate and end products. These are complex mixtures containing structurally related molecules. In this regard, chromatographic peak annotation, especially for critical pairs of isomers and closest structural analogs, can be supported by using a Quantitative Structure Retention Relationship (QSRR) approach. In our study, we investigated the fundamental basis of the reversed-phase (RP) retention mechanism for 1141 isomeric compounds from the METLIN SMRT dataset. Nine different descriptor calculation tools combined with different feature selection methods (genetic algorithm (GA), stepwise, Boruta) and machine learning (ML) approaches (support vector machine (SVM), multiple linear regression (MLR), random forest (RF), XGBoost) were applied to provide a reliable molecular structure-based interpretation of RP retention behaviour of the isomeric compounds. Strict internal and external validation metrics were used to select models with the best predictive capabilities (rtest > 0.73, order of elution > 60 %). For the developed models, mean absolute errors were in the range of 60 to 110 s. Stepwise and GA showed the most suitable performance as descriptor selection methods, while SVM and XGBoost modeling gave satisfactory predictive characteristics in most cases. Validation performed on the published experimental data for structurally related pharmaceutical compounds confirmed the best accuracy of MLR modeling in combination with GA feature selection of general physico-chemical properties. The resulting models will be useful for the prediction of separation and identification of structurally related compounds in pharmaceutical analysis, providing a simultaneous understanding of the interaction mechanisms leading to their retention under RP conditions.

Hybrid Machine Learning and Experimental Studies of Antiviral Potential of Ionic Liquids against P100, MS2, and Phi6

Viruses are a group of widespread organisms that are often responsible for very dangerous diseases, as most of them follow a mechanism to multiply and infect their hosts as quickly as possible. Pathogen viruses also mutate regularly, with the result that measures to prevent virus transmission and recover from the disease caused are often limited. The development of new substances is very time-consuming and highly budgeted and requires the sacrifice of many living organisms. Computational chemistry methods allow faster analysis at a much lower cost and, most importantly, reduce the number of living organisms sacrificed experimentally to a minimum. Ionic liquids (ILs) are a group of chemical compounds that could potentially find a wide range of applications due to their potential virucidal activity. In our study, we conducted a complex computational analysis to predict the antiviral activity of ionic liquids against three surrogate viruses: two nonenveloped viruses, Listeria monocytogenes phage P100 and Escherichia coli phage MS2, and one enveloped virus, Pseudomonas syringae phage Phi6. Based on experimental data of toxic activity (logEC90), we assigned activity classes to 154 ILs. Prediction models were created and validated according to the Organization for Economic Co-operation and Development (OECD) recommendations using the Classification Tree method. Further, we performed an external validation of our models through virtual screening on a set of 1277 theoretically generated ionic liquids and then selected 10 active ionic liquids, which were synthesized to verify their activity against the analyzed viruses. Our study proved the effectiveness and efficiency of computational methods to predict the antiviral activity of ionic liquids. Thus, computational models are a cost-effective alternative approach compared with time-consuming experimental studies where live animals are involved.

Developing a machine learning model for accurate nucleoside hydrogels prediction based on descriptors

Supramolecular hydrogels derived from nucleosides have been gaining significant attention in the biomedical field due to their unique properties and excellent biocompatibility. However, a major challenge in this field is that there is no model for predicting whether nucleoside derivative will form a hydrogel. Here, we successfully develop a machine learning model to predict the hydrogel-forming ability of nucleoside derivatives. The optimal model with a 71% (95% Confidence Interval, 0.69-0.73) accuracy is established based on a dataset of 71 reported nucleoside derivatives. 24 molecules are selected via the optimal model external application and the hydrogel-forming ability is experimentally verified. Among these, two rarely reported cation-independent nucleoside hydrogels are found. Based on their self-assemble mechanisms, the cation-independent hydrogel is found to have potential applications in rapid visual detection of Ag+ and cysteine. Here, we show the machine learning model may provide a tool to predict nucleoside derivatives with hydrogel-forming ability.

Relationships between the Photodegradation Reaction Rate and Structural Properties of Polymer Systems

The development of reusable polymeric materials inspires an attempt to combine renewable biomass with upcycling to form a biorenewable closed system. It has been reported that 2,5-furandicarboxylic acid (FDCA) can be recovered for recycling when incorporated as monomers into photodegradable polymeric systems. Here, we develop a procedure to better understand the photodegradation reactions combining density functional theory (DFT) based time-dependent excited-state molecular dynamics (TDESMD) studies with machine learning-based quantitative structure-activity relationships (QSAR) methodology. This procedure allows for the unveiling of hidden structural features between active orbitals that affect the rate of photodegradation and is coined InfoTDESMD. Findings show that electrotopological features are influential factors affecting the rate of photodegradation in differing environments. Additionally, statistical validations and knowledge-based analysis of descriptors are conducted to further understand the structural features' influence on the rate of photodegradation of polymeric materials.

First report on pesticide sub-chronic and chronic toxicities against dogs using QSAR and chemical read-across

Excessive use of chemicals is the outcome of the industrialization of agricultural sectors which leads to disturbance of ecological balance. Various agrochemicals are widely used in agricultural fields, urban green areas, and to protect from various pest-associated diseases. Due to their long-term health and environmental hazards, chronic toxicity assessment is crucial. Since in vivo and in vitro toxicity assessments are costly, lengthy, and require a large number of animal experiments, in silico toxicity approaches are better alternatives to save time, cost, and animal experimentation. We have developed the first regression-based 2D-QSAR models using different sub-chronic and chronic toxicity data of pesticides against dogs employing 2D descriptors. From the statistical results (n train = 53 - 62 ,   r 2  = 0.614 to 0.754, Q L O O 2  = 0.501 to 0.703 and   Q F 1 2  = 0.531 to 0.718, Q F 2 2 = 0.523 - 0.713 ), it was concluded that the models are robust, reliable, interpretable, and predictive. Similarity-based read-across algorithm was also used to improve the predictivity (Q F 1 2 = 0.595 - 0.813 , Q F 2 2 = 0.573 - 0.809 ) of the models. 5132 chemicals obtained from the CPDat and 1694 pesticides obtained from the PPDB database were also screened using the developed models, and their predictivity and reliability were checked. Thus, these models will be helpful for eco-toxicological data-gap filling, toxicity prediction of untested pesticides, and development of novel, safer & eco-friendly pesticides.

Predictive binary mixture toxicity modeling of fluoroquinolones (FQs) and the projection of toxicity of hypothetical binary FQ mixtures: a combination of 2D-QSAR and machine-learning approaches

All sorts of chemicals get degraded under various environmental stresses, and the degradates coexist with the parent compounds as mixtures in the environment. Antibiotics emerge as an additional concern due to the bioactive nature of both the parent compound and degradation products and their combined exposure to the environment. Therefore, environmental risk assessment of antibiotics and their degradation products is very much necessary. In this direction, we made use of in silico new approach methodologies (NAMs) and machine-learning algorithms. In this study, we have developed a robust and predictive mixture-quantitative structure-activity relationship (QSAR) model with promising quality and predictability (internal: MAETrain = 0.085, QLOO2 = 0.849, external: MAETest = 0.090, and QF12 = 0.859) for predicting the toxicity of the mixtures of a class of antibiotics and their degradation products. To obtain the predictive model, toxicity data of 78 binary fluoroquinolone mixtures in E. coli (endpoint: log 1/IC50 in molar) have been utilized. We have used only 0D-2D descriptors to efficiently encode the structural features of mixture components without any additional complexities. The optimization of the class of mixture descriptors has been performed in this study by using three different mixing rules (linear combination of molecular contributions, the squared molecular contributions, and the norm of molecular contributions). Different machine-learning approaches namely, random forest (RF), ada boost, gradient boost (GB), extreme gradient boost (XGB), support vector machine (SVM), linear support vector machine (LSVM), and ridge regression (RR) have been employed here apart from the conventional partial least squares (PLS) regression to optimize the modeling approach. A rigorous validation protocol has been used for assessing the goodness-of-fit, robustness, and external predictability of the models. Finally, the toxicity of possible untested mixtures of different photodegradation products of fluoroquinolones has been predicted using the best model reported in this study.

Computer-Aided Molecular Design of Ionic Liquids as Advanced Process Media: A Review from Fundamentals to Applications

The unique physicochemical properties, flexible structural tunability, and giant chemical space of ionic liquids (ILs) provide them a great opportunity to match different target properties to work as advanced process media. The crux of the matter is how to efficiently and reliably tailor suitable ILs toward a specific application. In this regard, the computer-aided molecular design (CAMD) approach has been widely adapted to cover this family of high-profile chemicals, that is, to perform computer-aided IL design (CAILD). This review discusses the past developments that have contributed to the state-of-the-art of CAILD and provides a perspective about how future works could pursue the acceleration of the practical application of ILs. In a broad context of CAILD, key aspects related to the forward structure-property modeling and reverse molecular design of ILs are overviewed. For the former forward task, diverse IL molecular representations, modeling algorithms, as well as representative models on physical properties, thermodynamic properties, among others of ILs are introduced. For the latter reverse task, representative works formulating different molecular design scenarios are summarized. Beyond the substantial progress made, some future perspectives to move CAILD a step forward are finally provided.

q-RASTR modelling for prediction of diverse toxic chemicals towards T. pyriformis

A series of diverse organic compounds impose serious detrimental effects on the health of living organisms and the environment. Determination of the structural aspects of compounds that impart toxicity and evaluation of the same is crucial before public usage. The present study aims to determine the structural characteristics of compounds for Tetrahymena pyriformis toxicity using the q-RASTR (Quantitative Read Across Structure-Toxicity Relationship) model. It was developed using RASTR and 2-D descriptors for a dataset of 1792 compounds with defined endpoint (pIGC50) against a model organism, T. pyriformis. For the current study, the whole dataset was divided based on activity/property into the training and test sets, and the q-RASTR model was developed employing six descriptors (three latent variables) having r2, Q2F1 and Q2 values of 0.739, 0.767, and 0.735, respectively. The generated model was thoroughly validated using internationally recognized internal and external validation criteria to assess the model's dependability and predictability. It was highlighted that high molecular weight, aromatic hydroxyls, nitrogen, double bonds, and hydrophobicity increase the toxicity of organic compounds. The current study demonstrates the applicability of the RASTR algorithm in QSTR model development for the prediction of toxic chemicals (pIGC50) towards T. pyriformis.

Development of a read-across-derived classification model for the predictions of mutagenicity data and its comparison with traditional QSAR models and expert systems

Mutagenicity is considered an important endpoint from the regulatory, environmental and medical points of view. Due to the wide number of compounds that may be of concern and the enormous expenses (in terms of time, money, and animals) associated with rodent mutagenicity bioassays, this endpoint is a major target for the development of alternative approaches for screening and prediction. The majority of old-aged expert systems and quantitative structure-activity relationship (QSAR) models may show reduced performance over time for their application on newer chemical candidates; thus, researchers constantly try to improve the modeling strategies. In our report, we initially performed traditional classification-based linear discriminant analysis (LDA) QSAR modeling using the benchmark Ames dataset of diverse chemicals (6512 compounds) to recognize the relationship between the molecules and their potential mutagenic behavior. The classical LDA QSAR model is developed from a selected set of 2D descriptors. The LDA QSAR model was developed by using a total of 31 descriptors identified from the analysis of the most discriminating features. Additionally, we have used similarity-derived features obtained from the read-across (RA) to develop an RA-based QSAR model. The developed RA-based LDA QSAR model has better predictivity, transferability, and interpretability compared to the LDA QSAR model, and it uses a very small number of descriptors compared to the classical QSAR model. Different machine learning (ML) models were also developed using the descriptors appearing in the read-across-based LDA QSAR model for comparative studies. We have checked the prediction quality of 216 true external set compounds using the novel similarity-derived RA model. The performance of the OECD toolbox is also compared with the RA-derived LDA QSAR model for a true external set. The current study aimed to explore the significance of the read-across-based algorithm and its application to the most current experimental mutagenicity data to complement already available expert systems.

Quantitative Read-across structure-activity relationship (q-RASAR): A new approach methodology to model aquatic toxicity of organic pesticides against different fish species

We have developed quantitative toxicity prediction models for organic pesticides of agricultural importance considering different fish species using a novel quantitative Read-across structure-activity relationship (q-RASAR) approach. The current study uses experimental (Log 1/LC50) data of organic pesticides to various fish species, including Rainbow trout (RT: Oncorhynchus mykiss: 715 data points), Lepomis (LP: Lepomis macrochirus: 136 data points), and Miscellaneous (Pimephales promelas, Brachydanio rerio: 226 data points). This study has also discussed the validation of the developed models and the analysis of structural features that are important for aquatic toxicity towards fishes. The read-across-derived similarity, error, and concordance measures (RASAR descriptors) have been extracted from the preliminary 0D-2D descriptors; the combined pool of RASAR and selected 0D-2D descriptors have been used to develop the final models by employing partial least squares algorithm. All the q-RASAR models are acceptable in terms of goodness of fit, robustness, and external predictivity, superseding the quality of the respective QSAR models, as seen from the computed validation metrics. The q-RASAR is an effective approach that has the potential to be used as a good alternative way to enhance external predictivity, interpretability, and transferability for aquatic toxicity prediction as well as ecotoxicity potential identification.

From intuition to AI: evolution of small molecule representations in drug discovery

Within drug discovery, the goal of AI scientists and cheminformaticians is to help identify molecular starting points that will develop into safe and efficacious drugs while reducing costs, time and failure rates. To achieve this goal, it is crucial to represent molecules in a digital format that makes them machine-readable and facilitates the accurate prediction of properties that drive decision-making. Over the years, molecular representations have evolved from intuitive and human-readable formats to bespoke numerical descriptors and fingerprints, and now to learned representations that capture patterns and salient features across vast chemical spaces. Among these, sequence-based and graph-based representations of small molecules have become highly popular. However, each approach has strengths and weaknesses across dimensions such as generality, computational cost, inversibility for generative applications and interpretability, which can be critical in informing practitioners' decisions. As the drug discovery landscape evolves, opportunities for innovation continue to emerge. These include the creation of molecular representations for high-value, low-data regimes, the distillation of broader biological and chemical knowledge into novel learned representations and the modeling of up-and-coming therapeutic modalities.

QSAR assessment of aquatic toxicity potential of diverse agrochemicals

The fast-increasing number of commercially produced chemicals challenges the experimental ecotoxicity assessment methods, which are costly, time-consuming, and dependent on the sacrifice of animals. In this regard, Quantitative Structure-Property/Activity Relationships (QSPR/QSAR) have led the way in developing ecotoxicity assessment models. In this study, QSAR models have been developed using the pEC50 values of 82 diverse agrochemicals or agro-molecules against a planktonic crustacean Daphnia magna with easily interpretable 2D descriptors. Moreover, a link among octanol-water partition coefficient (KOW), bio-concentration factor (BCF), and critical body residue (CBR) has been addressed, and their imputation for the prediction of the toxicity endpoint (EC50) has been done with an objective of the advanced exploration of several ecotoxicological parameters for toxic chemicals. The developed partial least squares (PLS) models were validated rigorously and proved to be robust, sound, and immensely well-predictive. The final Daphnia toxicity model derived from experimental derived properties along with computed descriptors emerged better in statistical quality and predictivity than those obtained solely from computed descriptors. Additionally, the pEC50 and other important properties (log KOW, log BCF, and log CBR) for a set of external agro-molecules, not employed in model development, were predicted to show the predictive ability of the models.

The Comparison of Machine Learning and Mechanistic In Vitro-In Vivo Extrapolation Models for the Prediction of Human Intrinsic Clearance

Accurate prediction of human pharmacokinetics (PK) remains one of the key objectives of drug metabolism and PK (DMPK) scientists in drug discovery projects. This is typically performed by using in vitro-in vivo extrapolation (IVIVE) based on mechanistic PK models. In recent years, machine learning (ML), with its ability to harness patterns from previous outcomes to predict future events, has gained increased popularity in application to absorption, distribution, metabolism, and excretion (ADME) sciences. This study compares the performance of various ML and mechanistic models for the prediction of human IV clearance for a large (645) set of diverse compounds with literature human IV PK data, as well as measured relevant in vitro end points. ML models were built using multiple approaches for the descriptors: (1) calculated physical properties and structural descriptors based on chemical structure alone (classical QSAR/QSPR); (2) in vitro measured inputs only with no structure-based descriptors (ML IVIVE); and (3) in silico ML IVIVE using in silico model predictions for the in vitro inputs. For the mechanistic models, well-stirred and parallel-tube liver models were considered with and without the use of empirical scaling factors and with and without renal clearance. The best ML model for the prediction of in vivo human intrinsic clearance (CLint) was an in vitro ML IVIVE model using only six in vitro inputs with an average absolute fold error (AAFE) of 2.5. The best mechanistic model used the parallel-tube liver model, with empirical scaling factors resulting in an AAFE of 2.8. The corresponding mechanistic model with full in silico inputs achieved an AAFE of 3.3. These relative performances of the models were confirmed with the prediction of 16 Pfizer drug candidates that were not part of the original data set. Results show that ML IVIVE models are comparable to or superior to their best mechanistic counterparts. We also show that ML IVIVE models can be used to derive insights into factors for the improvement of mechanistic PK prediction.

Expanding the applicability domain of QSPRs for predicting water solubility and vapor pressure of PFAS

This work aimed to verify whether it is possible to extend the applicability domain (AD) of existing QSPR (Quantitative Structure-Property Relationship) models by employing a strategy involving additional quantum-chemical calculations. We selected two published QSPR models: for water solubility, logSW, and vapor pressure, logVP of PFAS as case studies. We aimed to enlarge set of compounds used to build the model by applying factorial planning to plan the augmentation of the set of these compounds based on their structural features (descriptors). Next, we used the COSMO-RS model to calculate the logSW and logVP for selected chemicals. This allowed filling gaps in the experimental data for further training QSPR models. We improved the published models by significantly extending number of compounds for which theoretical predictions are reliable (i.e., extending the AD). Additionally, we performed external validation that had not been carried out in original models. To test effectiveness of the AD extension, we screened 4519 PFAS from NORMAN Database. The number of compounds outside the domain was reduced comparing the original model for both properties. Our work shows that combining physics-based methods with data-driven models can significantly improve the performance of predictions of phys-chem properties relevant for the chemical risk assessment.

Read-across-based intelligent learning: development of a global q-RASAR model for the efficient quantitative predictions of skin sensitization potential of diverse organic chemicals

Environmental chemicals and contaminants cause a wide array of harmful implications to terrestrial and aquatic life which ranges from skin sensitization to acute oral toxicity. The current study aims to assess the quantitative skin sensitization potential of a large set of industrial and environmental chemicals acting through different mechanisms using the novel quantitative Read-Across Structure-Activity Relationship (q-RASAR) approach. Based on the identified important set of structural and physicochemical features, Read-Across-based hyperparameters were optimized using the training set compounds followed by the calculation of similarity and error-based RASAR descriptors. Data fusion, further feature selection, and removal of prediction confidence outliers were performed to generate a partial least squares (PLS) q-RASAR model, followed by the application of various Machine Learning (ML) tools to check the quality of predictions. The PLS model was found to be the best among different models. A simple user-friendly Java-based software tool was developed based on the PLS model, which efficiently predicts the toxicity value(s) of query compound(s) along with their status of Applicability Domain (AD) in terms of leverage values. This model has been developed using structurally diverse compounds and is expected to predict efficiently and quantitatively the skin sensitization potential of environmental chemicals to estimate their occupational and health hazards.

Machine learning - based q-RASAR modeling to predict acute contact toxicity of binary organic pesticide mixtures in honey bees

We have reported here a quantitative read-across structure-activity relationship (q-RASAR) model for the prediction of binary mixture toxicity (acute contact toxicity) in honey bees. Both the quantitative structure-activity relationship (QSAR) and the similarity-based read-across algorithms are used simultaneously for enhancing the predictability of the model. Several similarity and error-based parameters, obtained from the read-across prediction tool, have been put together with the structural and physicochemical descriptors to develop the final q-RASAR model. The calculated statistical and validation metrics indicate the goodness-of-fit, robustness, and good predictability of the partial least squares (PLS) regression model. Machine learning algorithms like ridge regression, linear support vector machine (SVM), and non-linear SVM have been used to further enhance the predictability of the q-RASAR model. The prediction quality of the q-RASAR models outperforms the previously reported quasi-SMILEs-based QSAR model in terms of external correlation coefficient (Q2F1 SVM q-RASAR: 0.935 vs. Q2VLD QSAR: 0.89). In this research, the toxicity values of several new untested binary mixtures have been predicted with the new models, and the reliability of the PLS predictions has been validated by the prediction reliability indicator tool. The q-RASAR approach can be used as reliable, complementary, and integrative to the conventional experimental approaches of pesticide mixture risk assessment.

"Data fusion" quantitative read-across structure-activity-activity relationships (q-RASAARs) for the prediction of toxicities of binary and ternary antibiotic mixtures toward three bacterial species

Antibiotics are often found in the environment as pollutants. They are usually found as mixtures in the environment and may produce toxicity against different ecological species due to joint exposure in the sub-optimal range. Sometimes the degradation products of parent chemicals also interact with it and cause mixture toxicity. In this study, we have developed three different mixture-Quantitative Structure-Activity Relationship (mixture-QSAR) models for three different bacterial species (Vibrio fischeri, Escherichia coli, and Bacillus subtilis). The toxicity data were collected from a previous experimental report in the literature, which comprised binary and ternary mixtures of sulfonamides (SAs), sulfonamide potentiators (SAPs), and tetracyclines (TCs). We have also explored the interspecies modeling to find inter-correlation among the toxicity of these studied organisms and have developed quantitative structure activity-activity relationship (QSAAR) models by employing the "data fusion" quantitative read-across structure-activity-activity relationship (q-RASAAR) and partial least squares (PLS) regression algorithms. All the models are strictly validated using both internal and external validation tests as suggested in the OECD guidelines. Three different mixing rules have been used in this study for descriptor computations to incorporate the additive and interaction effects among the mixture components. To the best of our knowledge, this is the first report of interspecies mixture toxicity models which can predict the cellular toxicity of binary and ternary mixtures against any of the three above-mentioned organisms.

Facilitating structural elucidation of small environmental solutes in RPLC-HRMS by retention index prediction

Implementing effective environmental management strategies requires a comprehensive understanding of the chemical composition of environmental pollutants, particularly in complex mixtures. Utilizing innovative analytical techniques, such as high-resolution mass spectrometry and predictive retention index models, can provide valuable insights into the molecular structures of environmental contaminants. Liquid Chromatography-High-Resolution Mass Spectrometry is a powerful tool for the identification of isomeric structures in complex samples. However, there are some limitations that can prevent accurate isomeric structure identification, particularly in cases where the isomers have similar mass and fragmentation patterns. Liquid chromatographic retention, determined by the size, shape, and polarity of the analyte and its interactions with the stationary phase, contains valuable 3D structural information that is vastly underutilized. Therefore, a predictive retention index model is developed which is transferrable to LC-HRMS systems and can assist in the structural elucidation of unknowns. The approach is currently restricted to carbon, hydrogen, and oxygen-based molecules <500 g mol-1. The methodology facilitates the acceptance of accurate structural formulas and the exclusion of erroneous hypothetical structural representations by leveraging retention time estimations, thereby providing a permissible tolerance range for a given elemental composition and experimental retention time. This approach serves as a proof of concept for the development of a Quantitative Structure-Retention Relationship model using a generic gradient LC approach. The use of a widely used reversed-phase (U)HPLC column and a relatively large set of training (101) and test compounds (14) demonstrates the feasibility and potential applicability of this approach for predicting the retention behaviour of compounds in complex mixtures. By providing a standard operating procedure, this approach can be easily replicated and applied to various analytical challenges, further supporting its potential for broader implementation.

Prediction-Inspired Intelligent Training for the Development of Classification Read-across Structure-Activity Relationship (c-RASAR) Models for Organic Skin Sensitizers: Assessment of Classification Error Rate from Novel Similarity Coefficients

The advancements in the field of cheminformatics have led to a reduction in animal testing to estimate the activity, property, and toxicity of query chemicals. Read-across structure-activity relationship (RASAR) is an emerging concept that utilizes various similarity functions derived from chemical information to develop highly predictive models. Unlike quantitative structure-activity relationship (QSAR) models, RASAR descriptors of a query compound are computed from its close congeners instead of the compound itself, thus targeting predictions in the model training phase. The objective of the present study is not to propose new QSAR models for skin sensitization but to demonstrate the enhancement in the quality of predictions of the skin-sensitizing potential of organic compounds by developing classification-based RASAR (c-RASAR) models. A diverse, previously curated data set was collected from the literature for which 2D descriptors were computed. The extracted essential features were then used to develop a classification-based linear discriminant analysis (LDA) QSAR model. Furthermore, from the read-across-based predictions, RASAR descriptors were calculated using the basic settings of the hyperparameters for the Laplacian Kernel-based optimum similarity measure. After feature selection, an LDA c-RASAR model was developed, which superseded the prediction quality of the LDA-QSAR model. Various other combinations of RASAR descriptors were also taken to develop additional c-RASAR models, all showing better prediction quality than the LDA QSAR model while using a lower number of descriptors. Various other machine learning c-RASAR models were also developed for comparison purposes. In this work, we have proposed and analyzed three new similarity metrics: gm_class, sm1, and sm2. The first one is an indicator variable used to generate a simple univariate c-RASAR model with good prediction ability, while the remaining two are similarity indices used to analyze possible activity cliffs in the training and test sets and are believed to play an important role in the modelability analysis of data sets.

Repurposing the Medicines for Malaria Venture's COVID Box to discover potent inhibitors of Toxoplasma gondii, and in vivo efficacy evaluation of almitrine bismesylate (MMV1804175) in chronically infected mice

Toxoplasmosis, caused by the obligate intracellular parasite Toxoplasma gondii, affects about one-third of the world's population and can cause severe congenital, neurological and ocular issues. Current treatment options are limited, and there are no human vaccines available to prevent transmission. Drug repurposing has been effective in identifying anti-T. gondii drugs. In this study, the screening of the COVID Box, a compilation of 160 compounds provided by the "Medicines for Malaria Venture" organization, was conducted to explore its potential for repurposing drugs to combat toxoplasmosis. The objective of the present work was to evaluate the compounds' ability to inhibit T. gondii tachyzoite growth, assess their cytotoxicity against human cells, examine their absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties, and investigate the potential of one candidate drug through an experimental chronic model of toxoplasmosis. Early screening identified 29 compounds that could inhibit T. gondii survival by over 80% while keeping human cell survival up to 50% at a concentration of 1 μM. The Half Effective Concentrations (EC50) of these compounds ranged from 0.04 to 0.92 μM, while the Half Cytotoxic Concentrations (CC50) ranged from 2.48 to over 50 μM. Almitrine was chosen for further evaluation due to its favorable characteristics, including anti-T. gondii activity at nanomolar concentrations, low cytotoxicity, and ADMET properties. Administering almitrine bismesylate (Vectarion®) orally at dose of 25 mg/kg/day for ten consecutive days resulted in a statistically significant (p < 0.001) reduction in parasite burden in the brains of mice chronically infected with T. gondii (ME49 strain). This was determined by quantifying the RNA of living parasites using real-time PCR. The presented results suggest that almitrine may be a promising drug candidate for additional experimental studies on toxoplasmosis and provide further evidence of the potential of the MMV collections as a valuable source of drugs to be repositioned for infectious diseases.

Deep learning tools to accelerate antibiotic discovery

INTRODUCTION

As machine learning (ML) and artificial intelligence (AI) expand to many segments of our society, they are increasingly being used for drug discovery. Recent deep learning models offer an efficient way to explore high-dimensional data and design compounds with desired properties, including those with antibacterial activity.

AREAS COVERED

This review covers key frameworks in antibiotic discovery, highlighting physicochemical features and addressing dataset limitations. The deep learning approaches here described include discriminative models such as convolutional neural networks, recurrent neural networks, graph neural networks, and generative models like neural language models, variational autoencoders, generative adversarial networks, normalizing flow, and diffusion models. As the integration of these approaches in drug discovery continues to evolve, this review aims to provide insights into promising prospects and challenges that lie ahead in harnessing such technologies for the development of antibiotics.

EXPERT OPINION

Accurate antimicrobial prediction using deep learning faces challenges such as imbalanced data, limited datasets, experimental validation, target strains, and structure. The integration of deep generative models with bioinformatics, molecular dynamics, and data augmentation holds the potential to overcome these challenges, enhance model performance, and utlimately accelerate antimicrobial discovery.

Activity Models of Key GPCR Families in the Central Nervous System: A Tool for Many Purposes

G protein-coupled receptors (GPCRs) are targets of many drugs, of which ∼25% are indicated for central nervous system (CNS) disorders. Drug promiscuity affects their efficacy and safety profiles. Predicting the polypharmacology profile of compounds against GPCRs can thus provide a basis for producing more precise therapeutics by considering the targets and the anti-targets in that family of closely related proteins. We provide a tool for predicting the polypharmacology of compounds within prominent GPCR families in the CNS: serotonin, dopamine, histamine, muscarinic, opioid, and cannabinoid receptors. Our in-house algorithm, "iterative stochastic elimination" (ISE), produces high-quality ligand-based models for agonism and antagonism at 31 GPCRs. The ISE models correctly predict 68% of CNS drug-GPCR interactions, while the "similarity ensemble approach" predicts only 33%. The activity models correctly predict 56% of reported activities of DrugBank molecules for these CNS receptors. We conclude that the combination of interactions and activity profiles generated by screening through our models form the basis for subsequent designing and discovering novel therapeutics, either single, multitargeting, or repurposed.

Modelling the enantiorecognition of structurally diverse pharmaceuticals on O-substituted polysaccharide-based stationary phases

This study aims to develop models to predict the retention, separation and elution sequence of the enantiomers of structurally diverse pharmaceuticals. More specifically, Quantitative Structure Retention Relationships (QSRR) models are built that describe the relationship between molecular descriptors and retention. Eighteen structurally diverse chiral mixtures, each consisting of a pair of enantiomers, were analyzed on two polysaccharide chiral stationary phases, Chiralcel OD-RH (cellulose tris(3,5-dimethylphenylcarbamate)) and Lux amylose-2 (amylose tris(5-chloro-2-methylphenylcarbamate)), applying either a basic or an acidic mobile phase, and their retention factor and elution sequence were determined. Both achiral and, in-house defined, chiral descriptors were used as descriptive variables to build the models. Linear regression techniques, i.e. stepwise multiple linear regression (sMLR) and partial least squares (PLS) regression, were applied to model the retention or separation as a function of the descriptors. In a first step, models were built with only achiral descriptors to model the global retention of both enantiomers of a chiral molecule. Subsequently, models were built with only chiral descriptors to predict the enantioseparation and elution sequence, and finally, models were considered with both descriptor types to predict the retention, the separation and the elution sequence of the enantiomers. The global retention was predicted well by the sMLR models with only achiral descriptors. The models with only chiral descriptors were not found suitable to predict the enantioseparation and elution sequence. Finally, the models containing both chiral and achiral descriptors allowed predicting the retention well, but their ability to predict the elution sequence and separation of the enantiomers differed widely for the chromatographic systems considered.

Exploring quantitative structure-property relationship models for environmental fate assessment of petroleum hydrocarbons

The rate and extent of biodegradation of petroleum hydrocarbons in the different aquatic environments is an important element to address. The major avenue for removing petroleum hydrocarbons from the environment is thought to be biodegradation. The present study involves the development of predictive quantitative structure-property relationship (QSPR) models for the primary biodegradation half-life of petroleum hydrocarbons that may be used to forecast the biodegradation half-life of untested petroleum hydrocarbons within the established models' applicability domain. These models use easily computable two-dimensional (2D) descriptors to investigate important structural characteristics needed for the biodegradation of petroleum hydrocarbons in freshwater (dataset 1), temperate seawater (dataset 2), and arctic seawater (dataset 3). All the developed models follow OECD guidelines. We have used double cross-validation, best subset selection, and partial least squares tools for model development. In addition, the small dataset modeler tool has been successfully used for the dataset with very few compounds (dataset 3 with 17 compounds), where dataset division was not possible. The resultant models are robust, predictive, and mechanistically interpretable based on both internal and external validation metrics (R² range of 0.605-0.959. Q²_(Loo) range of 0.509-0.904, and Q²_F1 range of 0.526-0.959). The intelligent consensus predictor tool has been used for the improvement of the prediction quality for test set compounds which provided superior outcomes to those from individual partial least squares models based on several metrics (Q²_F1 = 0.808 and Q²_F2 = 0.805 for dataset 1 in freshwater). Molecular size and hydrophilic factor for freshwater, frequency of two carbon atoms at topological distance 4 for temperate seawater, and electronegative atom count relative to size for arctic seawater were found to be the most significant descriptors responsible for the regulation of biodegradation half-life of petroleum hydrocarbons.

First report on soil ecotoxicity prediction against Folsomia candida using intelligent consensus predictions and chemical read-across

Soil invertebrates serve as an outstanding biological indicator of the terrestrial ecosystem and overall soil quality, considering their high sensitivity when compared to other indicators of soil quality. In this study, the available soil ecotoxicity data (pEC50) against the soil invertebrate Folsomia candida (C. name: Springtail) (n = 45) were collated from the database of ECOTOX (cfpub.epa.gov/ecotox) and subjected to QSAR analysis using 2D descriptors. Four partial least squares (PLS) models were built based on the features selected through genertic algorithm followed by the best subset selection. These four models were then used as inputs for Intelligent Consensus Predictor version 1.2 (PLS version) to get the final consensus predictions, using the best selection of predictions (compound-wise) from four "qualified" individual models. Both internal and external validations metrics of the consensus predictions are well- balanced and within the acceptable range as per the OECD criteria. The consensus model was found to be better than the previous developed models for this endpoint. Predictions were also made using the Chemical Read-across approach, which showed even better external validation metric values than the consensus predictions. From the selected features in the QSAR models, it has been found out that molecular weight and presence of a di-thiophosphate group, electron donor groups, and polyhalogen substitutions have a significant impact on the soil ecotoxicity. The soil ecotoxicological risk assessment of organic chemicals can therefore be prioritized by these features. The models developed from diverse structural organic compounds can be applied to any new query compound for data gap filling.

Quick and efficient quantitative predictions of androgen receptor binding affinity for screening Endocrine Disruptor Chemicals using 2D-QSAR and Chemical Read-Across

Endocrine Disruptor Chemicals are synthetic or natural molecules in the environment that promote adverse modifications of endogenous hormone regulation in humans and/or in animals. In the present research, we have applied two-dimensional quantitative structure-activity relationship (2D-QSAR) modeling to analyze the structural features of these chemicals responsible for binding to the androgen receptors (logRBA) in rats. We have collected the receptor binding data from the EDKB database (https://www.fda.gov/science-research/endocrine-disruptor-knowledge-base/accessing-edkb-database) and then employed the DTC-QSAR tool, available from https://dtclab.webs.com/software-tools, for dataset division, feature selection, and model development. The final partial least squares model was evaluated using various stringent validation criteria. From the model, we interpreted that hydrophobicity, steroidal nucleus, bulkiness and a hydrogen bond donor at an appropriate position contribute to the receptor binding affinity, while presence of electron rich features like aromaticity and polar groups decrease the receptor binding affinity. Additionally we have also performed chemical Read-Across predictions using Read-Across-v3.1 available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home, and the results for the external validation metrics were found to be better than the QSAR-derived predictions. The best quality of external predictions emerged from the q-RASAR approach which combines both read-across and QSAR. To explore the essential features responsible for the receptor binding, pharmacophore mapping, molecular docking along with molecular dynamics simulation were also performed, and the results are in accordance with the QSAR/q-RASAR findings.

Chemical similarity and machine learning-based approaches for the prediction of aquatic toxicity of binary and multicomponent pharmaceutical and pesticide mixtures against Aliivibrio fischeri

Different classes of chemicals are present in the environment as mixtures. Among them, pharmaceuticals and pesticides are of major concern due to their improper use and disposal, and subsequent additive and non-additive effects. To assess the environmental risk posed by the mixtures of pharmaceuticals and pesticides, a quantitative structure-activity relationship (QSAR) model has been developed in this study using the pEC₅₀ values of 198 binary and multi-component mixtures against the marine bacterium Aliivibrio fischeri. The developed partial least squares (PLS) model has been rigorously validated and proved to be a robust and extremely predictive one. To address the chances of overestimation of validation metrics, three cross-validation tests (mixtures out, compounds out, and everything out) have been applied, and the results were satisfactory. The use of simple 2-dimensional descriptors makes the prediction much quick, and also makes the model easily interpretable. A machine learning-based chemical read-across prediction has also been performed to justify the effectiveness of selected structural features in this study. In a nutshell, this study proves QSAR and chemical read-across as effective alternative approaches for the toxicity prediction of pharmaceutical and pesticide mixtures and also approves the use of mixture descriptors for modelling mixtures successfully.

The use of machine learning modeling, virtual screening, molecular docking, and molecular dynamics simulations to identify potential VEGFR2 kinase inhibitors

Targeting the signaling pathway of the Vascular endothelial growth factor receptor-2 is a promising approach that has drawn attention in the quest to develop novel anti-cancer drugs and cardiovascular disease treatments. We construct a screening pipeline using machine learning classification integrated with similarity checks of approved drugs to find new inhibitors. The statistical metrics reveal that the random forest approach has slightly better performance. By further similarity screening against several approved drugs, two candidates are selected. Analysis of absorption, distribution, metabolism, excretion, and toxicity, along with molecular docking and dynamics are performed for the two candidates with regorafenib as a reference. The binding energies of molecule1, molecule2, and regorafenib are - 89.1, - 95.3, and - 87.4 (kJ/mol), respectively which suggest candidate compounds have strong binding to the target. Meanwhile, the median lethal dose and maximum tolerated dose for regorafenib, molecule1, and molecule2 are predicted to be 800, 1600, and 393 mg/kg, and 0.257, 0.527, and 0.428 log mg/kg/day, respectively. Also, the inhibitory activity of these compounds is predicted to be 7.23 and 7.31, which is comparable with the activity of pazopanib and sorafenib drugs. In light of these findings, the two compounds could be further investigated as potential candidates for anti-angiogenesis therapy.