New Workflow for QSAR Model Development from Small Data Sets: Small Dataset Curator and Small Dataset Modeler. Integration of Data Curation, Exhaustive Double Cross-Validation, and a Set of Optimal Model Selection Techniques

Machine learning for automating subjective clinical assessment of gait impairment in people with acquired brain injury - a comparison of an image extraction and classification system to expert scoring

BACKGROUND

Walking impairment is a common disability post acquired brain injury (ABI), with visually evident arm movement abnormality identified as negatively impacting a multitude of psychological factors. The International Classification of Functioning, Disability and Health (ICF) qualifiers scale has been used to subjectively assess arm movement abnormality, showing strong intra-rater and test-retest reliability, however, only moderate inter-rater reliability. This impacts clinical utility, limiting its use as a measurement tool. To both automate the analysis and overcome these errors, the primary aim of this study was to evaluate the ability of a novel two-level machine learning model to assess arm movement abnormality during walking in people with ABI.

METHODS

Frontal plane gait videos were used to train four networks with 50%, 75%, 90%, and 100% of participants (ABI: n = 42, healthy controls: n = 34) to automatically identify anatomical landmarks using DeepLabCut™ and calculate two-dimensional kinematic joint angles. Assessment scores from three experienced neurorehabilitation clinicians were used with these joint angles to train random forest networks with nested cross-validation to predict assessor scores for all videos. Agreement between unseen participant (i.e. test group participants that were not used to train the model) predictions and each individual assessor's scores were compared using quadratic weighted kappa. One sample t-tests (to determine over/underprediction against clinician ratings) and one-way ANOVA (to determine differences between networks) were applied to the four networks.

RESULTS

The machine learning predictions have similar agreement to experienced human assessors, with no statistically significant (p < 0.05) difference for any match contingency. There was no statistically significant difference between the predictions from the four networks (F = 0.119; p = 0.949). The four networks did however under-predict scores with small effect sizes (p range = 0.007 to 0.040; Cohen's d range = 0.156 to 0.217).

CONCLUSIONS

This study demonstrated that machine learning can perform similarly to experienced clinicians when subjectively assessing arm movement abnormality in people with ABI. The relatively small sample size may have resulted in under-prediction of some scores, albeit with small effect sizes. Studies with larger sample sizes that objectively and automatically assess dynamic movement in both local and telerehabilitation assessments, for example using smartphones and edge-based machine learning, to reduce measurement error and healthcare access inequality are needed.

Cytotoxicity prediction of nano metal oxides on different lung cells via Nano-QSAR

In recent years, nanomaterials have found extensive applications across diverse domains owing to their distinctive physical and chemical characteristics. It is of great importance in theoretical and practical terms to carry out the relationship between structural characteristics of nanomaterials and different cytotoxicity and to achieve practical assessment and prediction of cytotoxicity. This study investigated the intrinsic quantitative constitutive relationships between the cytotoxicity of nano-metal oxides on human normal lung epithelial cells and human lung adenocarcinoma cells. We first employed quasi-SMILES-based nanostructural descriptors by selecting the five physicochemical properties that are most closely related to the cytotoxicity of nanometal oxides, then established SMILES-based descriptors that can effectively describe and characterize the molecular structure of nanometal oxides, and then built the corresponding Nano-Quantitative Structure-Activity Relationship (Nano-QSAR) prediction models, finally, combined with the theory of reactive oxygen species (ROS) biotoxicity, to reveal the mechanism of toxicity and differences between the two cell types. The established model can efficiently and accurately predict the properties of targets, reveal the corresponding toxicity mechanisms, and guide the safe design, synthesis, and application of nanometal oxides.

First report on chemometric modeling of tilapia fish aquatic toxicity to organic chemicals: Toxicity data gap filling

The Toxic Substances Control Act (TSCA) mandates the Environmental Protection Agency (EPA) to document chemicals entering the US. Due to the vast range of toxicity endpoints, experimental toxicological study for all chemicals is impossible to conduct. To address this, in silico methods like QSAR and read-across are strategically used to prioritize testing for chemicals lacking ecotoxicity data. Aquatic toxicity is one of the most critical endpoints directly related to aquatic species, mainly fish, followed by direct to indirect effects on humans through drinking water and fish as food, respectively. Therefore, we have employed the ToxValDB database to curate acute LC50 toxicity data for three Tilapia species covering two different genera, an ideal species for aquatic toxicity testing. Employing the curated dataset, we have developed multiple robust and predictive QSAR and quantitative read-across structure-activity relationship (q-RASAR) models for Tilapia zillii, Oreochromis niloticus, and Oreochromis mossambicus which helped to understand the toxicological mode of action (MoA) of the modeled chemicals and predict the aquatic toxicity of new untested chemicals followed by toxicity data gap filling. The best three QSAR models showed encouraging statistical quality in terms of determination coefficient R2 (0.94, 0.74, and 0.77), cross-validated leave-one-out Q2 (0.90, 0.67 and 0.70), and predictive capability in terms of R2pred (0.95, 0.77, and 0.74) for T. zillii, O. niloticus, and O. mossambicus datasets, respectively. The developed best mathematical models were used for the prediction of aquatic toxicity in terms of pLC50 for 297 untested organic chemicals across three major Tilapia species ranging from 1.841 to 8.561 M in terms of environmental risk assessment.

MASSA Algorithm: an automated rational sampling of training and test subsets for QSAR modeling

QSAR models capable of predicting biological, toxicity, and pharmacokinetic properties were widely used to search lead bioactive molecules in chemical databases. The dataset's preparation to build these models has a strong influence on the quality of the generated models, and sampling requires that the original dataset be divided into training (for model training) and test (for statistical evaluation) sets. This sampling can be done randomly or rationally, but the rational division is superior. In this paper, we present MASSA, a Python tool that can be used to automatically sample datasets by exploring the biological, physicochemical, and structural spaces of molecules using PCA, HCA, and K-modes. The proposed algorithm is very useful when the variables used for QSAR are not available or to construct multiple QSAR models with the same training and test sets, producing models with lower variability and better values for validation metrics. These results were obtained even when the descriptors used in the QSAR/QSPR were different from those used in the separation of training and test sets, indicating that this tool can be used to build models for more than one QSAR/QSPR technique. Finally, this tool also generates useful graphical representations that can provide insights into the data.

Identification of novel pyrazole containing ɑ-glucosidase inhibitors: insight into pharmacophore, 3D-QSAR, virtual screening, and molecular dynamics study

Pharmacophore modelling, 3 D QSAR modelling, virtual screening, and molecular dynamics study, all-in-one combination were employed successfully design and develop an alpha-glucosidase inhibitor. To explain the structural prerequisites of biologically active components, 3 D-QSAR models were generated using the selected best hypothesis (AARRR) for compounds 55 included in the model C. The selection of 3 D-QSAR models showed that the Gaussian steric characteristic is crucial to alpha glucosidase's inhibitory potential. The alpha-glucosidase inhibitory potency of the compound is enhanced by other components, including Gaussian hydrophobic groups, Gaussian hydrogen bond acceptor or donor groups, Gaussian electrostatic characteristics, and a Gaussian steric feature. An identification of structure-activity relationships can be obtained from the developed 3 D-QSAR, C model, with R2 = 0.77 and SD = 0.02 for training set, and Q2 = 0.66, RMSE 0.02, and Pearson R = 0.81 for testing set, corresponding to elevated predictive ability. Additionally, docking and MM/GBSA experiments on 1146023 showed that it interacts with critical amino acids in the binding site when coupled with acarbose. Further, five compounds that display a high affinity for alpha-glucosidase were found, and these compounds may serve as potent leads for alpha-glucosidase inhibitor development. Biological activity will be tested for these compounds in the future.Communicated by Ramaswamy H. Sarma.

Optimal selection of learning data for highly accurate QSAR prediction of chemical biodegradability: a machine learning-based approach

Prior to the manufacture of new chemicals, regulations mandate a thorough review of the chemicals under risk management. This review involves evaluating their effects on the environment and human health. To assess these effects, a review report that conforms to the OECD Test Guidelines must be submitted to the regulatory body. One of the essential components of the report is an assessment of the biodegradability of chemicals in the environment. In addition to conventional methods, quantitative structure-activity relationship (QSAR) models have been developed to predict the properties of chemicals based on their structural features. Although a greater number of chemicals in the learning set may enhance the prediction accuracy, it may also lead to a decrease in accuracy due to the mixing of different structural features and properties of the chemicals. To improve the prediction performance, it is recommended to use only the appropriate data for biodegradability prediction as a training set. In this study, we propose a novel approach for the optimal selection of training set that enables a highly accurate prediction of the biodegradability of chemicals by QSAR. Our findings indicate that the proposed method effectively reduces the root mean squared error and improves the prediction accuracy.

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.

Intermolecular Interactions of Edaravone in Aqueous Solutions of Ethaline and Glyceline Inferred from Experiments and Quantum Chemistry Computations

Edaravone, acting as a cerebral protective agent, is administered to treat acute brain infarction. Its poor solubility is addressed here by means of optimizing the composition of the aqueous choline chloride (ChCl)-based eutectic solvents prepared with ethylene glycol (EG) or glycerol (GL) in the three different designed solvents compositions. The slurry method was used for spectroscopic solubility determination in temperatures between 298.15 K and 313.15 K. Measurements confirmed that ethaline (ETA = ChCl:EG = 1:2) and glyceline (GLE = ChCl:GL = 1:2) are very effective solvents for edaravone. The solubility at 298.15 K in the optimal compositions was found to be equal x_E = 0.158 (c_E = 302.96 mg/mL) and x_E = 0.105 (c_E = 191.06 mg/mL) for glyceline and ethaline, respectively. In addition, it was documented that wetting of neat eutectic mixtures increases edaravone solubility which is a fortunate circumstance not only from the perspective of a solubility advantage but also addresses high hygroscopicity of eutectic mixtures. The aqueous mixture with 0.6 mole fraction of the optimal composition yielded solubility values at 298.15 K equal to x_E = 0.193 (c_E = 459.69 mg/mL) and x_E = 0.145 (c_E = 344.22 mg/mL) for glyceline and ethaline, respectively. Since GLE is a pharmaceutically acceptable solvent, it is possible to consider this as a potential new liquid form of this drug with a tunable dosage. In fact, the recommended amount of edaravone administered to patients can be easily achieved using the studied systems. The observed high solubility is interpreted in terms of intermolecular interactions computed using the Conductor-like Screening Model for Real Solvents (COSMO-RS) approach and corrected for accounting of electron correlation, zero-point vibrational energy and basis set superposition errors. Extensive conformational search allowed for identifying the most probable contacts, the thermodynamic and geometric features of which were collected and discussed. It was documented that edaravone can form stable dimers stabilized via stacking interactions between five-membered heterocyclic rings. In addition, edaravone can act as a hydrogen bond acceptor with all components of the studied systems with the highest affinities to ion pairs of ETA and GLE. Finally, the linear regression model was formulated, which can accurately estimate edaravone solubility utilizing molecular descriptors obtained from COSMO-RS computations. This enables the screening of new eutectic solvents for finding greener replacers of designed solvents. The theoretical analysis of tautomeric equilibria confirmed that keto-isomer edaravone is predominant in the bulk liquid phase of all considered deep eutectic solvents (DES).

Q-raKtion: A Semiautomated KNIME Workflow for Bioactivity Data Points Curation

The recent increase of bioactivity data freely available to the scientific community and stored as activity data points in chemogenomic repositories provides a huge amount of ready-to-use information to support the development of predictive models. However, the benefits provided by the availability of such a vast amount of accessible information are strongly counteracted by the lack of uniformity and consistency of data from multiple sources, requiring a process of integration and harmonization. While different automated pipelines for processing and assessing chemical data have emerged in the last years, the curation of bioactivity data points is a less investigated topic, with useful concepts provided but no tangible tools available. In this context, the present work represents a first step toward the filling of this gap, by providing a tool to meet the needs of end-user in building proprietary high-quality data sets for further studies. Specifically, we herein describe Q-raKtion, a systematic, semiautomated, flexible, and, above all, customizable KNIME workflow that effectively aggregates information on biological activities of compounds retrieved by two of the most comprehensive and widely used repositories, PubChem and ChEMBL.

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.

Quantitative Structure-Toxicity Relationship in Bioactive Molecules from a Conceptual DFT Perspective

The preclinical drug discovery stage often requires a large amount of costly and time-consuming experiments using huge sets of chemical compounds. In the last few decades, this process has undergone significant improvements by the introduction of quantitative structure-activity relationship (QSAR) modelling that uses a certain percentage of experimental data to predict the biological activity/property of compounds with similar structural skeleton and/or containing a particular functional group(s). The use of machine learning tools along with it has made life even easier for pharmaceutical researchers. Here, we discuss the toxicity of certain sets of bioactive compounds towards Pimephales promelas and Tetrahymena pyriformis in terms of the global conceptual density functional theory (CDFT)-based descriptor, electrophilicity index (ω). We have compared the results with those obtained by using the commonly used hydrophobicity parameter, logP (where P is the n-octanol/water partition coefficient), considering the greater ease of computing the ω descriptor. The Human African trypanosomiasis (HAT) curing activity of 32 pyridyl benzamide derivatives is also studied against Tryphanosoma brucei. In this review article, we summarize these multiple linear regression (MLR)-based QSAR studies in terms of electrophilicity (ω, ω2) and hydrophobicity (logP, (logP)2) parameters.

In silico study of natural antioxidants

Antioxidants are the body's defense system against the damage of reactive oxygen species, which are usually produced in the body through various physiological processes. There are various sources of these antioxidants such as endogenous antioxidants in the body and exogenous food sources. This chapter provides important information on methods used to investigate antioxidant activity and sources of plant antioxidants. Over the past two decades, numerous studies have demonstrated the importance of in silico research in the development of novel natural and synthesized antioxidants. In silico methods such as quantitative structure-activity relationships (QSAR), pharmacophore, docking, and virtual screenings are play critical roles in designing effective antioxidants that may be synthesized and tested later. This chapter introduces the available in silico approaches for different classes of antioxidants. Many successful applications of in silico methods in the development and design of novel antioxidants are thoroughly discussed. The QSAR, pharmacophore, molecular docking techniques, and virtual screenings process summarized here would help readers to find out the proper mechanism for the interaction between the free radicals and antioxidant compounds. Furthermore, this chapter focuses on introducing new QSAR models in combination with other in silico methods to predict antioxidants activity and design more active antioxidants. In silico studies are essential to explore largely unknown plant tissue, food sources for antioxidant synthesis, as well as saving time and money in such studies.

QSPR Modeling and Experimental Determination of the Antioxidant Activity of Some Polycyclic Compounds in the Radical-Chain Oxidation Reaction of Organic Substrates

The present work addresses the quantitative structure−antioxidant activity relationship in a series of 148 sulfur-containing alkylphenols, natural phenols, chromane, betulonic and betulinic acids, and 20-hydroxyecdysone using GUSAR2019 software. Statistically significant valid models were constructed to predict the parameter logk7, where k7 is the rate constant for the oxidation chain termination by the antioxidant molecule. These results can be used to search for new potentially effective antioxidants in virtual libraries and databases and adequately predict logk7 for test samples. A combination of MNA- and QNA-descriptors with three whole molecule descriptors (topological length, topological volume, and lipophilicity) was used to develop six statistically significant valid consensus QSPR models, which have a satisfactory accuracy in predicting logk7 for training and test set structures: R2TR > 0.6; Q2TR > 0.5; R2TS > 0.5. Our theoretical prediction of logk7 for antioxidants AO1 and AO2, based on consensus models agrees well with the experimental value of the measure in this paper. Thus, the descriptor calculation algorithms implemented in the GUSAR2019 software allowed us to model the kinetic parameters of the reactions underlying the liquid-phase oxidation of organic hydrocarbons.

Studying Complex Evolution of Hyperelastic Materials under External Field Stimuli using Artificial Neural Networks with Spatiotemporal Features in a Small-Scale Dataset

Deep-learning (DL) methods, in consideration of their excellence in dealing with highly complex structure-performance relationships for materials, are expected to become a new design paradigm for breakthroughs in material performance. However, in most cases, it is impractical to collect massive-scale experimental data or open-source theoretical databases to support training DL models with sufficient prediction accuracy. In a dataset consisting of 483 porous silicone rubber observations generated via ink-writing additive manufacturing, this work demonstrates that constructing low-dimensional, accurate descriptors is the prerequisite for obtaining high-precision DL models based on small experimental datasets. On this basis, a unique convolutional bidirectional long short-term memory model with spatiotemporal features extraction capability is designed, whose hierarchical learning mechanism further reduces the requirement for the amount of data by taking full advantage of data information. The proposed approach can be expected as a powerful tool for innovative material design on small experimental datasets, which can also be used to explore the evolutionary mechanisms of the structures and properties of materials under complex working conditions.

Monte Carlo Models for Sub-Chronic Repeated-Dose Toxicity: Systemic and Organ-Specific Toxicity

The risk-characterization of chemicals requires the determination of repeated-dose toxicity (RDT). This depends on two main outcomes: the no-observed-adverse-effect level (NOAEL) and the lowest-observed-adverse-effect level (LOAEL). These endpoints are fundamental requirements in several regulatory frameworks, such as the Registration, Evaluation, Authorization and Restriction of Chemicals (REACH) and the European Regulation of 1223/2009 on cosmetics. The RDT results for the safety evaluation of chemicals are undeniably important; however, the in vivo tests are time-consuming and very expensive. The in silico models can provide useful input to investigate sub-chronic RDT. Considering the complexity of these endpoints, involving variable experimental designs, this non-testing approach is challenging and attractive. Here, we built eight in silico models for the NOAEL and LOAEL predictions, focusing on systemic and organ-specific toxicity, looking into the effects on the liver, kidney and brain. Starting with the NOAEL and LOAEL data for oral sub-chronic toxicity in rats, retrieved from public databases, we developed and validated eight quantitative structure-activity relationship (QSAR) models based on the optimal descriptors calculated by the Monte Carlo method, using the CORAL software. The results obtained with these models represent a good achievement, to exploit them in a safety assessment, considering the importance of organ-related toxicity.

Nano-read-across predictions of toxicity of metal oxide engineered nanoparticles (MeOx ENPS) used in nanopesticides to BEAS-2B and RAW 264.7 cells

The demand for nutrients and new technologies has increased with population growth. The agro-technological revolution with metal oxide engineered nanoparticles (MeOx ENPs) has the potential to reform the resilient agricultural system while maintaining the security of food. When utilized extensively, MeOx ENPs may have unintended toxicological effects on both target and non-targeted species. Since limited information about nanopesticides' pernicious effects is available, in silico modeling can be done to explore these issues. Hence, in the present work, we have applied computational modeling to explore the influence of metal oxide nanoparticles on the toxicity of bronchial epithelial (BEAS-2B) and murine myeloid (RAW 264.7) cells to bridge the data gap relating to the toxicity of MeOx NPs. Initially, partial least squares (PLS) regression models were developed applying the Small Dataset Modeler software (http://teqip.jdvu.ac.in/QSAR_Tools/DTCLab/) using four datasets having effective concentration (EC₅₀%) as the endpoints and employing only periodic table descriptors. To further explore the predictions, we applied a read-across approach using the descriptors selected in the QSAR models. Also, the inter-endpoint cytotoxicity relationship modeling (quantitative toxicity-toxicity relationship or QTTR) was conducted. It was found that the result obtained by nano-read-across provided a similar level of accuracy as provided by QSAR. The information derived from the PLS models of both the cell lines suggested that metal cation formation, and bond-forming capacity influence the toxicity whereas the presence of metal has an influential impact on the ecotoxicological effects. Thus, it is feasible to design safe nanopesticides that could be more effective than conventional analogs.

Prediction reliability of QSAR models: an overview of various validation tools

The reliability of any quantitative structure-activity relationship (QSAR) model depends on multiple aspects such as the accuracy of the input dataset, selection of significant descriptors, the appropriate splitting process of the dataset, statistical tools used, and most notably on the measures of validation. Validation, the most crucial step in QSAR model development, confirms the reliability of the developed QSAR models and the acceptability of each step in the model development. The present review deals with various validation tools that involve multiple techniques that improve the model quality and robustness. The double cross-validation tool helps in building improved quality models using different combinations of the same training set in an inner cross-validation loop. This exhaustive method is also integrated for small datasets (< 40 compounds) in another tool, namely the small dataset modeler tool. The main aim of QSAR researchers is to improve prediction quality by lowering the prediction errors for the query compounds. 'Intelligent' selection of multiple models and consensus predictions integrated in the intelligent consensus predictor tool were found to be more externally predictive than individual models. Furthermore, another tool called Prediction Reliability Indicator was explained to understand the quality of predictions for a true external set. This tool uses a composite scoring technique to identify query compounds as 'good' or 'moderate' or 'bad' predictions. We have also discussed a quantitative read-across tool which predicts a chemical response based on the similarity with structural analogues. The discussed tools are freely available from https://dtclab.webs.com/software-tools or http://teqip.jdvu.ac.in/QSAR_Tools/DTCLab/ and https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home (for read-across).

Modeling and mechanistic understanding of cytotoxicity of metal oxide nanoparticles (MeOxNPs) to Escherichia coli: categorization and data gap filling for untested metal oxides

Metal oxide nanoparticles (MeO_xNPs) production is expected to increase every year exponentially, and their potential to cause adverse effect to the environment and human health will also expand rapidly. Hence, risk assessment of nanoparticles (NPs) is necessary to design ecosafe products. However, experimental ecotoxicological assessments are time-consuming requiring a lot of resources. Therefore, researchers rely on alternative in silico approaches to predict the behavior of NPs in the biological system. Quantitative structure - toxicity relationship (QSTR) has been adopted as a potential method to predict the cytotoxicity of untested NPs. Hence, in the present study, multiple linear regression (MLR) models were developed using 17 MeO_xNPs on Escherichia coli (E. coli) bacteria cells under both light and dark conditions. The models were developed applying Small Dataset Modeler software, version 1.0.0 (http://teqip.jdvu.ac.in/QSAR_Tools/DTCLab/) which generates models with a limited number of data points. Periodic table-based descriptors (both 1st and 2nd generation) were used for the modeling purpose. Two statistically significant MLR models based on photo-induced toxicity (Q(LOO)2= 0.612, R² = 0.726) and dark-based toxicity (Q(LOO)2= 0.627, R² = 0.770) were developed. From the developed models, we interpreted that increase in valency and oxidation state of the metal will decrease the cytotoxicity whereas the atomic radius of the metal and electronegativity of MeO_xNPs influence the toxicity toward E. coli cells. The MLR models were validated using different internal validation metrics. Additionally, we have collected 42 MeO_xNPs as an external set to observe the predictive power of the two developed MLR models and categorize them into toxic and non-toxic classes. The chemical features selected in the developed models are important for understanding the mechanisms of nanotoxicity. Thus, the developed models can be a scientific basis for designing safer NPs.

QSAR models for soil ecotoxicity: Development and validation of models to predict reproductive toxicity of organic chemicals in the collembola Folsomia candida

Soil pollution is a critical environmental challenge: the substances released in the soil can adversely affect humans and the ecosystem. Several bioassays were developed to investigate the soil ecotoxicity of chemicals with soil microbes, plants, invertebrates and vertebrates. The 28-day collembolan reproduction test with the springtail Folsomia candida is a recently introduced bioassay described by OECD guideline 232. Although the importance of springtails for maintaining soil quality, toxicity data for Collembola are still limited. We have developed two QSAR models for the prediction of reproductive toxicity induced by organic compounds in Folsomia candida using 28 days NOEC data. We assembled a dataset with the highest number of compounds available so far: 54 compounds were collected from publicly available sources, including plant protection products, reactive intermediates and industrial chemicals, household and cosmetic ingredients, drugs, environmental transformation products and polycyclic aromatic hydrocarbons. The models were developed using partial least squares regression (PLS) and the Monte Carlo technique with respectively the open source tools Small Dataset Modeler and CORAL software. Both QSAR models gave good predictive performance even though based on a small dataset, so they could serve for the ecological risk assessment of chemicals for terrestrial organisms.

Ecotoxicological QSTR and QSTTR Modeling for the Prediction of Acute Oral Toxicity of Pesticides against Multiple Avian Species

The ever-increasing use of pesticides in response to the rising agricultural demand has threatened the existence of nontarget organisms like avian species, disrupting the global ecological integrity. Therefore, it is critical to protect and restore different endangered bird species from the perspective of ecosystem safety. In the present work, we have developed regression-based two-dimensional quantitative structure toxicity relationship (2D QSTR) and quantitative structure toxicity-toxicity relationship (QSTTR) models to estimate the toxicity of pesticides on five different avian species following the Organization for Economic Co-operation and Development (OECD) guidelines. Rigorous validation has been performed using different statistical internal and external validation parameters to ensure the robustness and interpretability of the developed models. From the developed models, it can be stated that the presence of electronegative and lipophilic features greatly enhance pesticide toxicity, whereas the hydrophilic characters are shown to have a detrimental impact on the toxicity of pesticides. Moreover, the developed QSTTR models have been employed to the in silico toxicity prediction of 124, 154, and 250 pesticides against bobwhite quail, ring-necked pheasant, and mallard duck species, respectively, extracted from the Office of Pesticides Program (OPP) Pesticide Ecotoxicity Database. The information obtained from the modeled descriptors might be used for pesticide risk assessment in the future, with the added benefit of providing an early caution of their possible negative impact on birds for regulatory purposes.

Computational insight to design new potential hepatitis C virus NS5B polymerase inhibitors with drug-likeness and pharmacokinetic ADMET parameters predictions

Background

Hepatitis C virus (HCV) is considered a worldwide health problem since it affects over 3% of the population and causes 300,000 fatalities per year. Chronic infection causes high morbidity and mortality in patients, leading to liver cirrhosis, hepatocellular carcinoma, fibrosis, liver cancer, and other HCV-related illnesses. Finding novel and better HCV treatments is a top international health goal right now. As a result, the pressing need for new HCV antiviral drugs has fueled research into the structural requirements of NS5B polymerase inhibitors at a molecular basis.

Results

In this study, an in silico technique was applied to study 79 compounds with HCV inhibitory bioactivity, with the best statistical results ($$R^{2}$$ R 2 = 0.7051, $$Q^{2}$$ Q 2 = 0.6455, $$R_{{{\text{pred}}}}^{2}$$ R pred 2 = 0.6992, $$^{{\text{c}}} R_{{\text{r}}}^{2}$$ c R r 2 = 0.6570, SEE = 0.2694).

Conclusions

This QSAR investigation allowed the research team to evaluate the influence of straightforward descriptors, shedding insight into the critical elements that guide the design of innovative effective molecules. Most of the innovative effective molecules exhibited better binding affinity (− 195.6 kcal/mol) than dasabuvir the reference drug (− 171.0 kcal/mol) with the target receptor (hepatitis C virus NS5B RNA polymerase). ADMET prediction disclosed enhanced pharmacokinetic properties with lower MRTD (maximum tolerated dose) of some new derivatives.

Ecotoxicological QSAR modeling of the acute toxicity of organic compounds to the freshwater crustacean Thamnocephalus platyurus

Growing interest in environmental toxicity assessment using Thamnocephalus platyurus as organism has led to an increased availability of acute toxicity data. Despite this growing interest in tests with this organism, however, to the best of our knowledge there are no computational models to predict the acute toxicity in T. platyurus. In view of the limited number of in silico models for this crustacean, we developed Quantitative Structure-Activity Relationship (QSAR) models for the prediction of acute toxicity towards T. platyurus, reflected by the 24h LC_50, using publicly available data according to the ISO 14380:2011 guideline. Two models were developed following the principles of QSAR modeling recommended by the Organization for Economic Cooperation and Development (OECD). We used partial least squares and gradient boosting machine techniques, which gave encouraging statistical quality in our data set.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

In silico modelling of acute toxicity of 1, 2, 4-triazole antifungal agents towards zebrafish (Danio rerio) embryos: Application of the Small Dataset Modeller tool

Nowadays, there is a widespread use of triazole antifungal agents to kill broad classes of fungi in farming lands and to protect herbs, fruits and grains. These agents further deposit into the aquatic systems causing toxicity to the living aquatic creatures, which can then affect human beings. Considering this issue, risk assessment of these toxic chemicals is a very essential task. Due to the inadequate experimental data on acute toxicity of antifungal agents containing the 1, 2, 4-triazole ring, higher testing costs along with the regulatory restrictions and the international regulations to lessen animal testing emphasize on in silico techniques such as quantitative structure-activity relationship (QSAR) studies. The application of QSAR modelling has created an easier avenue to predict activity/property/toxicity of newly synthesized compounds. In the present study, we have used 23 antifungal agents containing the 1, 2, 4-triazole ring to develop 2D-QSAR models and explored their structural attributes crucial for acute toxicity towards embryonic phase of zebrafish (Danio rerio). Here, we have employed simple 2D descriptors to develop the QSAR models. The models were evolved by executing the Small Dataset Modeller tool (https://dtclab.webs.com/software-tools), and the validation of the models was achieved by employing different precise validation principles. The statistical validation metrics confirm that built models are robust, useful and well predictive to forecast the acute toxicity of new compounds.

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.

Consensus versus Individual QSARs in Classification: Comparison on a Large-Scale Case Study

Consensus strategies have been widely applied in many different scientific fields, based on the assumption that the fusion of several sources of information increases the outcome reliability. Despite the widespread application of consensus approaches, their advantages in quantitative structure–activity relationship (QSAR) modeling have not been thoroughly evaluated, mainly due to the lack of appropriate large-scale data sets. In this study, we evaluated the advantages and drawbacks of consensus approaches compared to single classification QSAR models. To this end, we used a data set of three properties (androgen receptor binding, agonism, and antagonism) for approximately 4000 molecules with predictions performed by more than 20 QSAR models, made available in a large-scale collaborative project. The individual QSAR models were compared with two consensus approaches, majority voting and the Bayes consensus with discrete probability distributions, in both protective and nonprotective forms. Consensus strategies proved to be more accurate and to better cover the analyzed chemical space than individual QSARs on average, thus motivating their widespread application for property prediction. Scripts and data to reproduce the results of this study are available for download.

In silico QSAR and molecular docking simulation of some novel aryl sulfonamide derivatives as inhibitors of H5N1 influenza A virus subtype

Background

This research provides a comprehensive analysis of QSAR modeling performed on 25 aryl sulfonamide derivatives to predict their effective concentration (EC50) against H5N1 influenza A virus by using some numerical information derived from structural and chemical features (descriptors) of the compounds to generate a statistically significant model. Subsequently, the molecular docking simulations were done so as to determine the binding modes of some potent ligands in the dataset with the M2 proton channel protein of the H5N1 influenza A virus as the target.

Results

In building the QSAR model, the genetic algorithm task was employed in the variable selection of the descriptors which are used to form the multi-linear regression equation. The model with descriptors, RDF100m, nO, and RDF45p, showed satisfactory internal and external validation parameters (R2train = 0.72963, R2adjusted = 0.67169, Q2cv = 0.598, $$ {R}_{\mathrm{pred}}^2= $$Rpred2= 0.67295, R2test = 0.6860) which passed the model criteria of acceptability. Docking simulation results of the more potent compounds (ligands 2, 3, and 8) revealed the formation of hydrophobic and hydrogen bonds with the binding pockets of M2 protein of influenza A virus.

Conclusion

The results in this study can help to advance the research in designing (in silico design) and synthesis of more potent aryl sulfonamides derivatives against H5N1 influenza virus.

Exploring indole derivatives as myeloid cell leukaemia-1 (Mcl-1) inhibitors with multi-QSAR approach: a novel hope in anti-cancer drug discovery

In humans, the over-expression of Mcl-1 protein causes different cancers and it is also responsible for cancer resistance to different cytotoxic agents.

The good, the bad, and the ugly in chemical and biological data for machine learning

Machine learning and artificial intelligence (ML/AI) have become important research tools in molecular medicine and chemistry. Their rise and recent success in drug discovery promises a rapid progression of development pipelines while reshaping how fundamental and clinical research is conducted. By taking advantage of the ever-growing wealth of publicly available and proprietary data, learning algorithms now provide an attractive means to generate statistically motivated research hypotheses. Hitherto unknown data patterns may guide and prioritize experiments, and augment expert intuition. Therefore, data is a key component in the model building workflow. Herein, I aim to discuss types of chemical and biological data according to their quality and reemphasize general recommendations for their use in ML/AI.