Statistical Methods in QSAR/QSPR

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.

Application of parallel artificial membrane permeability assay technique and chemometric modeling for blood-brain barrier permeability prediction of protein kinase inhibitors

Aim: This study aims to investigate the passive diffusion of protein kinase inhibitors through the blood-brain barrier (BBB) and to develop a model for their permeability prediction. Materials & methods: We used the parallel artificial membrane permeability assay to obtain logPe values of each of 34 compounds and calculated descriptors for these structures to perform quantitative structure-property relationship modeling, creating different regression models. Results: The logPe values have been calculated for all 34 compounds. Support vector machine regression was considered the most reliable, and CATS2D_09_DA, CATS2D_04_AA, B04[N-S] and F07[C-N] descriptors were identified as the most influential to passive BBB permeability. Conclusion: The quantitative structure-property relationship-support vector machine regression model that has been generated can serve as an efficient method for preliminary screening of BBB permeability of new analogs.

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.

In-silico molecular modelling studies of some camphor imine based compounds as anti-influenza A (H1N1) pdm09 virus agents

The advent of influenza A (H1N1) drug-resistant strains led to the search quest for more potent inhibitors of the influenza A virus, especially in this devastating COVID-19 pandemic era. Hence, the present research utilized some molecular modelling strategies to unveil new camphor imine-based compounds as anti-influenza A (H1N1) pdm09 agents. The 2D-QSAR results revealed GFA-MLR (R2train = 0.9158, Q2=0.8475) and GFA-ANN (R2train = 0.9264, Q2=0.9238) models for the anti-influenza A (H1N1) pdm09 activity prediction which have passed the QSAR model acceptability thresholds. The results from the 3D-QSAR studies also revealed CoMFA (R2train =0.977, Q2=0.509) and CoMSIA_S (R2train =0.976, Q2=0.527) models for activity predictions. Based on the notable information derived from the 2D-QSAR, 3D-QSAR, and docking analysis, ten (10) new camphor imine-based compounds (22a-22j) were designed using the most active compound 22 as the template. Furthermore, the high predicted activity and binding scores of compound 22j were further justified by the high reactive sites shown in the electrostatic potential maps and other quantum chemical calculations. The MD simulation of 22j in the active site of the influenza hemagglutinin (HA) receptor confirmed the dynamic stability of the complex. Moreover, the appraisals of drug-likeness and ADMET properties of the proposed compounds showed zero violation of Lipinski's criteria with good pharmacokinetic profiles. Hence, the outcomes in this work recommend further in-depth in vivo and in-vitro investigations to validate these theoretical findings.Communicated by Ramaswamy H. Sarma.

Molecular modelling studies of substituted indole derivatives as novel influenza a virus inhibitors

The emergence of drug-resistant strains motivate researchers to find new innovative anti-IAV candidates with a different mode of action. In this work, molecular modelling strategies, such as 2D-QSAR, 3D-QSAR, molecular docking, molecular dynamics, FMOs, and ADMET were applied to some substituted indoles as IAV inhibitors. The best-developed 2D-QSAR models, MLR (Q2 = 0.7634, R2train = 0.8666) and ANN[4-3-1] (Q2 = 0.8699, R2train = 0.8705) revealed good statistical validation for the inhibitory response predictions. The 3D-QSAR models, CoMFA (Q2 = 0.504, R2train = 0.805) and CoMSIA/SEDHA (Q2 = 0.619, R2train = 0.813) are selected as the best 3D models following the global thresholds. In addition, the contour maps generated from the CoMFA and CoMSIA models illustrate the relationship between the molecular fields and the inhibitory effects of the studied molecules. The results of the studies led to the design of five new molecules (24a-e) with enhanced anti-IAV activities and binding potentials using the most active molecule (24) as the template scaffold. The conformational stability of the best-designed molecules with the NA protein showed hydrophobic and H-bonds with the key residues from the molecular dynamics simulations of 100 ns. Furthermore, the global reactivity indices from the DFT calculations portrayed the relevance of 24c in view of its smaller band gap as also justified by our QSAR and molecular simulation studies.Communicated by Ramaswamy H. Sarma.

QSAR classification model for diverse series of antifungal agents based on binary coyote optimization algorithm

One of the recently developed metaheuristic algorithms, the coyote optimization algorithm (COA), has shown to perform better in a number of difficult optimization tasks. The binary form, BCOA, is used in this study as a solution to the descriptor selection issue in classifying diverse antifungal series. Z-shape transfer functions (ZTF) are evaluated to verify their efficiency in improving BCOA performance in QSAR classification based on classification accuracy (CA), the geometric mean of sensitivity and specificity (G-mean), and the area under the curve (AUC). The Kruskal-Wallis test is also applied to show the statistical differences between the functions. The efficacy of the best suggested transfer function, ZTF4, is further assessed by comparing it to the most recent binary algorithms. The results prove that ZTF, especially ZTF4, significantly improves the performance of the original BCOA. The ZTF4 function yields the best CA and G-mean of 99.03% and 0.992%, respectively. It shows the fastest convergence behaviour compared to other binary algorithms. It takes the fewest iterations to reach high classification performance and selects the fewest descriptors. In conclusion, the obtained results indicate the ability of the ZTF4-based BCOA to find the smallest subset of descriptors while maintaining the best classification accuracy performance.

Computational modeling of PET imaging agents for vesicular acetylcholine transporter (VAChT) protein binding affinity: application of 2D-QSAR modeling and molecular docking techniques

The neurotransmitter acetylcholine (ACh) plays a ubiquitous role in cognitive functions including learning and memory with widespread innervation in the cortex, subcortical structures, and the cerebellum. Cholinergic receptors, transporters, or enzymes associated with many neurodegenerative diseases, including Alzheimer's disease (AD) and Parkinson's disease (PD), are potential imaging targets. In the present study, we have developed 2D-quantitative structure-activity relationship (2D-QSAR) models for 19 positron emission tomography (PET) imaging agents targeted against presynaptic vesicular acetylcholine transporter (VAChT). VAChT assists in the transport of ACh into the presynaptic storage vesicles, and it becomes one of the main targets for the diagnosis of various neurodegenerative diseases. In our work, we aimed to understand the important structural features of the PET imaging agents required for their binding with VAChT. This was done by feature selection using a Genetic Algorithm followed by the Best Subset Selection method and developing a Partial Least Squares- based 2D-QSAR model using the best feature combination. The developed QSAR model showed significant statistical performance and reliability. Using the features selected in the 2D-QSAR analysis, we have also performed similarity-based chemical read-across predictions and obtained encouraging external validation statistics. Further, we have also performed molecular docking analysis to understand the molecular interactions occurring between the PET imaging agents and the VAChT receptor. The molecular docking results were correlated with the QSAR features for a better understanding of the molecular interactions. This research serves to fulfill the experimental data gap, highlighting the applicability of computational methods in the PET imaging agents' binding affinity prediction.

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s40203-023-00146-4.

Discovery of new chemotypes of dual 5-HT2A/D2 receptor antagonists with a strategy of drug design methodologies

Aim: Through the application of structure- and ligand-based methods, the authors aimed to create an integrative approach to developing a computational protocol for the rational drug design of potent dual 5-HT_2A/D₂ receptor antagonists without off-target activities on H₁ receptors. Materials & methods: Molecular dynamics and virtual docking methods were used to identify key interactions of the structurally diverse antagonists in the binding sites of the studied targets, and to generate their bioactive conformations for further 3D-quantitative structure-activity relationship modeling. Results & conclusion: Toward the goal of finding multi-potent drugs with a more effective and safer profile, the obtained results led to the design of a new set of dual antagonists and opened a new perspective on the therapy for complex brain diseases.

Assessing the influence of the amount of reachable habitat on genetic structure using landscape and genetic graphs

Genetic structure, i.e. intra-population genetic diversity and inter-population genetic differentiation, is influenced by the amount and spatial configuration of habitat. Measuring the amount of reachable habitat (ARH) makes it possible to describe habitat patterns by considering intra-patch and inter-patch connectivity, dispersal capacities and matrix resistance. Complementary ARH metrics computed under various resistance scenarios are expected to reflect both drift and gene flow influence on genetic structure. Using an empirical genetic dataset concerning the large marsh grasshopper (Stethophyma grossum), we tested whether ARH metrics are good predictors of genetic structure. We further investigated (i) how the components of the ARH influence genetic structure and (ii) which resistance scenario best explains these relationships. We computed local genetic diversity and genetic differentiation indices in genetic graphs, and ARH metrics in the unified and flexible framework offered by landscape graphs, and we tested the relationships between these variables. ARH metrics were relevant predictors of the two components of genetic structure, providing an advantage over commonly used habitat metrics. Although allelic richness was significantly explained by three complementary ARH metrics in the best PLS regression model, private allelic richness and MIW indices were essentially related with the ARH measured outside the focal patch. Considering several matrix resistance scenarios was also key for explaining the different genetic responses. We thus call for further use of ARH metrics in landscape genetics to explain the influence of habitat patterns on the different components of genetic structure.

High-Throughput Routes to Biomaterials Discovery

Many existing clinical treatments are limited in their ability to completely restore decreased or lost tissue and organ function, an unenviable situation only further exacerbated by a globally aging population. As a result, the demand for new medical interventions has increased substantially over the past 20 years, with the burgeoning fields of gene therapy, tissue engineering, and regenerative medicine showing promise to offer solutions for full repair or replacement of damaged or aging tissues. Success in these fields, however, inherently relies on biomaterials that are engendered with the ability to provide the necessary biological cues mimicking native extracellular matrixes that support cell fate. Accelerating the development of such "directive" biomaterials requires a shift in current design practices toward those that enable rapid synthesis and characterization of polymeric materials and the coupling of these processes with techniques that enable similarly rapid quantification and optimization of the interactions between these new material systems and target cells and tissues. This manuscript reviews recent advances in combinatorial and high-throughput (HT) technologies applied to polymeric biomaterial synthesis, fabrication, and chemical, physical, and biological screening with targeted end-point applications in the fields of gene therapy, tissue engineering, and regenerative medicine. Limitations of, and future opportunities for, the further application of these research tools and methodologies are also discussed.

Current computer-aided drug design methodologies in discovery of novel drug candidates for neuropsychiatric and inflammatory diseases

Drug discovery and development is a very challenging, expensive and time-consuming process. Impressive technological advances in computer sciences and molecular biology have made it possible to use computer-aided drug design (CADD) methods in various stages of the drug discovery and development pipeline. Nowadays, CADD presents an efficacious and indispensable tool, widely used in medicinal chemistry, to lead rational drug design and synthesis of novel compounds. In this article, an overview of commonly used CADD approaches from hit identification to lead optimization was presented. Moreover, different aspects of design of multitarget ligands for neuropsychiatric and anti-inflammatory diseases were summarized. Apparently, designing multi-target directed ligands for treatment of various complex diseases may offer better efficacy, and fewer side effects. Antipsychotics that act through aminergic G protein-coupled receptors (GPCRs), especially Dopamine D2 and serotonin 5-HT2A receptors, are the best option for treatment of various symptoms associated with neuropsychiatric disorders. Furthermore, multi-target directed cyclooxygenase-2 (COX-2) and 5-lipoxygenase (5-LOX) inhibitors are also a successful approach to aid the discovery of new anti-inflammatory drugs with fewer side effects. Overall, employing CADD approaches in the process of rational drug design provides a great opportunity for future development, allowing rapid identification of compounds with the optimal polypharmacological profile.

Comparative QSAR model generation using pyrazole derivatives for screening Janus kinase-1 inhibitors

Asthma is a multitargeted disease. IL-4-JAK-STAT signaling pathway is a promising route for the effective control of the disease. JAK inhibition by small molecules could effectively block the IL-4 signaling pathway. It was established that JAK1 is responsive toward IL-4-mediated signaling process. In the present study, three-dimensional QSAR analyses on a set of pyrazole derivatives against JAK1 and JAK2 enzyme inhibition had been executed. Molecular docking studies were conducted with the target JAK1 using the pyrazole derivative compounds and found out potential intermolecular interactions operating among them. The binding energy of all the derivative compounds with the target JAK1 has calculated and found out their affinity toward the target system. These models have predicted the JAK1 inhibitory activity of some five JAK1 active drugs and 50 structurally similar compounds. These models can, thus, suggestively be recommended for virtual screening of JAK1-selective candidates as a lead for immunomodulatory diseases like asthma.

In silico screening of FDA approved drugs on AXL kinase and validation for breast cancer cell line

AXL kinase has been over expressed in many tumors and its involvement in cell proliferation, migration, survival, and resistance makes the kinase as attractive therapeutic target for many cancers. In this study, we performed a virtual screening of the food and drug administration (FDA) approved drug molecule database against AXL kinase for repurposing studies of breast cancer. We have identified three non-cancer drugs with good binding energies were subjected to in vitro breast cancer MCF-7 cell lines. Three drug molecules showing the activity with good IC50 values toward the cancer cell line. We also carried out a 2 dimensional (2 D) quantitative structure activity relation (QSAR) studies on N-[4-(Quinolin-4-yloxy)phenyl]benzenesulfonamides derivatives to design potent inhibitors for AXL kinase. The final QSAR equation was robust with good predictivity and the statistical validation having R² and Q² values are 0.91 and 0.86, respectively. QSAR equation descriptors informs about the chemical properties of AXL inhibitors and helpful for designing novel inhibitors. Communicated by Ramaswamy H. Sarma.

A robust model for estimating thermal conductivity of liquid alkyl halides

Thermal conductivity is an essential thermodynamic property in chemical engineering application. As a result, estimating the thermal conductivity of organic compounds is of significance in industry production. Alkyl halides are important organic intermediates and raw materials, but little investigations have been performed to estimate their thermal conductivity. In this study, the structures of compounds were optimized in Gaussian 09W and molecular descriptors were extracted by Dragon software. Finally, we developed a 6-descriptor linear quantitative structure-property relationship (QSPR) model to estimate the thermal conductivity of alkyl halides using the genetic function approximation (GFA) method. Validation proved that the developed model had goodness-of-fit, robustness and predictive ability. The r²_pred and root-mean-square error (RMSE_P) of prediction set for the model were equal to 0.9745 and 0.0035, respectively. Meanwhile, the applicability domain was visualized by means of the Williams plot. This study provides a new model for estimating the thermal conductivity of this important class of chemicals.

Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean

Recent substantial advances in high-throughput field phenotyping have provided plant breeders with affordable and efficient tools for evaluating a large number of genotypes for important agronomic traits at early growth stages. Nevertheless, the implementation of large datasets generated by high-throughput phenotyping tools such as hyperspectral reflectance in cultivar development programs is still challenging due to the essential need for intensive knowledge in computational and statistical analyses. In this study, the robustness of three common machine learning (ML) algorithms, multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF), were evaluated for predicting soybean (Glycine max) seed yield using hyperspectral reflectance. For this aim, the hyperspectral reflectance data for the whole spectra ranged from 395 to 1005 nm, which were collected at the R4 and R5 growth stages on 250 soybean genotypes grown in four environments. The recursive feature elimination (RFE) approach was performed to reduce the dimensionality of the hyperspectral reflectance data and select variables with the largest importance values. The results indicated that R5 is more informative stage for measuring hyperspectral reflectance to predict seed yields. The 395 nm reflectance band was also identified as the high ranked band in predicting the soybean seed yield. By considering either full or selected variables as the input variables, the ML algorithms were evaluated individually and combined-version using the ensemble-stacking (E-S) method to predict the soybean yield. The RF algorithm had the highest performance with a value of 84% yield classification accuracy among all the individual tested algorithms. Therefore, by selecting RF as the metaClassifier for E-S method, the prediction accuracy increased to 0.93, using all variables, and 0.87, using selected variables showing the success of using E-S as one of the ensemble techniques. This study demonstrated that soybean breeders could implement E-S algorithm using either the full or selected spectra reflectance to select the high-yielding soybean genotypes, among a large number of genotypes, at early growth stages.

Classification of Staphylococcus Aureus FabI Inhibitors by Machine Learning Techniques

Enoyl-acyl carrier protein reductase (FabI) is a key enzyme in the fatty acid metabolism of gram-positive bacteria and is considered a potential target for new antibacterial drugs development. Indeed, triclosan is a widely employed antibacterial and AFN-1252 is currently under phase-II clinical trials, both are known as FabI inhibitors. Nowadays, there is an urgent need for new drug discovery due to increasing antibacterial resistance. In the present study, classification models using machine learning techniques were generated to distinguish SaFabI inhibitors from non-inhibitors successfully (e.g., Mathews correlation coefficient values equal to 0.837 and 0.789 calculated with internal and external validations). The interpretation of a selected model indicates that larger compounds, number of N atoms and the distance between central amide and naphthyridinone ring are important to biological activity, corroborating previous studies. Therefore, these obtained information and generated models can be useful for design/discovery of novel bioactive ligands as potential antibacterial agents.

Novel hits for acetylcholinesterase inhibition derived by docking-based screening on ZINC database

The inhibition of the enzyme acetylcholinesterase (AChE) increases the levels of the neurotransmitter acetylcholine and symptomatically improves the affected cognitive function. In the present study, we searched for novel AChE inhibitors by docking-based virtual screening of the standard lead-like set of ZINC database containing more than 6 million small molecules using GOLD software. The top 10 best-scored hits were tested in vitro for AChE affinity, neurotoxicity, GIT and BBB permeability. The main pharmacokinetic parameters like volume of distribution, free fraction in plasma, total clearance, and half-life were predicted by previously derived models. Nine of the compounds bind to the enzyme with affinities from 0.517 to 0.735 µM, eight of them are non-toxic. All hits permeate GIT and BBB and bind extensively to plasma proteins. Most of them are low-clearance compounds. In total, seven of the 10 hits are promising for further lead optimisation. These are structures with ZINC IDs: 00220177, 44455618, 66142300, 71804814, 72065926, 96007907, and 97159977.

Strategies of Virtual Screening in Medicinal Chemistry

Virtual screening represents an effective computational strategy to rise-up the chances of finding new bioactive compounds by accelerating the time needed to move from an initial intuition to market. Classically, the most pursued approaches rely on ligand- and structure-based studies, the former employed when structural data information about the target is missing while the latter employed when X-ray/NMR solved or homology models are instead available for the target. The authors will focus on the most advanced techniques applied in this area. In particular, they will survey the key concepts of virtual screening by discussing how to properly select chemical libraries, how to make database curation, how to applying and- and structure-based techniques, how to wisely use post-processing methods. Emphasis will be also given to the most meaningful databases used in VS protocols. For the ease of discussion several examples will be presented.

Ezqsar: An R Package for Developing QSAR Models Directly From Structures

Background:

Quantitative Structure Activity Relationship (QSAR) is a difficult computational chemistry approach for beginner scientists and a time consuming one for even more experienced researchers.

Method and Materials:

Ezqsar which is introduced here addresses both the issues. It considers important steps to have a reliable QSAR model. Besides calculation of descriptors using CDK library, highly correlated descriptors are removed, a provided data set is divided to train and test sets, descriptors are selected by a statistical method, statistical parameter for the model are presented and applicability domain is investigated.

Results:

Finally, the model can be applied to predict the activities for an extra set of molecules for a purpose of either lead optimization or virtual screening. The performance is demonstrated by an example.

Conclusion:

The R package, ezqsar, is freely available viahttps://github.com/shamsaraj/ezqsar, and it runs on Linux and MS-Windows.

Studies of Staphylococcus aureus FabI inhibitors: fragment-based approach based on holographic structure-activity relationship analyses

AIM

FabI is a key enzyme in the fatty acid metabolism of Gram-positive bacteria such as Staphylococcus aureus and is an established drug target for known antibiotics such as triclosan. However, due to increasing antibacterial resistance, there is an urgent demand for new drug discovery. Recently, aminopyridine derivatives have been proposed as promising competitive inhibitors of FabI.

METHODS

In the present study, holographic structure-activity relationship (HQSAR) analyses were employed for determining structural contributions of a series containing 105 FabI inhibitors.

RESULTS & CONCLUSION

The final HQSAR model was robust and predictive according to statistical validation (q² and r²_pred equal to 0.696 and 0.854, respectively) and could be further employed to generate fragment contribution maps. Then, final HQSAR model together with FabI active site information can be useful for designing novel bioactive ligands.

Use of machine learning approaches for novel drug discovery

INTRODUCTION

The use of computational tools in the early stages of drug development has increased in recent decades. Machine learning (ML) approaches have been of special interest, since they can be applied in several steps of the drug discovery methodology, such as prediction of target structure, prediction of biological activity of new ligands through model construction, discovery or optimization of hits, and construction of models that predict the pharmacokinetic and toxicological (ADMET) profile of compounds.

AREAS COVERED

This article presents an overview on some applications of ML techniques in drug design. These techniques can be employed in ligand-based drug design (LBDD) and structure-based drug design (SBDD) studies, such as similarity searches, construction of classification and/or prediction models of biological activity, prediction of secondary structures and binding sites docking and virtual screening.

EXPERT OPINION

Successful cases have been reported in the literature, demonstrating the efficiency of ML techniques combined with traditional approaches to study medicinal chemistry problems. Some ML techniques used in drug design are: support vector machine, random forest, decision trees and artificial neural networks. Currently, an important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.