On the Misleading Use of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msubsup><mml:mi>Q</mml:mi> <mml:mrow><mml:mi>F</mml:mi> <mml:mn>3</mml:mn></mml:mrow> <mml:mn>2</mml:mn></mml:msubsup> </mml:math> for QSAR Model Comparison

QSAR modeling approaches to identify a novel ACE2 inhibitor that selectively bind with the C and N terminals of the ectodomain

Due to the high rates of drug development failure and the massive expenses associated with drug discovery, repurposing existing drugs has become more popular. As a result, we have used QSAR modelling on a large and varied dataset of 657 compounds in an effort to discover both explicit and subtle structural features requisite for ACE2 inhibitory activity, with the goal of identifying novel hit molecules. The QSAR modelling yielded a statistically robust QSAR model with high predictivity (R2tr=0.84, R2ex=0.79), previously undisclosed features, and novel mechanistic interpretations. The developed QSAR model predicted the ACE2 inhibitory activity (PIC50) of 1615 ZINC FDA compounds. This led to the detection of a PIC50 of 8.604 M for the hit molecule (ZINC000027990463). The hit molecule's docking score is -9.67 kcal/mol (RMSD 1.4). The hit molecule revealed 25 interactions with the residue ASP40, which defines the N and C termini of the ectodomain of ACE2. The HIT molecule conducted more than thirty contacts with water molecules and exhibited polar interaction with the ARG522 residue coupled with the second chloride ion, which is 10.4 nm away from the zinc ion. Both molecular docking and QSAR produced comparable findings. Moreover, MD simulation and MMGBSA studies verified docking analysis. The MD simulation showed that the hit molecule-ACE2 receptor complex is stable for 400 ns, suggesting that repurposed hit molecule 3 is a viable ACE2 inhibitor.

Predictionof Environmental FateandToxicityofInsecticidesUsing Multi-Target QSAR Approach

Ecotoxicological risk assessments form the foundation of regulatory decisions for industrial chemicals used in various sectors. In this study, a multi-target-QSAR model established by a backpropagation neural network trained with the Levenberg-Marquardt (LM) algorithm was used to construct a statistically robust and easily interpretable Mt-QSAR model with high external predictability for the simultaneous prediction of the environmental fate in form of octanol-water partition coefficient (LogP), (BCF) and acute oral toxicity in mammals and birds (LD50rat ) and (LD50bird ) for a wide range of chemical structural classes of insecticides. Principal component analysis was performed on descriptors selected by the SW-MLR method, and the selected PCs were used for constructing the SW-MLR-PCA-ANN model. The developed well-trained model (RMSE=0.83, MPE=0.004, CCC=0.82, IIC=0.78, R2 =0.69) was statistically robust as indicated by the external validation parameters (RMSE=0.93, MPE=0.008, CCC=0.77, IIC=0.68, R2 =0.61). The AD of the developed Mt-QSAR model was also defined to identify the most reliable predictions. Finally, the missing values in the dataset for the aforementioned targets were predicted using the constructed Mt-QSAR model. The proposed approach can be used for simultaneous prediction of the environmental fate of new insecticides, especially ones that haven't been tested yet.

In-silico studies of 2-aminothiazole derivatives as anticancer agents by QSAR, molecular docking, MD simulation and MM-GBSA approaches

Targeting Hec1/Nek2 is considered as crucial target for cancer treatment due to its significant role in cell proliferation. In pursuit of this, a series of twenty-five 2-aminothiazoles derivatives, along with their Hec1/Nek2 inhibitory activities were subjected to QSAR studies utilizing QSARINS software. The significant three descriptor QSAR model was generated, showing noteworthy statistical parameters: a correlation coefficient of cross validation leave one out (Q2LOO) = 0.7965, coefficient of determination (R2) = 0.8436, (R2ext) = 0.6308, cross validation leave many out (Q2LMO) = 0.7656, Concordance Correlation Coefficient (CCCCV = 0.8875), CCCtr = 0.9151, and CCCext = 0.0.7241. The descriptors integral to generated QSAR model include Moreau-Broto autocorrelation, which represents the spatial autocorrelation of a property along the molecular graph's topological structure (ATSC1i), Moran autocorrelation at lag 8, which is weighted by charges (MATS8c) and RPSA representing the total molecular surface area. It was noted that these descriptors significantly influence Hec1/Nek2 inhibitory activity of 2-aminothiazoles derivatives. New lead molecules were designed and predicted for their Hec1/Nek2 inhibitory activity based on the developed three descriptor model. Further, the ADMET and Molecular docking studies were carried out for these designed molecules. The three molecules were selected based on their docking score and further subjected for MD simulation studies. Post-MD MM-GBSA analysis were also performed to predicted the free binding energies of molecules. The study helped us to understand the key interactions between 2-aminothiazoles derivatives and Hec1/Nek2 protein that may be necessary to develop new lead molecules against cancer.Communicated by Ramaswamy H. Sarma.

SIRT2i_Predictor: A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors

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

Exposing the Limitations of Molecular Machine Learning with Activity Cliffs

Machine learning has become a crucial tool in drug discovery and chemistry at large, e.g., to predict molecular properties, such as bioactivity, with high accuracy. However, activity cliffs─pairs of molecules that are highly similar in their structure but exhibit large differences in potency─have received limited attention for their effect on model performance. Not only are these edge cases informative for molecule discovery and optimization but also models that are well equipped to accurately predict the potency of activity cliffs have increased potential for prospective applications. Our work aims to fill the current knowledge gap on best-practice machine learning methods in the presence of activity cliffs. We benchmarked a total of 24 machine and deep learning approaches on curated bioactivity data from 30 macromolecular targets for their performance on activity cliff compounds. While all methods struggled in the presence of activity cliffs, machine learning approaches based on molecular descriptors outperformed more complex deep learning methods. Our findings highlight large case-by-case differences in performance, advocating for (a) the inclusion of dedicated "activity-cliff-centered" metrics during model development and evaluation and (b) the development of novel algorithms to better predict the properties of activity cliffs. To this end, the methods, metrics, and results of this study have been encapsulated into an open-access benchmarking platform named MoleculeACE (Activity Cliff Estimation, available on GitHub at: https://github.com/molML/MoleculeACE). MoleculeACE is designed to steer the community toward addressing the pressing but overlooked limitation of molecular machine learning models posed by activity cliffs.

Pharmacophore Synergism in Diverse Scaffold Clinches in Aurora Kinase B

Aurora kinase B (AKB) is a crucial signaling kinase with an important role in cell division. Therefore, inhibition of AKB is an attractive approach to the treatment of cancer. In the present work, extensive quantitative structure-activity relationships (QSAR) analysis has been performed using a set of 561 structurally diverse aurora kinase B inhibitors. The Organization for Economic Cooperation and Development (OECD) guidelines were used to develop a QSAR model that has high statistical performance (R²_tr = 0.815, Q²_LMO = 0.808, R²_ex = 0.814, CCC_ex = 0.899). The seven-variable-based newly developed QSAR model has an excellent balance of external predictive ability (Predictive QSAR) and mechanistic interpretation (Mechanistic QSAR). The QSAR analysis successfully identifies not only the visible pharmacophoric features but also the hidden features. The analysis indicates that the lipophilic and polar groups-especially the H-bond capable groups-must be present at a specific distance from each other. Moreover, the ring nitrogen and ring carbon atoms play important roles in determining the inhibitory activity for AKB. The analysis effectively captures reported as well as unreported pharmacophoric features. The results of the present analysis are also supported by the reported crystal structures of inhibitors bound to AKB.

Predicting the Bioconcentration Factor in Fish from Molecular Structures

The bioconcentration factor (BCF) is one of the metrics used to evaluate the potential of a substance to bioaccumulate into aquatic organisms. In this work, linear and non-linear regression QSARs were developed for the prediction of log BCF using different computational approaches, and starting from a large and structurally heterogeneous dataset. The new MLR-OLS and ANN regression models have good fitting with R2 values of 0.62 and 0.70, respectively, and comparable external predictivity with R2ext 0.64 and 0.65 (RMSEext of 0.78 and 0.76), respectively. Furthermore, linear and non-linear classification models were developed using the regulatory threshold BCF >2000. A class balanced subset was used to develop classification models which were applied to chemicals not used to create the QSARs. These classification models are characterized by external and internal accuracy up to 84% and 90%, respectively, and sensitivity and specificity up to 90% and 80%, respectively. QSARs presented in this work are validated according to regulatory requirements and their quality is in line with other tools available for the same endpoint and dataset, with the advantage of low complexity and easy application through the software QSAR-ME Profiler. These QSARs can be used as alternatives for, or in combination with, existing models to support bioaccumulation assessment procedures.

Investigation of [3H]diazepam derivatives as allosteric modulators of GABAA receptor α1β2γ2 subtypes: combination of molecular docking/dynamic simulations, pharmacokinetics/drug-likeness prediction, and QSAR analysis

In this paper, a data set of [³H] diazepam derivatives was analyzed using various computational methods: molecular docking/dynamic simulations, and QSAR analysis. The main aims of these studies are to understand the binding mechanisms by which benzodiazepines allosterically modulate GABA_A receptor α₁β₂γ₂ subtypes, from inducing neuronal inhibition at lower doses to the anesthetic effect at higher doses, and also, to define the structural requirements that contribute to improving the response of GABA_A/α₁β₂γ₂ receptor to benzodiazepine drugs. The results of the molecular docking study allowed selecting Ro12-6377 and proflazepam as the best modulators for the four binding sites simultaneously. Subsequently, the stability of the selected complexes was investigated by performing molecular dynamics simulation. The latter confirmed the features of both modulators to exert direct effects on the chloride-channel lining residues. Pharmacokinetics and drug-likeness profile were assessed through in silico tool. Furthermore, a QSAR analysis was conducted using an improved vemolecular dynamics simulations proposed byrsion of PLS regression. The goodness of fit and the predictive power of the resulting PLS model were estimated according to internal and external validation parameters: R² = 0.632, R²_adj = 0.584, F = 12.806; p-value = 6.2050e − 07, Q²_loo = 0.639, and Q²_F3 = 0.813. Clearly, the obtained results ensure the predictive ability of the developed QSAR model for the design of new high-potency benzodiazepine drugs.

QSAR, Molecular Docking, MD Simulation and MMGBSA Calculations Approaches to Recognize Concealed Pharmacophoric Features Requisite for the Optimization of ALK Tyrosine Kinase Inhibitors as Anticancer Leads

ALK tyrosine kinase ALK TK is an important target in the development of anticancer drugs. In the present work, we have performed a QSAR analysis on a dataset of 224 molecules in order to quickly predict anticancer activity on query compounds. Double cross validation assigns an upward plunge to the genetic algorithm−multi linear regression (GA-MLR) based on robust univariate and multivariate QSAR models with high statistical performance reflected in various parameters like, fitting parameters; R2 = 0.69−0.87, F = 403.46−292.11, etc., internal validation parameters; Q2LOO = 0.69−0.86, Q2LMO = 0.69−0.86, CCCcv = 0.82−0.93, etc., or external validation parameters Q2F1 = 0.64−0.82, Q2F2 = 0.63−0.82, Q2F3 = 0.65−0.81, R2ext = 0.65−0.83 including RMSEtr < RMSEcv. The present QSAR evaluation successfully identified certain distinct structural features responsible for ALK TK inhibitory potency, such as planar Nitrogen within four bonds from the Nitrogen atom, Fluorine atom within five bonds beside the non-ring Oxygen atom, lipophilic atoms within two bonds from the ring Carbon atoms. Molecular docking, MD simulation, and MMGBSA computation results are in consensus with and complementary to the QSAR evaluations. As a result, the current study assists medicinal chemists in prioritizing compounds for experimental detection of anticancer activity, as well as their optimization towards more potent ALK tyrosine kinase inhibitor.

QSAR Evaluations to Unravel the Structural Features in Lysine-Specific Histone Demethylase 1A Inhibitors for Novel Anticancer Lead Development Supported by Molecular Docking, MD Simulation and MMGBSA

Using 84 structurally diverse and experimentally validated LSD1/KDM1A inhibitors, quantitative structure–activity relationship (QSAR) models were built by OECD requirements. In the QSAR analysis, certainly significant and understated pharmacophoric features were identified as critical for LSD1 inhibition, such as a ring Carbon atom with exactly six bonds from a Nitrogen atom, partial charges of lipophilic atoms within eight bonds from a ring Sulphur atom, a non-ring Oxygen atom exactly nine bonds from the amide Nitrogen, etc. The genetic algorithm–multi-linear regression (GA-MLR) and double cross-validation criteria were used to create robust QSAR models with high predictability. In this study, two QSAR models were developed, with fitting parameters like R² = 0.83–0.81, F = 61.22–67.96, internal validation parameters such as Q²_LOO = 0.79–0.77, Q²_LMO = 0.78–0.76, CCC_cv = 0.89–0.88, and external validation parameters such as, R2ext = 0.82 and CCCex = 0.90. In terms of mechanistic interpretation and statistical analysis, both QSAR models are well-balanced. Furthermore, utilizing the pharmacophoric features revealed by QSAR modelling, molecular docking experiments corroborated with the most active compound’s binding to the LSD1 receptor. The docking results are then refined using Molecular dynamic simulation and MMGBSA analysis. As a consequence, the findings of the study can be used to produce LSD1/KDM1A inhibitors as anticancer leads.

Identification of Potent Aldose Reductase Inhibitors as Antidiabetic (Anti-hyperglycemic) agents using QSAR Based Virtual Screening, Molecular Docking, MD Simulation and MMGBSA Approaches

The aldose reductase (AR) enzyme is an important target enzyme in the development of therapeutics against hyperglycaemia induced health complications such as retinopathy, etc. In the present study, a quantitative structure activity relationship (QSAR) evaluation of a dataset of 226 reported AR inhibitor (ARi) molecules is performed using a genetic algorithm – multi linear regression (GA-MLR) technique. Multi-criteria decision making (MCDM) analysis furnished two five variables based QSAR models with acceptably high performance reflected in various statistical parameters such as, R² = 0.79–0.80, Q²_LOO = 0.78–0.79, Q²_LMO = 0.78–0.79. The QSAR model analysis revealed some of the molecular features that play crucial role in deciding inhibitory potency of the molecule against AR such as; hydrophobic Nitrogen within 2 Å of the center of mass of the molecule, non-ring Carbon separated by three and four bonds from hydrogen bond donor atoms, number of sp2 hybridized Oxygen separated by four bonds from sp2 hybridized Carbon atoms, etc. 14 in silico generated hits, using a compound 18 (a most potent ARi from present dataset with pIC₅₀ = 8.04 M) as a template, on QSAR based virtual screening (QSAR-VS) furnished a scaffold 5 with better ARi activity (pIC₅₀ = 8.05 M) than template compound 18. Furthermore, molecular docking of compound 18 (Docking Score = –7.91 kcal/mol) and scaffold 5 (Docking Score = –8.08 kcal/mol) against AR, divulged that they both occupy the specific pocket(s) in AR receptor binding sites through hydrogen bonding and hydrophobic interactions. Molecular dynamic simulation (MDS) and MMGBSA studies right back the docking results by revealing the fact that binding site residues interact with scaffold 5 and compound 18 to produce a stable complex similar to co-crystallized ligand's conformation. The QSAR analysis, molecular docking, and MDS results are all in agreement and complementary. QSAR-VS successfully identified a more potent novel ARi and can be used in the development of therapeutic agents to treat diabetes.

Target Specific Inhibition of Protein Tyrosine Kinase in Conjunction With Cancer and SARS-COV-2 by Olive Nutraceuticals

The fact that viruses cause human cancer dates back to the early 1980s. By reprogramming cellular signaling pathways, viruses encoded protein that can regulate altered control of cell cycle events. Viruses can interact with a superfamily of membrane bound protein, receptor tyrosine kinase to modulate their activity in order to increase virus entrance into cells and promotion of viral replication within the host. Therefore, our study aimed at screening of inhibitors of tyrosine kinase using natural compounds from olive. Protein tyrosine kinase (PTK) is an important factor for cancer progression and can be linked to coronavirus. It is evident that over expression of Protein tyrosine kinase (PTK) enhance viral endocytosis and proliferation and the use of tyrosine kinase inhibitors reduced the period of infection period. Functional network studies were carried out using two major PTKs viz. Anaplastic lymphoma kinase (ALK) and B-lymphocytic kinase (BTK). They are associated with coronavirus in regulation of cell signaling proteins for cellular processes. We virtually screened for 161 library of natural compounds from olive found overexpressed in ALK and BTK in metastatic as well as virus host cells. We have employed both ligand and target-based approach for drug designing by high throughput screening using Multilinear regression model based QSAR and docking. The QSAR based virtual screening of 161 olive nutraceutical compounds has successfully identified certain new hit; Wedelosin, in which, the descriptor rsa (ratio of molecular surface area to the solvent accessible surface area) plays crucial role in deciding Wedelosin’s inhibitory potency. The best-docked olive nutraceuticals further investigated for the stability and effectivity of the BTK and ALK during in 150 ns molecular dynamics and simulation. Post simulation analysis and binding energy estimation in MMGBSA further revealed the intensive potential of the olive nutraceuticals in PTK inhibition. This study is therefore expected to widen the use of nutraceuticals from olive in cancer as well as SARS-CoV2 alternative therapy.

QSAR based virtual screening derived identification of a novel hit as a SARS CoV-229E 3CLpro Inhibitor: GA-MLR QSAR modeling supported by molecular Docking, molecular dynamics simulation and MMGBSA calculation approaches

Congruous coronavirus drug targets and analogous lead molecules must be identified as quickly as possible to produce antiviral therapeutics against human coronavirus (HCoV SARS 3CLpro) infections. In the present communication, we bear recognized a HIT candidate for HCoV SARS 3CLpro inhibition. Four Parametric GA-MLR primarily based QSAR model (R2:0.84, R2adj:0.82, Q2loo: 0.78) was once promoted using a dataset over 37 structurally diverse molecules along QSAR based virtual screening (QSAR-VS), molecular docking (MD) then molecular dynamic simulation (MDS) analysis and MMGBSA calculations. The QSAR-based virtual screening was utilized to find novel lead molecules from an in-house database of 100 molecules. The QSAR-vS successfully offered a hit molecule with an improved _PEC₅₀ value from 5.88 to 6.08. The benzene ring, phenyl ring, amide oxygen and nitrogen, and other important pharmacophoric sites are revealed via MD and MDS studies. Ile164, Pro188, Leu190, Thr25, His41, Asn46, Thr47, Ser49, Asn189, Gln191, Thr47, and Asn141 are among the key amino acid residues in the S1 and S2 pocket. A stable complex of a lead molecule with the HCoV SARS 3CLpro was discovered using MDS. MM-GBSA calculations resulted from MD simulation results well supported with the binding energies calculated from the docking results. The results of this study can be exploited to develop a novel antiviral target, such as an HCoV SARS 3CLpro Inhibitor.

QSAR, pharmacophore modeling and molecular docking studies to identify structural alerts for some nitrogen heterocycles as dual inhibitor of telomerase reverse transcriptase and human telomeric G-quadruplex DNA

Background

Telomerase reverse transcriptase (TERT) and human telomeric G-quadruplex DNA are amongst the favorable target for researchers to discover novel and more effective anticancer agents. To understand and elucidate structure activity relationship and mechanism of inhibition of telomerase reverse transcriptase (TERT) and human telomeric G-quadruplex DNA, a QSAR modeling and molecular docking were conducted.

Results

Two robust QSAR model were obtained which consist of full set QSAR model (R2: 0.8174, CCCtr: 0.8995, Q2loo: 0.7881, Q2LMO: 0.7814) and divided set QSAR model (R2: 0.8217, CCCtr: 0.9021, Q2loo: 0.7886, Q2LMO: 0.7783, Q2-F1: 0.7078, Q2-F2: 0.6865, Q2-F3: 0.7346) for envisaging the inhibitory activity of telomerase reverse transcriptase (TERT) and human telomeric G-quadruplex DNA. The analysis reveals that carbon atom exactly at 3 bonds from aromatic carbon atom, nitrogen atom exactly at six bonds from planer nitrogen atom, aromatic carbon atom within 2 A0 from the center of mass of molecule and occurrence of element hydrogen within 2 A0 from donar atom are the key pharmacophoric features important for dual inhibition of TERT and human telomeric G-quadruplex DNA. To validate this analysis, pharmacophore modeling and the molecular docking is performed. Molecular docking analysis support QSAR analysis and revealed that, dual inhibition of TERT and human telomeric DNA is mainly contributed from hydrophobic and hydrogen bonding interactions.

Conclusion

The findings of molecular docking, pharmacophore modelling, and QSAR are all consistent and in strong agreement. The validated QSAR analyses can detect structural alerts, pharmacophore modelling can classify a molecule's consensus pharmacophore involving hydrophobic and acceptor regions, whereas docking analysis can reveal the mechanism of dual inhibition of telomerase reverse transcriptase (TERT) and human telomeric G-quadruplex DNA. The combination of QSAR, pharmacophore modeling and molecular docking may be useful for the future drug design of dual inhibitors to combat the devastating issue of resistance.

Graphical abstract

Identification of concealed structural alerts using QSTR modeling for Pseudokirchneriella subcapitata

In the present work, QSTR modeling was conducted for microalga Pseudokirchneriella subcapitata using a data set of 271 molecules belonging to different types of chemical classes for the prediction of EC₅₀ for 72 hr based assays. The balanced QSTR model encompasses seven easily interpretable molecular descriptors and possesses statistical robustness with high predictive ability. This Genetic Algorithm Multi-linear regression (GA-MLR) model was subjected to internal validation, Y-randomization test, applicability domain analysis, and external validation as per the recommended OECD guidelines. The newly developed model fulfilled the threshold values for more than 20 recommended validation parameters including R² = 0.72, Q²_LOO = 0.70, etc. The developed QSTR model was successful in identifying the type of hybridization or specific type of atoms of previously reported and newer structural alerts. Thus, the model could be useful for data gap filling and expanding mechanistic interpretation of toxicity for different chemicals.

Quantitative Structure-Activity Relationship Evaluation of MDA-MB-231 Cell Anti-Proliferative Leads

In the present endeavor, for the dataset of 219 in vitro MDA-MB-231 TNBC cell antagonists, a (QSAR) quantitative structure–activity relationships model has been carried out. The quantitative and explicative assessments were performed to identify inconspicuous yet pre-eminent structural features that govern the anti-tumor activity of these compounds. GA-MLR (genetic algorithm multi-linear regression) methodology was employed to build statistically robust and highly predictive multiple QSAR models, abiding by the OECD guidelines. Thoroughly validated QSAR models attained values for various statistical parameters well above the threshold values (i.e., R² = 0.79, Q²_LOO = 0.77, Q²_LMO = 0.76–0.77, Q²-Fⁿ = 0.72–0.76). Both de novo QSAR models have a sound balance of descriptive and statistical approaches. Decidedly, these QSAR models are serviceable in the development of MDA-MB-231 TNBC cell antagonists.

Mechanistic and Predictive QSAR Analysis of Diverse Molecules to Capture Salient and Hidden Pharmacophores for Anti-Thrombotic Activity

Thrombosis is a life-threatening disease with a high mortality rate in many countries. Even though anti-thrombotic drugs are available, their serious side effects compel the search for safer drugs. In search of a safer anti-thrombotic drug, Quantitative Structure-Activity Relationship (QSAR) could be useful to identify crucial pharmacophoric features. The present work is based on a larger data set comprising 1121 diverse compounds to develop a QSAR model having a balance of acceptable predictive ability (Predictive QSAR) and mechanistic interpretation (Mechanistic QSAR). The developed six parametric model fulfils the recommended values for internal and external validation along with Y-randomization parameters such as R²_tr = 0.831, Q²_LMO = 0.828, R²_ex = 0.783. The present analysis reveals that anti-thrombotic activity is found to be correlated with concealed structural traits such as positively charged ring carbon atoms, specific combination of aromatic Nitrogen and sp2-hybridized carbon atoms, etc. Thus, the model captured reported as well as novel pharmacophoric features. The results of QSAR analysis are further vindicated by reported crystal structures of compounds with factor Xa. The analysis led to the identification of useful novel pharmacophoric features, which could be used for future optimization of lead compounds.

QSAR and Pharmacophore Modeling of Nitrogen Heterocycles as Potent Human N-Myristoyltransferase (Hs-NMT) Inhibitors

N-myristoyltransferase (NMT) is an important eukaryotic monomeric enzyme which has emerged as an attractive target for developing a drug for cancer, leishmaniasis, ischemia-reperfusion injury, malaria, inflammation, etc. In the present work, statistically robust machine leaning models (QSAR (Quantitative Structure–Activity Relationship) approach) for Human NMT (Hs-NMT) inhibitory has been performed for a dataset of 309 Nitrogen heterocycles screened for NMT inhibitory activity. Hundreds of QSAR models were derived. Of these, the model 1 and 2 were chosen as they not only fulfil the recommended values for a good number of validation parameters (e.g., R² = 0.77–0.79, Q²_LMO = 0.75–0.76, CCC_ex = 0.86–0.87, Q²-F³ = 0.74–0.76, etc.) but also provide useful insights into the structural features that sway the Hs-NMT inhibitory activity of Nitrogen heterocycles. That is, they have an acceptable equipoise of descriptive and predictive qualities as per Organisation for Economic Co-operation and Development (OECD) guidelines. The developed QSAR models identified a good number of molecular descriptors like solvent accessible surface area of all atoms having specific partial charge, absolute surface area of Carbon atoms, etc. as important features to be considered in future optimizations. In addition, pharmacophore modeling has been performed to get additional insight into the pharmacophoric features, which provided additional results.

Structure features of peptide-type SARS-CoV main protease inhibitors: Quantitative structure activity relationship study

In the present work, an extensive QSAR (Quantitative Structure Activity Relationships) analysis of a series of peptide-type SARS-CoV main protease (MPro) inhibitors following the OECD guidelines has been accomplished. The analysis was aimed to identify salient and concealed structural features that govern the MPro inhibitory activity of peptide-type compounds. The QSAR analysis is based on a dataset of sixty-two peptide-type compounds which resulted in the generation of statistically robust and highly predictive multiple models. All the developed models were validated extensively and satisfy the threshold values for many statistical parameters (for e.g. R² ​= ​0.80-0.82, Q² _loo ​= ​0.74-0.77, Q ² _LMO  ​= ​0.66-0.67). The developed QSAR models identified number of sp² hybridized Oxygen atoms within seven bonds from aromatic Carbon atoms, the presence of Carbon and Nitrogen atoms at a topological distance of 3 and other interrelations of atom pairs as important pharmacophoric features. Hence, the present QSAR models have a good balance of Qualitative (Descriptive QSARs) and Quantitative (Predictive QSARs) approaches, therefore useful for future modifications of peptide-type compounds for anti- SARS-CoV activity.

Prediction of the Partition Coefficient between Adipose Tissue and Blood for Environmental Chemicals: From Single QSAR Models to an Integrated Approach

The adipose tissue:blood partition coefficient is a key-endpoint to predict the pharmacokinetics of chemicals in humans and animals, since other organ:blood affinities can be estimated as a function of this parameter. We performed a search in the literature to select all the available rat in vivo data. This approach resulted into two improvements to existing models: a homogeneous definition of the endpoint and an expanded data collection. The resulting dataset was used to develop QSAR models as a function of linear and non-linear algorithms. Several applicability domain definitions were assessed and the definition corresponding to a good balance between performance and coverage was retained. We assessed the pertinence of combining single models into integrated approaches to increase the accuracy in predictions. The best integrated model outperformed the single models and it was characterized by an external mean absolute error (MAE) equal to 0.26, while preserving an adequate coverage (84 %). This performance is comparable to experimental variability and it highlights the pertinence of the integrated model.

Comparative study between deep learning and QSAR classifications for TNBC inhibitors and novel GPCR agonist discovery

Machine learning is a well-known approach for virtual screening. Recently, deep learning, a machine learning algorithm in artificial neural networks, has been applied to the advancement of precision medicine and drug discovery. In this study, we performed comparative studies between deep neural networks (DNN) and other ligand-based virtual screening (LBVS) methods to demonstrate that DNN and random forest (RF) were superior in hit prediction efficiency. By using DNN, several triple-negative breast cancer (TNBC) inhibitors were identified as potent hits from a screening of an in-house database of 165,000 compounds. In broadening the application of this method, we harnessed the predictive properties of trained model in the discovery of G protein-coupled receptor (GPCR) agonist, by which computational structure-based design of molecules could be greatly hindered by lack of structural information. Notably, a potent (~ 500 nM) mu-opioid receptor (MOR) agonist was identified as a hit from a small-size training set of 63 compounds. Our results show that DNN could be an efficient module in hit prediction and provide experimental evidence that machine learning could identify potent hits in silico from a limited training set.

Extending the identification of structural features responsible for anti-SARS-CoV activity of peptide-type compounds using QSAR modelling

A quantitative structure-activity relationship (QSAR) model was built from a dataset of 54 peptide-type compounds as SARS-CoV inhibitors. The analysis was executed to identify prominent and hidden structural features that govern anti-SARS-CoV activity. The QSAR model was derived from the genetic algorithm-multi-linear regression (GA-MLR) methodology. This resulted in the generation of a statistically robust and highly predictive model. In addition, it satisfied the OECD principles for QSAR validation. The model was validated thoroughly and fulfilled the threshold values of a battery of statistical parameters (e.g. r ² = 0.87, Q ² _loo = 0.82). The derived model is successful in identifying many atom-pairs as important structural features that govern the anti-SARS-CoV activity of peptide-type compounds. The newly developed model has a good balance of descriptive and statistical approaches. Consequently, the present work is useful for future modifications of peptide-type compounds for SARS-CoV and SARS-CoV-2 activity.

Thermal Conductivity Estimation of Diverse Liquid Aliphatic Oxygen-Containing Organic Compounds Using the Quantitative Structure-Property Relationship Method

Thermal conductivity is an essential thermodynamic data in chemical engineering applications. Liquid aliphatic oxygen-containing organic compounds are important organic intermediates and raw materials. As a result, estimating thermal conductivity of liquid aliphatic oxygen-containing organic compounds is of significance in industry production. In this study, the genetic function approximation method was applied to screen descriptors and develop a 6-descriptor linear quantitative structure-property relationship model. The entire data set of these compounds covering 1064 thermal conductivity values was divided into 694-member training set, 298-member test set, and 72-member prediction set. The average absolute relative deviation of the training set, test set, and prediction set were 4.14, 4.41, and 4.16%, respectively. Model validation and Y-randomization test proved that the developed model has goodness-of-fit, predictive power, and robustness. In addition, the applicability domain of the developed model was visualized by the Williams plot. This study can provide a convenient method to estimate the thermal conductivity for researchers in chemical engineering production.

Multivariate image analysis-quantitative structure-retention relationship study of polychlorinated biphenyls using partial least squares and radial basis function neural networks

Polychlorinated biphenyls belong to a class of hazardous and environmental pollutants. Gas chromatography separation and experimental relative retention time evaluation of these compounds on a poly (94% methyl/5% phenyl) silicone-based capillary non-bonded and cross-linked column are time consuming and expensive. In this study, relative retention times were estimated using two-dimensional images of molecules based on a newly implemented rapid and simple quantitative structure retention relationship methodology. The resulting descriptors were subjected to partial least square and principal component-radial basis function neural networks as linear and nonlinear models, respectively, to attain a statistical explanation of the retention behavior of the molecules. The high numerical values of correlation coefficients and low root mean square errors in the case of the partial least square model, confirm the supremacy of this model as well as the linear dependency of images of molecules to their relative retention times. Evaluation of the best correlation model performed using internal and external tests and its good applicability domain was checked using a distance to the model in the X-Space plot. This study provides a practical and effective method for analytical chemists working with chromatographic platforms to improve predictive confidence of studies that seek to identify unknown molecules or impurities.

Exploring the Potential of Spherical Harmonics and PCVM for Compounds Activity Prediction

Biologically active chemical compounds may provide remedies for several diseases. Meanwhile, Machine Learning techniques applied to Drug Discovery, which are cheaper and faster than wet-lab experiments, have the capability to more effectively identify molecules with the expected pharmacological activity. Therefore, it is urgent and essential to develop more representative descriptors and reliable classification methods to accurately predict molecular activity. In this paper, we investigate the potential of a novel representation based on Spherical Harmonics fed into Probabilistic Classification Vector Machines classifier, namely SHPCVM, to compound the activity prediction task. We make use of representation learning to acquire the features which describe the molecules as precise as possible. To verify the performance of SHPCVM ten-fold cross-validation tests are performed on twenty-one G protein-coupled receptors (GPCRs). Experimental outcomes (accuracy of 0.86) assessed by the classification accuracy, precision, recall, Matthews’ Correlation Coefficient and Cohen’s kappa reveal that using our Spherical Harmonics-based representation which is relatively short and Probabilistic Classification Vector Machines can achieve very satisfactory performance results for GPCRs.

Predictive models in ecotoxicology: Bridging the gap between scientific progress and regulatory applicability-Remarks and research needs

This paper concludes a special series of 7 articles (4 on toxicokinetic-toxicodynamic [TK-TD] models and 3 on quantitative structure-activity relationship [QSAR] models) published in previous issues of Integrated Environmental Assessment and Management (IEAM). The present paper summarizes the special series articles and highlights their contribution to the topic of increasing the regulatory applicability of effect models. For both TK-TD and QSAR approaches, we then describe the main research needs. The use of TK-TD models for describing sublethal effects must be better developed, particularly through the improvement of the dynamic energy budget (DEBtox) approach. The potential of TK-TD models for moving from lower (molecular) to higher (population) hierarchical levels is highlighted as a promising research line. Some relevant issues to improve the acceptance of QSAR models at the regulatory level are also described, such as increased transparency of the performance assessment and of the modeling algorithms, model documentation, relevance of the chosen target for regulatory needs, and improved mechanistic interpretability. Integr Environ Assess Manag 2019;00:000-000. © 2019 SETAC.