Showing papers in "Sar and Qsar in Environmental Research in 2019"
TL;DR: The predictive potential of QSAR models of FAK inhibitors was explored by applying the index of ideality of correlation (IIC), which is a new criterion for the prediction of the potential for quantitative structure–property activity relationships (QSPRs/QSARs).
Abstract: Quantitative structure-activity relationship (QSAR) modelling of 55 focal adhesion kinase (FAK) (EC 2.7.10.2) inhibitors of triazinic nature was performed using the Monte Carlo method. The ...
58 citations
TL;DR: The current research describes the development of hybrid optimal descriptors-based quantitative structure–activity relationship (QSAR) models intended for a set of 62 FBPase inhibitors with the Monte Carlo method.
Abstract: Fructose-1,6-bisphosphatase (FBPase) is an enzyme important for regulation of gluconeogenesis, which is a major process in the liver responsible for glucose production. Inhibition of FBPase enzyme causing blockage of the gluconeogenesis process represents a newer scheme in the progress of anti-diabetic drugs. The current research describes the development of hybrid optimal descriptors-based quantitative structure-activity relationship (QSAR) models intended for a set of 62 FBPase inhibitors with the Monte Carlo method. The molecular structures were expressed by the simplified molecular input line entry system (SMILES) notation. Three splits were prepared by random division of the molecules into training set, calibration set and validation set. Statistical parameters obtained from QSAR modelling were good for various designed splits. The best QSAR model showed the following parameters: the values of r2 for calibration set and validation set of the best model were 0.6837 and 0.8623 and of Q2 were 0.6114 and 0.8036, respectively. Based on the results obtained for correlation weights, different structural attributes were described as promoter of the endpoint. Further, these structural attributes were used in designing of new FBPase inhibitors and a molecular docking study was completed for the determination of interactions of the designed molecules with the enzyme.
47 citations
TL;DR: Quantitative structure–activity relationship (QSAR) modelling is an essential technique in drug design and development and to study the aspect of DGAT1 inhibitors, Monte-Carlo method-based QSAR was developed for 197 DGat1 inhibitors.
Abstract: Diabetes, obesity and other diseases related to metabolism are worldwide health problems. These syndromes can be well treated when a particular enzyme-based therapy is developed. Diacylglycerol acyltransferase (DGAT; EC 2.3.1.20) is a microsomal enzyme which is responsible for the synthesis of triglycerides from 1,2-diacylglycerol by catalyzing the acyl-CoA-dependent acylation. The obesity and type-II diabetes can be checked by the inhibition of DGAT1 enzyme. Quantitative structure-activity relationship (QSAR) modelling is an essential technique in drug design and development. To study the aspect of DGAT1 inhibitors, Monte-Carlo method-based QSAR was developed for 197 DGAT1 inhibitors. QSAR models were derived by using the optimal descriptor based on SMILES notation. Different statistical parameters including the novel index of ideality of correlation were applied to validate the generated QSAR models. Four random splits were prepared from the data set. The statistical criteria r2 = 0.8129, CCC = 0.8979 and Q2 = 0.7962 of the validation set of split 1 were the best; therefore, the developed QSAR model of split 1 was decided to be the leading model. The molecular fragments, which were promoter of endpoint increase or decrease were also determined. Thirteen new DGAT1 inhibitors were designed from the lead compound DGAT011.
41 citations
TL;DR: This work designed SmilesNet, a recurrent neural network taking SMILES as the only input and integrated the two networks into C-Tox network to make the final classification, which match or even outperform the current state of the art.
Abstract: Assessing chemical toxicity is a multidisciplinary process, traditionally involving in vivo, in vitro and in silico tests. Currently, toxicological goal is to reduce new tests on chemicals, exploiting all information yet available. Recent advancements in machine learning and deep neural networks allow computers to automatically mine patterns and learn from data. This technology, applied to (Q)SAR model development, leads to discover by learning the structural-chemical-biological relationships and the emergent properties. Starting from Toxception, a deep neural network predicting activity from the chemical graph image, we designed SmilesNet, a recurrent neural network taking SMILES as the only input. We then integrated the two networks into C-Tox network to make the final classification. Results of our networks, trained on a ~20K molecule dataset with Ames test experimental values, match or even outperform the current state of the art. We also extract knowledge from the networks and compare it with the available mutagenic structural alerts. The advantage over traditional QSAR modelling is that our models automatically extract the features without using descriptors. Nevertheless, the model is successful if large numbers of examples are provided and computation is more complex than in classical methods.
29 citations
TL;DR: The developed PHASE-based common six-point pharmacophore hypothesis (AADHPR_1) showed the necessity of two hydrogen bond acceptor features, one hydrogen bond donor feature, one hydrophobic group feature, two positively ionizable and one aromatic ring feature for further designing, and developed best 3D-QSAR models with high regression coefficients.
Abstract: The pathogenic Ebola virus (EBOV) causes a potential health risk and global spread. To date, few drugs are available for the treatment of Ebola virus disease (EVD) that allow researchers to use computational methods for designing potential drugs. The developed PHASE-based common six-point pharmacophore hypothesis (AADHPR_1) showed the necessity of two hydrogen bond acceptor features, one hydrogen bond donor feature, one hydrophobic group feature, one positively ionizable and one aromatic ring feature for further designing. We developed best 3D-QSAR models with high regression coefficients for the training (r2>0.82) and test (Q2>0.5) sets for both atoms-based and field-based 3D-QSAR models. The molecule 1A-4 (docking score = -4.711 kcal/mol) was obtained as best docked (SP mode) on Ebola virus envelope glycoprotein (PDB ID-3CSY) as compared with the standards oseltamivir (docking score = -4.39 kcal/mol) and zanamivir (docking score = -3.392 kcal/mol). The obtained ZINC hit ZINC58935541 showed a good docking score of -4.892 kcal/mol. The ZINC58935541 molecule also showed a strong binding affinity towards the receptor cavity of Ebola virus envelope glycoprotein when simulated for 1.2 ns. The good QikProp parameters reflect the fact that this molecule, upon optimization into a lead, might become a good candidate for the treatment of EVD.
22 citations
TL;DR: In the future, the data gap for other chemicals within the application domain on their chronic toxicity for D. magna and P. subcapitata could be filled using the models developed here, and the obtained optimum models had high accuracy, sensitivity and specificity.
Abstract: Both the acute toxicity and chronic toxicity data on aquatic organisms are indispensable parameters in the ecological risk assessment priority chemical screening process (e.g. persistent, bioaccumulative and toxic chemicals). However, most of the present modelling actions are focused on developing predictive models for the acute toxicity of chemicals to aquatic organisms. As regards chronic aquatic toxicity, considerable work is needed. The major objective of the present study was to construct in silico models for predicting chronic toxicity data for Daphnia magna and Pseudokirchneriella subcapitata. In the modelling, a set of chronic toxicity data was collected for D. magna (21 days no observed effect concentration (NOEC)) and P. subcapitata (72 h NOEC), respectively. Then, binary classification models were developed for D. magna and P. subcapitata by employing the k-nearest neighbour method (k-NN). The model assessment results indicated that the obtained optimum models had high accuracy, sensitivity and specificity. The model application domain was characterized by the Euclidean distance-based method. In the future, the data gap for other chemicals within the application domain on their chronic toxicity for D. magna and P. subcapitata could be filled using the models developed here.
22 citations
TL;DR: Robust consensus quantitative structure-activity relationship (QSAR) models developed from 334 organic chemicals covering a wide chemical domain are provided for the prediction of effective concentrations of chemicals for 50% and 10% inhibition of algal growth.
Abstract: The present study provides robust consensus quantitative structure-activity relationship (QSAR) models developed from 334 organic chemicals covering a wide chemical domain for the prediction of effective concentrations of chemicals for 50% and 10% inhibition of algal growth. Only 2D descriptors with definite physicochemical meaning were employed for QSAR model building, whereas development, validation and interpretation were achieved following the strict Organization for Economic Co-operation and Development (OECD) recommended guidelines. Genetic algorithm along with stepwise approach was used in feature selection while the final QSAR models were derived using partial least squares regression technique. The applicability domain of the developed models was also checked. The obtained consensus models were then used to predict 64 organic chemicals having no definite observed responses while the confidence of predictions was checked by the 'prediction reliability indicator' tool. The developed models should be applicable for data gap filling in case of new or untested organic chemicals provided they fall within the domain of the model and can also be implemented to design safer alternatives to the environment.
22 citations
TL;DR: Structural requirements of phenyltetrazole derivatives for ABCG2 inhibition by combining classical QSAR, Bayesian classification modelling and molecular docking studies will guide the medicinal chemists to act faster in the drug discovery ofABCG2 inhibitors for the management of resistant breast cancer.
Abstract: ABCG2 is the principal ABC transporter involved in the multidrug resistance of breast cancer. Looking at the current demand in the development of ABCG2 inhibitors for the treatment of multidrug-res...
21 citations
TL;DR: The feasibility of calculating molecular descriptors from an amino acid sequence translated from DNA aptamer sequences to develop a QSAR model for the anti-influenza aptamers was demonstrated and the model is accurate and competes favourably with the existing model.
Abstract: Thousands of investigations on quantitative structure-activity/property relationships (QSARs/QSPRs) have been reported. However, few publications can be found that deal with QSARs for aptamers, because calculating two-dimensional and three-dimensional descriptors directly from aptamers (typically with 15-45 nucleotides) is difficult. This paper describes calculating molecular descriptors from amino acid sequences that are translated from DNA aptamer sequences with DNAMAN software, and developing QSAR models for the aptamers' binding affinity to the influenza virus. General regression neural network (GRNN) based on Parzen windows estimation was used to build the QSAR model by applying six molecular descriptors. The optimal spreading factor σ of Gaussian function of 0.3 was obtained with the circulation method. The correlation coefficients r from the GRNN model were 0.889 for the training set and 0.892 for the test set. Compared with the existing model for aptamers' binding affinity to the influenza virus, our model is accurate and competes favourably. The feasibility of calculating molecular descriptors from an amino acid sequence translated from DNA aptamer sequences to develop a QSAR model for the anti-influenza aptamers was demonstrated.
19 citations
TL;DR: The Index of Ideality of Correlation is a new criterion of the predictive potential for quantitative structure–property/activity relationships and has been applied to develop QSAR models for skin sensitization achieving good predictive potential.
Abstract: The Index of Ideality of Correlation (IIC) is a new criterion of the predictive potential for quantitative structure–property/activity relationships. The value of the IIC is a mathematical function sensitive to the value of the correlation coefficient and dispersion (expressed via mean absolute error). The IIC has been applied to develop QSAR models for skin sensitization achieving good predictive potential. The ‘ideal correlation’ is based on elementary fragments of simplified molecular input-line entry system (SMILES) and on the taking into account of the total numbers of nitrogen, oxygen, sulphur and phosphorus in the molecule.
18 citations
TL;DR: Predictive models of acute oral systemic toxicity representing a follow-up of the previous work in the framework of the NICEATM project include the update of original models through the addition of new data and an external validation of the models using a dataset relevant for the chemical industry context.
Abstract: We report predictive models of acute oral systemic toxicity representing a follow-up of our previous work in the framework of the NICEATM project. It includes the update of original models through ...
TL;DR: Although it is based on only simple structural parameters, the reliability of the new model is also higher than the complex QSAR model because the values of the root-mean-square deviation (RMSD) of –log (LD50) for the new and the outputs of the latestQSAR method are 0.342 and 0.377.
Abstract: A simple approach is introduced to assess the toxicity of nitroaromatic compounds in terms of an oral LD50 dose (50% lethal dose) for rats. Most of the presented Quantitative Structure-Activity Rel...
TL;DR: The results prove that the V4 transfer function significantly improves the performance of the original BDS and takes the lowest iterations and selects the fewest descriptors.
Abstract: An improved binary differential search (improved BDS) algorithm is proposed for QSAR classification of diverse series of antimicrobial compounds against Candida albicans inhibitors. The tra...
TL;DR: Regression-dependent quantitative structure–activity relationship (QSAR) strategies might be among the possible drug design methods to explore the essential structural features that would be valuable to find a suitable MMP-2 inhibitor.
Abstract: Matrix metalloproteinase-2 (MMP-2) is a lucrative therapeutic target as far as anticancer drug discovery is concerned. Overexpression of MMP-2 is found to facilitate tumour propagation through the involvement of vascular endothelial growth factor (VEGF). However, even after different techniques, finding a target-specific MMP-2 inhibitor with respectable pharmacodynamic properties is still a challenging task. Regression-dependent quantitative structure-activity relationship (QSAR) strategies might be among the possible drug design methods to explore the essential structural features that would be valuable to find a suitable MMP-2 inhibitor. In this paper, 72 molecules were explored using the PaDEL descriptors and stepwise multiple linear regression (S-MLR). The partial least squares (PLS) method was also used to create a viable statistical model with an acceptable metric related to these models. The final statistical models were formed with statistical parameters within acceptable range (r2 = 0.797, Q2 = 0.725 and r2pred = 0.643 for the MLR model, and r2 = 0.780, Q2 = 0.685 and r2pred = 0.666 for the PLS model). The models were analysed and compared with those already published on the same endpoint.
TL;DR: Whether models built on public data only have adequate performances when challenged to predict industrial compounds is analyzed, and a new BCF model has been built using ISIDA fragment descriptors, support vector regression and random forest machine-learning methods.
Abstract: The bioconcentration factor (BCF), a key parameter required by the REACH regulation, estimates the tendency for a xenobiotic to concentrate inside living organisms. In silico methods can be valid alternatives to costly data measurements. However, in the industrial context, these theoretical approaches may fail to predict BCF with reasonable accuracy. We analyzed whether models built on public data only have adequate performances when challenged to predict industrial compounds. A new set of 1129 compounds has been collected by merging publicly available datasets. Generative Topographic Mapping was employed to compare this chemical space with a set of new compounds issued from the industry. Some new chemotypes absent in the training set (such as siloxanes) have been detected. A new BCF model has been built using ISIDA (In SIlico design and Data Analysis) fragment descriptors, support vector regression and random forest machine-learning methods. It has been externally validated on: (i) collected data from the literature and (ii) industrial data. The latter also served as benchmark for the freely available tools VEGA, EPISuite, TEST, OPERA. New model performs (RMSE of 0.58 log BCF units) comparably to existing ones but benefits of an extended applicability, covering the industrial set chemical space (78% data coverage).
TL;DR: The 3D-stucture of the catalytic pocket of the Staphylococcus aureus MurD enzyme is prepared by homology modelling and the designed molecule D1-modelled protein complex had a stable conformation in response to the atomic flexibility and interaction, when subjected to MD simulation at 40 ns in aqueous solution.
Abstract: The ATP-dependent bacterial MurD enzyme catalyses the formation of the peptide bond between cytoplasmic intermediate UDP-N-acetylmuramoyl-L-alanine and D-glutamic acid. This is essential for bacterial cell wall peptidoglycan synthesis in both Gram-positive and Gram-negative bacteria. MurD is recognized as an important target for the development of new antibacterial agents. In the present study we prepared the 3D-stucture of the catalytic pocket of the Staphylococcus aureus MurD enzyme by homology modelling. Extra-precision docking, binding free energy calculation by the MM-GBSA approach and a 40 ns molecular dynamics (MD) simulation of 2-thioxothiazolidin-4-one based inhibitor $1 was carried out to elucidate its inhibition potential for the S. aureus MurD enzyme. Molecular docking results showed that Lys19, Gly147, Tyr148, Lys328, Thr330 and Phe431 residues are responsible for the inhibitor-protein complex stabilization. Binding free energy calculation revealed electrostatic solvation and van der Waals energy components as major contributors for the inhibitor binding. The inhibitor-modelled S. aureus protein complex had a stable conformation in response to the atomic flexibility and interaction, when subjected to MD simulation at 40 ns in aqueous solution. We designed some molecules as potent inhibitors of S. aureus MurD, and to validate the stability of the designed molecule D1-modelled protein complex we performed a 20 ns MD simulation. Results obtained from this study can be utilized for the design of potent S. aureus MurD inhibitors.
TL;DR: This work introduces a novel approach for epigenetic quantitative structure–activity relationship (QSAR) modelling using conformal prediction and discusses the development of models for 11 sets of inhibitors of histone deacetylases, which are one of the major epigenetic target families that have been screened.
Abstract: The growing interest in epigenetic probes and drug discovery, as revealed by several epigenetic drugs in clinical use or in the lineup of the drug development pipeline, is boosting the generation of screening data. In order to maximize the use of structure-activity relationships there is a clear need to develop robust and accurate models to understand the underlying structure-activity relationship. Similarly, accurate models should be able to guide the rational screening of compound libraries. Herein we introduce a novel approach for epigenetic quantitative structure-activity relationship (QSAR) modelling using conformal prediction. As a case study, we discuss the development of models for 11 sets of inhibitors of histone deacetylases (HDACs), which are one of the major epigenetic target families that have been screened. It was found that all derived models, for every HDAC endpoint and all three significance levels, are valid with respect to predictions for the external test sets as well as the internal validation of the corresponding training sets. Furthermore, the efficiencies for the predictions are above 80% for most data sets and above 90% for four data sets at different significant levels. The findings of this work encourage prospective applications of conformal prediction for other epigenetic target data sets.
TL;DR: The findings suggest that the selected models used to build different classification models for predicting the antimalarial activity against Plasmodium falciparum are robust and can be potentially useful for facilitating the discovery of antimalaria agents.
Abstract: The large collection of known and experimentally verified compounds from the ChEMBL database was used to build different classification models for predicting the antimalarial activity against Plasmodium falciparum. Four different machine learning methods, namely the support vector machine (SVM), random forest (RF), k-nearest neighbour (kNN) and XGBoost have been used for the development of models using the diverse antimalarial dataset from ChEMBL. A well-established feature selection framework was used to select the best subset from a larger pool of descriptors. Performance of the models was rigorously evaluated by evaluation of the applicability domain, Y-scrambling and AUC-ROC curve. Additionally, the predictive power of the models was also assessed using probability calibration and predictiveness curves. SVM and XGBoost showed the best performances, yielding an accuracy of ~85% on the independent test set. In term of probability prediction, SVM and XGBoost were well calibrated. Total gain (TG) from the predictiveness curve was more related to SVM (TG = 0.67) and XGBoost (TG = 0.75). These models also predict the high-affinity compounds from PubChem antimalarial bioassay (as external validation) with a high probability score. Our findings suggest that the selected models are robust and can be potentially useful for facilitating the discovery of antimalarial agents.
TL;DR: This work proposes the use of a hierarchical extreme learning machine (H-ELM) to make a classification of high-dimensional input data without demanding a dimension reduction process, which yields acceptable results.
Abstract: Apoptosis is a fundamental process controlling normal tissue homeostasis by regulating a balance between cell proliferation and death. Predicting the subcellular location of apoptosis proteins is v...
TL;DR: The results clearly reveal that the proposed TVBGSA method is useful for constructing reliable and robust QSARs for predicting antidiabetic activity of DPP-IV inhibitors prior to designing and experimental synthesizing of new DPP -IV inhibitors.
Abstract: Time-varying binary gravitational search algorithm (TVBGSA) is proposed for predicting antidiabetic activity of 134 dipeptidyl peptidase-IV (DPP-IV) inhibitors. To improve the performance of the bi...
TL;DR: In this paper, the authors used OpeRational ClassificAtion (ORCA) system for categorizing drug-drug interactions (DDIs) in the human body and achieved an average accuracy of 0.84.
Abstract: Simultaneous use of the drugs may lead to undesirable Drug-Drug Interactions (DDIs) in the human body. Many DDIs are associated with changes in drug metabolism that performed by Drug-Metabolizing Enzymes (DMEs). In this case, DDI manifests itself as a result of the effect of one drug on the biotransformation of other drug(s), its slowing down (in the case of inhibiting DME) or acceleration (in case of induction of DME), which leads to a change in the pharmacological effect of the drugs combination. We used OpeRational ClassificAtion (ORCA) system for categorizing DDIs. ORCA divides DDIs into five classes: contraindicated (class 1), provisionally contraindicated (class 2), conditional (class 3), minimal risk (class 4), no interaction (class 5). We collected a training set consisting of several thousands of drug pairs. Algorithm of PASS program was used for the first, second and third classes DDI prediction. Chemical descriptors called PoSMNA (Pairs of Substances Multilevel Neighbourhoods of Atoms) were developed and implemented in PASS software to describe in a machine-readable format drug substances pairs instead of the single molecules. The average accuracy of DDI class prediction is about 0.84. A freely available web resource for DDI prediction was developed (http://way2drug.com/ddi/).
TL;DR: Key structural features and a structural concept for rational design of novel DNA gyrase inhibitors with improved biological activities against both enzyme and mycobacterial cell, and with good pharmacokinetic properties and drug safety profiles are provided.
Abstract: Mycobacterium tuberculosis DNA gyrase subunit B (GyrB) has been identified as a promising target for rational drug design against fluoroquinolone drug-resistant tuberculosis. In this study, we attempted to identify the key structural feature for highly potent GyrB inhibitors through 2D-QSAR using HQSAR, 3D-QSAR using CoMSIA and molecular dynamics (MD) simulations approaches on a series of thiazole urea core derivatives. The best HQSAR and CoMSIA models based on IC50 and MIC displayed the structural basis required for good activity against both GyrB enzyme and mycobacterial cell. MD simulations and binding free energy analysis using MM-GBSA and waterswap calculations revealed that the urea core of inhibitors has the strongest interaction with Asp79 via hydrogen bond interactions. In addition, cation-pi interaction and hydrophobic interactions of the R2 substituent with Arg82 and Arg141 help to enhance the binding affinity in the GyrB ATPase binding site. Thus, the present study provides crucial structural features and a structural concept for rational design of novel DNA gyrase inhibitors with improved biological activities against both enzyme and mycobacterial cell, and with good pharmacokinetic properties and drug safety profiles.
TL;DR: This study investigated the possibility of creating SAR models for the prediction of the qualitative metabolite yield depending on species and biological experimental systems and created models for prediction of xenobiotic excretion depending on its administration route for different species.
Abstract: Metabolite identification is an essential part of the drug discovery and development process. Experimental methods allow identifying metabolites and estimating their relative amount, but they require cost-intensive and time-consuming techniques. Computational methods for metabolite prediction are devoid of these shortcomings and may be applied at the early stage of drug discovery. In this study, we investigated the possibility of creating SAR models for the prediction of the qualitative metabolite yield ('major', 'minor', "trace" and "negligible") depending on species and biological experimental systems. In addition, we have created models for prediction of xenobiotic excretion depending on its administration route for different species. The prediction is based on an algorithm of naive Bayes classifier implemented in PASS software. The average accuracy of prediction was 0.91 for qualitative metabolite yield prediction and 0.89 for prediction of xenobiotic excretion. The created models were included as a component of MetaTox web application, which allows predicting the xenobiotic metabolism pathways ( http://www.way2drug.com/mg ).
TL;DR: The main goal of this work was to conduct the most valuable meta-pharmacometrics/pharmacoinformatics analysis with all Praziquantel medicinal chemistry data available in the literature.
Abstract: Praziquantel (PZQ) is the first line drug for the treatment of human Schistosoma spp. worm infections. However, it suffers from low activity towards immature stages of the worm, and its prolonged u...
TL;DR: In the present study, various computational tools such as homology modelling, pharmacophore modelling, docking, molecular dynamics and molecular mechanics have been employed to design dual DHFR-TS and PTR1 inhibitors.
Abstract: Folates are essential biomolecules required to carry out many crucial processes in leishmania parasite. Dihydrofolate reductase-thymidylate synthase (DHFR-TS) and pteridine reductase 1 (PTR1) involved in folate biosynthesis in leishmania have been established as suitable targets for development of chemotherapy against leishmaniasis. In the present study, various computational tools such as homology modelling, pharmacophore modelling, docking, molecular dynamics and molecular mechanics have been employed to design dual DHFR-TS and PTR1 inhibitors. Two designed molecules, i.e. 2-(4-((4-nitrobenzyl)oxy)phenyl)-1H-benzo[d]imidazole and 2-(4-((2,4-dichlorobenzyl)oxy)phenyl)-1H-benzo[d]oxazolemolecules were synthesized. MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide) assay was performed to evaluate in vitro activity of molecules against promastigote form of Leishmania donovani using Miltefosine as standard. 2-(4-((4-nitrobenzyl)oxy)phenyl)-1H-benzo[d]imidazole and 2-(4-((2,4-dichlorobenzyl)oxy)phenyl)-1H-benzo[d]oxazolemolecules were found to be moderately active with showed IC50 = 68 ± 2.8 µM and 57 ± 4.2 µM, respectively.
TL;DR: A statistical feature extraction model using the detrended moving-average cross-correlation (DMCA) coefficient descriptor based on din nucleotide property matrix generated by the 15 DNA dinucleotide properties is developed, and this model is named iDHS-DMCAC.
Abstract: DNase I hypersensitive sites (DHSs) are associated with regulatory DNA elements, so their good understanding is significant for both the biomedical research and the discovery of new drugs. Traditional experimental methods are laborious, time consuming and an inaccurately task to detect DHSs. More importantly, with the avalanche of genome sequences in the postgenomic age, it is highly essential to develop cost-effective computational approaches to identify DHSs. In this paper, we develop a statistical feature extraction model using the detrended moving-average cross-correlation (DMCA) coefficient descriptor based on dinucleotide property matrix generated by the 15 DNA dinucleotide properties, and this model is named iDHS-DMCAC. A 105-dimensional feature vector is constructed for a certain window on the two class imbalanced benchmark datasets, with over-sampling and support vector machine algorithms. Rigorous cross-validations indicate that our predictor remarkably outperforms the existing models in both accuracy and stability. We anticipate that iDHS-DMCAC will become a very useful high throughput tool, or at the very least, a complementary tool to the existing methods of identifying DNase I hypersensitive sites. The datasets and source codes of the proposed model are freely available at https://github.com/shengli0201/Datasets .
TL;DR: An attempt was made for developing QSAR models using structural descriptors for 1,3-thiazolidine-4-one compounds that can predict significant dimension of essential structural features of these inhibitors to evaluate, screen and help priorities of the synthesis of the candidates against anthrax bioterrorism.
Abstract: Bacillus anthracis is considered as a biological warfare agent because it is the causative agent of the serious infectious anthrax disease. Delay in treatment leads to lethal factor-mediated toxaemia which is very critical due to lack of therapeutic options. Consequently, attempts have been made to discover potent lethal factor (LF) protease inhibitors such as small-molecule synthetic 2-thio-1,3-thiazolidine-4-one (rhodanine) compounds. But computed descriptor-based quantitative structure-activity relationship (QSAR) and drug design studies on such aspect are poorly represented. Therefore, an attempt was made for developing QSAR models using structural descriptors for 1,3-thiazolidine-4-one compounds. The models were developed on a series of 49 LF protease inhibitors using the combination of constitutional, functional group, atom-centred fragment and molecular property descriptors. The best QSAR model included four variables, namely, C-040, nR05, GVWAI-80 and ALOGP that correlated well with the anti-LF protease activity with a good correlation coefficient (r = 0.870) of good statistical significance (F4, 29 = 14.09 (α = 0.001) F4, 29 = 6.19). This model was also validated and explained 58.1% of variances of the Bacillus anthracis inhibitory activities of the studied compounds with r2pred = 0.710 which denotes external predictability. Finally, molecular docking was carried out to predict the mode of binding of some highly active congeneric compounds. It was shown that VAL 1403 is an important residue for phenyl ring. TYR 1456 and HIS 1418 are responsible for interaction with the rhodanine nucleus. Therefore, these residues are considered responsible for the inhibition of LF protease anthrax and can predict significant dimension of essential structural features of these inhibitors to evaluate, screen and help priorities of the synthesis of the candidates against anthrax bioterrorism.
TL;DR: The physical and chemical requirements for the development of novel ORAI1 inhibitors with improved biological activity are provided and Coulomb energy, van der Waals energy and non-polar solvation terms are more favourable for ligand binding.
Abstract: Upregulation of store-operated Ca2+ influx via ORAI1, an integral component of the CRAC channel, is responsible for abnormal cytokine release in active rheumatoid arthritis, and therefore ORAI1 has been proposed as an attractive molecular target. In this study, we attempted to predict the mechanical insights of ORAI1 inhibitors through pharmacophore modelling, 3D-QSAR, molecular docking and free energy analysis. Various hypotheses of pharmacophores were generated and from that, a pharmacophore hypothesis with two hydrogen bond acceptors, one hydrogen bond donor and two aromatic rings (AADRR) resulted in a statistically significant 3D-QSAR model (r2 = 0.84 and q2 = 0.74). We believe that the obtained statistical model is a reliable QSAR model for the diverse dataset of inhibitors against the IL-2 production assay. The visualization of contours in active and inactive compounds generated from the 3D-QSAR models and molecular docking studies revealed major interaction with GLN108, HIS113 and ASP114, and interestingly, these residues are located near the Ca2+ selectivity filter region. Free energy binding analysis revealed that Coulomb energy, van der Waals energy and non-polar solvation terms are more favourable for ligand binding. Thus, the present study provides the physical and chemical requirements for the development of novel ORAI1 inhibitors with improved biological activity.
TL;DR: A performance comparative study of 13 state-of-the-art feature selection filter methods is conducted and the methods that exhibit the best performance are correlation-based feature selection, fast clustering- based feature selection and the set cover method.
Abstract: The application of machine learning methods to the construction of quantitative structure-activity relationship models is a complex computational problem in which dimensionality reduction of the representation of the molecular structure plays a fundamental role in predicting a target activity. The feature selection pre-processing approach has been indicated to be effective in dimensionality reduction for building simpler and more understandable models. In this paper, a performance comparative study of 13 state-of-the-art feature selection filter methods is conducted. Structure-activity relationship models are constructed using three widely used classifiers and a diverse collection of datasets. The comparative study utilizes robust statistical tests to compare the algorithms. According to the experimental results, there are substantial differences in performance among the evaluated feature selection methods. The methods that exhibit the best performance are correlation-based feature selection, fast clustering-based feature selection and the set cover method.
TL;DR: Seven new CD38 inhibitors with greater activity with respect to the greatest active molecules were designed, and the CoMFA model developed to predict the CD38 inhibitory activity of the molecules was validated by calculating several statistical parameters.
Abstract: In this study, based on molecular docking analysis and comparative molecular field analysis (CoMFA) modelling of a series of 71 CD38 inhibitors including 4‑amino-8-quinoline carboxamides and 2,4-diamino-8-quinazoline carboxamides, new CD38 inhibitors were designed. The interactions of the molecules with the greatest and the lowest activities with the nicotinamide mononucleotide (NMN) binding site were investigated by molecular docking analysis. A CoMFA model with four partial least squares regression (PLSR) components was developed to predict the CD38 inhibitory activity of the molecules. The r2 values for the training and test sets were 0.89 and 0.82, respectively. The Q2 values for leave-one-out cross-validation (LOO-CV) and leave-many-out cross-validation (LMO-CV) tests on the training set were 0.65 and 0.64, respectively. The CoMFA model was validated by calculating several statistical parameters. CoMFA contour maps were interpreted, and structural features that influence the CD38 inhibitory activity of molecules were determined. Finally, seven new CD38 inhibitors with greater activity with respect to the greatest active molecules were designed.