Applicability Domain Of Model Research Articles

Study of the Applicability Domain of the QSAR Classification Models by Means of the Rivality and Modelability Indexes.

The reliability of a QSAR classification model depends on its capacity to achieve confident predictions of new compounds not considered in the building of the model. The results of this external validation process show the applicability domain (AD) of the QSAR model and, therefore, the robustness of the model to predict the property/activity of new molecules. In this paper we propose the use of the rivality and modelability indexes for the study of the characteristics of the datasets to be correctly modeled by a QSAR algorithm and to predict the reliability of the built model to prognosticate the property/activity of new molecules. The calculation of these indexes has a very low computational cost, not requiring the building of a model, thus being good tools for the analysis of the datasets in the first stages of the building of QSAR classification models. In our study, we have selected two benchmark datasets with similar number of molecules but with very different modelability and we have corroborated the capacity of the predictability of the rivality and modelability indexes regarding the classification models built using Support Vector Machine and Random Forest algorithms with 5-fold cross-validation and leave-one-out techniques. The results have shown the excellent ability of both indexes to predict outliers and the applicability domain of the QSAR classification models. In all cases, these values accurately predicted the statistic parameters of the QSAR models generated by the algorithms.

How Precise Are Our Quantitative Structure–Activity Relationship Derived Predictions for New Query Chemicals?

Quantitative structure–activity relationship (QSAR) models have long been used for making predictions and data gap filling in diverse fields including medicinal chemistry, predictive toxicology, environmental fate modeling, materials science, agricultural science, nanoscience, food science, and so forth. Usually a QSAR model is developed based on chemical information of a properly designed training set and corresponding experimental response data while the model is validated using one or more test set(s) for which the experimental response data are available. However, it is interesting to estimate the reliability of predictions when the model is applied to a completely new data set (true external set) even when the new data points are within applicability domain (AD) of the developed model. In the present study, we have categorized the quality of predictions for the test set or true external set into three groups (good, moderate, and bad) based on absolute prediction errors. Then, we have used three criteria [(a) mean absolute error of leave-one-out predictions for 10 most close training compounds for each query molecule; (b) AD in terms of similarity based on the standardization approach; and (c) proximity of the predicted value of the query compound to the mean training response] in different weighting schemes for making a composite score of predictions. It was found that using the most frequently appearing weighting scheme 0.5–0–0.5, the composite score-based categorization showed concordance with absolute prediction error-based categorization for more than 80% test data points while working with 5 different datasets with 15 models for each set derived in three different splitting techniques. These observations were also confirmed with true external sets for another four endpoints suggesting applicability of the scheme to judge the reliability of predictions for new datasets. The scheme has been implemented in a tool “Prediction Reliability Indicator” available at http://dtclab.webs.com/software-tools and http://teqip.jdvu.ac.in/QSAR_Tools/DTCLab/, and the tool is presently valid for multiple linear regression models only.

QSAR Study of (5-Nitroheteroaryl-1,3,4-Thiadiazole-2-yl) Piperazinyl Derivatives to Predict New Similar Compounds as Antileishmanial Agents

To search for newer and potent antileishmanial drugs, a series of 36 compounds of 5-(5-nitroheteroaryl-2-yl)-1,3,4-thiadiazole derivatives were subjected to a quantitative structure-activity relationship (QSAR) analysis for studying, interpreting, and predicting activities and designing new compounds using several statistical tools. The multiple linear regression (MLR), nonlinear regression (RNLM), and artificial neural network (ANN) models were developed using 30 molecules having pIC50 ranging from 3.155 to 5.046. The best generated MLR, RNLM, and ANN models show conventional correlation coefficients R of 0.750, 0.782, and 0.967 as well as their leave-one-out cross-validation correlation coefficients RCV of 0.722, 0.744, and 0.720, respectively. The predictive ability of those models was evaluated by the external validation using a test set of 6 molecules with predicted correlation coefficients Rtest of 0.840, 0.850, and 0.802, respectively. The applicability domains of MLR and MNLR transparent models were investigated using William’s plot to detect outliers and outsides compounds. We expect that this study would be of great help in lead optimization for early drug discovery of new similar compounds.

Illustration of merits of semi-supervised learning in regression analysis

Semi-supervised learning (SSL) is a method for learning the relationship between X and y, and the essential structure of the corresponding dataset, using both labeled and unlabeled data. In this paper, an approach to use a combination of labeled and unlabeled samples to reduce the dimension, then perform regression analysis using the labeled samples in a low-dimensional space is focused in SSL methods. While various SSL methods for regression have been developed, there has been insufficient discussion as to why SSL is effective in regression analysis. Therefore, in this study, the merits of SSL in regression analysis are discussed in terms of the stability or the robustness and applicability domains of regression models and prior distribution of X-variables. The superiorities of SSL methods over fully supervised methods in regression are demonstrated using data from numerical simulations, quantitative structure–activity relationships and quantitative structure–property relationships.

BMM: A Business Modeling Method For Information Systems Development


 
 
 An important premise of most of the contemporary methods for developing Software and Information Systems is that a good understanding of the application domain is essential for a comprehensive definition of its requirements. However, when these methods are applied to the enterprise context, it is very unclear what an application domain means. To solve this problem, we elaborate the notion of business system and propose a method based on such notion for modeling application domains of Enterprise Information Systems (EIS). This method helps EIS development teams to get comprehensive knowledge about EIS application domains. This knowledge is expressed in terms of the fundamental concepts of a business system: goals, technologies, business rules, business processes, business objects, actors, job structure, and events. The method is described in terms of three methodological components: a product model, a process model, and a team model. This structure facilitates the explanation, understanding and application of the method.
 
 

Free Radical Scavenging Activity Evaluation of Hydrazones by Quantitative Structure Activity Relationship

The 2, 2-diphenyl-1-picrylhydrazyl (<strong>DPPH</strong>) free radical scavenging properties of selected hydrazone antioxidants was investigated by the application of Quantitative Structure Activity Relationship (<strong>QSAR</strong>). Density functional theory (<strong>DFT</strong>) was employed in the optimization of the molecular structures. Internal and external validation as well as y-randomization tests were conducted in order to confirm the statistical reliability and acceptability of the developed models. The leverage approach was employed in the assessment of the applicability domain of the developed model. While the relative contribution and strength of each descriptor in the model was obtained by estimating the variation inflation factor, mean effect, and degree of contribution of each descriptor in the developed model. Model 3 which gave the best validation results was chosen as the best of the five models. This model dictates that the most important descriptors that influence the free radical scavenging activities of the hydrazone antioxidants are the Broto-Moreau autocorrelation - lag 2 / weighted by polarizabilities; Count of atom-type H E-State: H on C bonded to saturated C; Number of hydrogen bond donors (using CDK H Bond Donor Count Descriptor algorithm); Structural information content index (neighborhood symmetry of 1-order) and the 3D topological distance based autocorrelation - lag 7 / weighted by I-state descriptors. The Structural information content index descriptor was observed to be the most influential of all the descriptors

Development of QSAR model for predicting the inclusion constants of organic chemicals with α-cyclodextrin.

Solubility is a crucial limiting factor in pharmaceutical research and contaminated site remediation. Cyclodextrin, with its structure of hydrophilic exterior and hydrophobic cavity, has a potential ability to enhance the hydrophobic chemical's solubility through the formation of host-guest complex. The stability of host-guest complex is often quantified by the inclusion constant. In this study, the logarithm of 1:1 α-cyclodextrin inclusion constants (log Kα) for 195 organic chemicals was collected. With this parameter as the endpoint, a quantitative structure-activity relationship (QSAR) model was developed using DRAGON descriptors and stepwise multiple linear regression analysis. The model statistics parameters indicated that the established model had a good determination coefficient of 0.857, a high cross-validation coefficient of 0.835, a low root mean square error of 0.380, together with the acceptable results of external validation, which indicate a satisfactory goodness-of-fit, robustness, and predictive ability of the model. Based on the screened eight descriptors, we propose an appropriate mechanism interpretation for the inclusion interaction. Additionally, the applicability domain of the current model was characterized by the Euclidean distance-based method and Williams plot, and results indicated that the model covered a large number of structurally diverse chemicals belonging to 13 different classes. Comparing with the previous reported models, this model has obvious advantages with a larger dataset, a higher value of correlation coefficient, and a wider application domain.

Evaluation of the antioxidant properties of curcumin derivatives by genetic function algorithm

The prevalence of degenerative diseases in recent time has triggered extensive research on their control. This condition could be prevented if the body has an efficient antioxidant mechanism to scavenge the free radicals which are their main causes. Curcumin and its derivatives are widely employed as antioxidants. The free radical scavenging activities of curcumin and its derivatives have been explored in this research by the application of quantitative structure activity relationship (QSAR). The entire data set was optimized at the density functional theory (DFT) level using the Becke's three-parameter Lee-Yang-Parr hybrid functional (B3LYP) in combination with the 6-311G∗ basis set. The training set was subjected to QSAR studies by genetic function algorithm (GFA). Five predictive QSAR models were developed and statistically subjected to both internal and external validations. Also the applicability domain of the developed model was accessed by the leverage approach. Furthermore, the variation inflation factor, (VIF), mean effect (MF) and the degree of contribution (DC) of each descriptor in the resulting model were calculated. The developed models met all the standard requirements for acceptability upon validation with highly impressive results (R=0.965,R2=0.931,Q2(RCV2)=0.887,Rpred2=0.844,cRp2=0.842s=0.226,rmsep=0.362). Based on the results of this research, the most crucial descriptor that influence the free radical scavenge of the curcumins is the nsssN (count of atom-type E-state: >N-) descriptor with DC and MF values of 12.980 and 0.965 respectively.

Optimization of the anticonvulsant activity of 2-acetamido-N-benzyl-2-(5-methylfuran-2-yl) acetamide using QSAR modeling and molecular docking techniques

Chemometric descriptors were used to analyze quantitatively the anticonvulsant activity of ninety propanamide derivatives. Molecular geometries of the data set were optimized with B3LYP/6-31G∗∗ quantum mechanical method and chemometric descriptors were calculated from the optimized structure. Linear QSAR models were developed using genetic function algorithm. Predictive capabilities of the models were evaluated using various internal and external validation techniques. The best three models proposed were octa-parametric equation with good statistical quality: R2 (0.898–0.918); Q2 (0.865–0.893); R2pred (0.746–0.772) and F (66.657–88.036). 2-acetamido-N-benzyl-2-(5-methylfuran-2-yl) acetamide a member of the data set was chosen as scaffold for in silico design. Using the information afforded by the models, several attempts were made to optimize the scaffold by introducing various modifications. Potential derivatives with higher predicted activity values than the template were identified and a detailed analysis on the models applicability domain defined the designed compounds, whose estimations can be accepted with confidence. Some of the designed compounds docked with γ-aminobutyrate aminotransferase (PBD: 1OHV) (target) showed better binding affinity for the target when compare with 4-aminohex-5-enoic acid (vigabatrin) (a known inhibitor of the target).

Modeling interfacial tension in N2/n-alkane systems using corresponding state theory: Application to gas injection processes

Nitrogen is of paramount importance for many processes in chemical and petroleum engineering; including enhanced oil recovery, gas injection for pressure maintenance, and gas recycling. Precise estimation of interfacial tension (IFT) between N2 and the reservoir hydrocarbons is, therefore indispensable. However, experimental measurement of IFT is expensive and time consuming. Therefore, reliable model for estimating IFT is vital. In this communication, the IFT between N2 and n-alkanes was modeled over a wide range of pressure (0.1–69 MPa) and temperature (295–442 K) based on the principle of corresponding state theory using dimensionless pressure and dimensionless temperature. Three well-known models; namely, Multilayer Perceptron (MLP) Neural Networks (optimized by Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), or Bayesian Regularization (BR)), two Radial Basis Function (RBF) Neural Networks (optimized by Particle Swarm optimization (PSO) technique or Genetic Algorithm (GA)) and one Least Square Support Vector Machine (LSSVM) (optimized by coupled simulated annealing) were used to develop robust and accurate models for predicting IFT based on the proposed dimensionless parameters. Results suggested that the developed MLP-LM was the most accurate model of all with an average absolute relative error of 1.38%. MLP-LM model was compared with three well-known models in the literature; namely Density Gradient Theory (DGT), Linear Gradient Theory (LGT), and Parachor approaches combined with the Volume Translated Predictive Peng Robinson Equation of State (VT-PPR EOS) and the recently developed model by Hemmati-Sarapardeh and Mohagheghian. In addition to the advantage of being normal alkane-independent, results showed that the proposed MLP-LM model is superior to published models. Lastly, the quality of the literature IFT data and the applicability domain of MLP-LM model were evaluated using the Leverage approach.

Quantitative Structure Activity Relationship Analysis of Coumarins as Free Radical Scavengers by Genetic Function Algorithm

The antioxidant properties of coumarin derivatives using the 2,2ˈ -diphenyl-1- picrylhydrazyl (DPPH) radical scavenging assay were investigated by the application of Quantitative Structure Activity Relationship (QSAR) studies. The molecular structures were optimized and submitted for the generation of quantum chemical and molecular descriptors. Genetic Function Algorithm (GFA) was employed in model development. Also the applicability domain of the developed models were accessed by the leverage approach. The Variation Inflation Factor (VIF), Mean Effect (MF) and Degree of Contribution (DC) of these descriptors were estimated. Five predictive QSAR models were developed and subjected to various validation tests. The developed models gave highly encouraging results upon validation (R=0.938, R^2=0.879, Q^2=0.845, 〖R^2〗_pred=0.700 and cR_p^2= 0.832. This research indicates that the most crucial descriptors that influence the free radical scavenging activities and essential in the design of new set of the coumarin antioxidants are the HBDCount (hydrogen-bond donor count), AATS3e (Average Broto-Moreau autocorrelation - lag 3 / weighted by Sanderson electronegativities), and the MW (Molecular weight) descriptors.

How to judge whether QSAR/read-across predictions can be trusted: a novel approach for establishing a model's applicability domain

Probability-oriented distance-based approach (ADProbDist) for determining the nano-QSAR/read-across model's applicability domain where true and reliable predictions can be expected.

Exploring QSAR of Some Antitubercular Agents

The in vitro vero cell cytotoxicity of 93 antitubercular compounds belonging to the classes of chiral pentaamines, bis-cyclic guanidines, bis-cyclic thioureas, bis-cyclic piperazines, and quinolylhydrazones has been modeled in the present quantitative structure-activity relationship (QSAR) study. Genetic function approximation followed by multiple linear regression (GFA-MLR) based on the mean absolute error (MAE) based criteria was used as the chemometric tool for the model development using 2D descriptors available from open source PaDEL-Descriptor. The developed model was statistically robust (Q2:0.868, R2pred:0.896). Additionally, the r2m metrics, concordance correlation coefficient (CCC) and MAE criteria for the test set validation were also tested. The models indicate importance of autocorrelation descriptors weighted by charge (ATSc3, ATSc5) and some electrotopological state atom type descriptor of fragments -NH-,-O-, >N- for cytotoxicity. The applicability domains of GFA-MLR models were also studied by applying both leverage and standardized residual approaches.

Natural Model based Design in Context: an Effective Method for Environmental Problems

Analyzing complex problem domains is not easy. Simulation tools support decision makers to find the best policies. Model-based system development is an approach where a model of the application domain is the central driving force when designing simulation tools. State-of-the-art techniques however still require both expert knowledge of the application domain and the implementation techniques as provided by ICT (such as multilevel agent technology). Domain experts, however, usually do not master ICT sufficiently. Modeling is more insightful for the domain expert when its goal is to formalize the language being used in that domain as a semi-natural language. At the meta level, this language describes the main concepts of the type of application domain. The model then is a concretization of this meta model. The main focus of this article is (1) to propose a natural-language-based approach to modeling application domains, (2) to show how these models can be transformed systematically into computational models, and (3) to propose the tool TiC (Tool in Context) that supports the domain expert when developing a model and generating a simulation tool. Our research methodology is based on Design Science. We verify our approach by describing the various transformation steps in detail, and by demonstrating the way of working via a sample session applying a real problem of Laf Forest Reserve deforestation in North Cameroon.

A strategy on the definition of applicability domain of model based on population analysis

In recent years, there have been growing concerns about quality evaluation of predictions of developed quantitative structure-activity relationship (QSAR) models. Well-defined applicability domain (AD) is very crucial in the validation of QSAR models as stated in the third principle of Organization for Economic Co-operation and Development (OECD). In this study, a new perspective on defining AD of model based on population analysis (PA) strategy, including model population analysis (MPA) and approach population analysis (APA), was proposed. MPA employed classical AD approaches to define AD with a vast amount of sub-datasets derived from training set. On the basis of MPA, the classical AD approaches could distinguish part of the samples that cannot be distinguished by full training samples. APA was then used to get a union of all results generated by the used AD approaches to give a consensus list of samples as falling outside the AD. In order to investigate the performance of PA strategy in defining AD with the classical AD approaches, two QSAR datasets were used. The results show that implementing PA strategy can assist three classical AD approaches to distinguish the additional samples that cannot be distinguished using full training dataset. When excluding the additional samples, the root mean square error of prediction of test set decreased, suggesting that PA strategy has a potential to distinguish the samples that cannot be reliably predicted.

Comprehensive and Automated Linear Interaction Energy Based Binding-Affinity Prediction for Multifarious Cytochrome P450 Aromatase Inhibitors

Cytochrome P450 aromatase (CYP19A1) plays a key role in the development of estrogen dependent breast cancer, and aromatase inhibitors have been at the front line of treatment for the past three decades. The development of potent, selective and safer inhibitors is ongoing with in silico screening methods playing a more prominent role in the search for promising lead compounds in bioactivity-relevant chemical space. Here we present a set of comprehensive binding affinity prediction models for CYP19A1 using our automated Linear Interaction Energy (LIE) based workflow on a set of 132 putative and structurally diverse aromatase inhibitors obtained from a typical industrial screening study. We extended the workflow with machine learning methods to automatically cluster training and test compounds in order to maximize the number of explained compounds in one or more predictive LIE models. The method uses protein–ligand interaction profiles obtained from Molecular Dynamics (MD) trajectories to help model search and define the applicability domain of the resolved models. Our method was successful in accounting for 86% of the data set in 3 robust models that show high correlation between calculated and observed values for ligand-binding free energies (RMSE < 2.5 kJ mol–1), with good cross-validation statistics.

Efficiency of different measures for defining the applicability domain of classification models

The goal of defining an applicability domain for a predictive classification model is to identify the region in chemical space where the model’s predictions are reliable. The boundary of the applicability domain is defined with the help of a measure that shall reflect the reliability of an individual prediction. Here, the available measures are differentiated into those that flag unusual objects and which are independent of the original classifier and those that use information of the trained classifier. The former set of techniques is referred to as novelty detection while the latter is designated as confidence estimation. A review of the available confidence estimators shows that most of these measures estimate the probability of class membership of the predicted objects which is inversely related to the error probability. Thus, class probability estimates are natural candidates for defining the applicability domain but were not comprehensively included in previous benchmark studies. The focus of the present study is to find the best measure for defining the applicability domain for a given binary classification technique and to determine the performance of novelty detection versus confidence estimation. Six different binary classification techniques in combination with ten data sets were studied to benchmark the various measures. The area under the receiver operating characteristic curve (AUC ROC) was employed as main benchmark criterion. It is shown that class probability estimates constantly perform best to differentiate between reliable and unreliable predictions. Previously proposed alternatives to class probability estimates do not perform better than the latter and are inferior in most cases. Interestingly, the impact of defining an applicability domain depends on the observed area under the receiver operator characteristic curve. That means that it depends on the level of difficulty of the classification problem (expressed as AUC ROC) and will be largest for intermediately difficult problems (range AUC ROC 0.7–0.9). In the ranking of classifiers, classification random forests performed best on average. Hence, classification random forests in combination with the respective class probability estimate are a good starting point for predictive binary chemoinformatic classifiers with applicability domain.Graphical abstract.

Ensemble partial least squares regression for descriptor selection, outlier detection, applicability domain assessment, and ensemble modeling in QSAR/QSPR modeling

In QSAR/QSPR modeling, building an accurate partial least squares (PLS) model usually involves descriptor selection, outlier detection, applicability domain assessment, nonlinear relationship, and model stability problems. In the present study, we presented an ensemble PLS (EnPLS) method for solving these modeling tasks under a unified methodology framework. EnPLS aims at developing a consistent algorithmic framework by means of the idea of ensemble learning and statistical distribution. The approach exploits the fact that the distribution of PLS model coefficients provides a mechanism for ranking and interpreting the effects of variables, whereas the distribution of prediction errors provides a mechanism for differentiating the outliers from normal samples and assessing the applicability domain of models. The use of statistics of these distributions, namely, mean/median value and standard deviation, inherently provides a feasible way to effectively describe the information contained by the original samples. Furthermore, ensemble modeling and prediction based on several cross‐predictive PLS models could effectively improve the model prediction performance and increase the model stability to a certain extent. The aqueous solubility data are used to demonstrate the ability of our proposed EnPLS method in solving various modeling tasks such as descriptor selection, outlier detection, applicability domain assessment, performance improvement, and model stability. Finally, a freely available R package implementing EnPLS is developed to facilitate the use of chemists and pharmacologists. The R package is freely available at https://github.com/wind22zhu/enpls1.2.

Predictive cartography of metal binders using generative topographic mapping.

Generative topographic mapping (GTM) approach is used to visualize the chemical space of organic molecules (L) with respect to binding a wide range of 41 different metal cations (M) and also to build predictive models for stability constants (logK) of 1:1 (M:L) complexes using "density maps," "activity landscapes," and "selectivity landscapes" techniques. A two-dimensional map describing the entire set of 2962 metal binders reveals the selectivity and promiscuity zones with respect to individual metals or groups of metals with similar chemical properties (lanthanides, transition metals, etc). The GTM-based global (for entire set) and local (for selected subsets) models demonstrate a good predictive performance in the cross-validation procedure. It is also shown that the data likelihood could be used as a definition of the applicability domain of GTM-based models. Thus, the GTM approach represents an efficient tool for the predictive cartography of metal binders, which can both visualize their chemical space and predict the affinity profile of metals for new ligands.

Quantitative Structure–Activity Relationship Studies of Anticancer Activity for Isatin (1H-indole-2,3-dione) Derivatives Based on Density Functional Theory

To establish a QSAR of anticancer activity for Isatin derivatives, a series of Isatin derivatives were analyzed by principal component analysis, multiple linear regression, partial least squares and multiple nonlinear regression analysis. The authors proposed linear and nonlinear models and interpreted the activity of the compounds by multivariate statistical analysis. The proposed models were used to predict the activity of test set compounds, and an agreement between experimental and predicted values was verified. The applicability domain of MLR models was investigated using William's plot to detect outliers and outsides compounds. For the successful application of the developed models to predict new compounds, rigorous validation tests have been used in this direction. Additionally, the rm2 metrics have been used to ensure the close agreement of predicted response data with observed ones. The developed models have been used for designing some new Isatin derivatives with high predicted values of anticancer effect.