QSPR Models for Predicting Log Pliver Values for Volatile Organic Compounds Combining Statistical Methods and Domain Knowledge

Palomba, Damián; Martínez, María Jimena; Ponzoni, Ignacio; Díaz, Mónica F.; Vazquez, Gustavo E.; Soto, Axel J.

doi:10.3390/molecules171214937

Cited by 14 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process encompasses several aspects, such as analyzing descriptor co-occurrence in the different candidate models, avoiding redundant descriptor sets, and analyzing descriptor–target relationships. This analysis has been traditionally carried out by the expert combining her expertise with the design of plots and tables in an ad - hoc manner [ 10 , 11 ].…”

Section: Methodsmentioning

confidence: 99%

“…At this point, the modeler can have a better understanding of the contribution of each descriptor to the modeling of the target property and the type of relationship (linear, quadratic, cubic, etc.). For example, in previous works [ 11 , 26 ], the best models were obtained by combining descriptors that cover different subregions of the chemical domain. In other words, the exploration of this visualization allows assessing the contribution of the different descriptors to the model.…”

Section: Methodsmentioning

confidence: 99%

“…This is due to the fact that in order to fine-tune the results or introduce domain knowledge in the selection criteria it is necessary to know the inner workings of the method [ 9 ] or, in the best case, to encode this knowledge in the form of some prior probabilities. While some works have overcome this limitation by ad - hoc analyses [ 10 , 11 ], we claim that there is a need for better support in the descriptor selection task, so that these methods can be embraced by the cheminformatics community.…”

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods

et al. 2015

Self Cite

View full text Add to dashboard Cite

BackgroundThe design of QSAR/QSPR models is a challenging problem, where the selection of the most relevant descriptors constitutes a key step of the process. Several feature selection methods that address this step are concentrated on statistical associations among descriptors and target properties, whereas the chemical knowledge is left out of the analysis. For this reason, the interpretability and generality of the QSAR/QSPR models obtained by these feature selection methods are drastically affected. Therefore, an approach for integrating domain expert’s knowledge in the selection process is needed for increase the confidence in the final set of descriptors.ResultsIn this paper a software tool, which we named Visual and Interactive DEscriptor ANalysis (VIDEAN), that combines statistical methods with interactive visualizations for choosing a set of descriptors for predicting a target property is proposed. Domain expertise can be added to the feature selection process by means of an interactive visual exploration of data, and aided by statistical tools and metrics based on information theory. Coordinated visual representations are presented for capturing different relationships and interactions among descriptors, target properties and candidate subsets of descriptors. The competencies of the proposed software were assessed through different scenarios. These scenarios reveal how an expert can use this tool to choose one subset of descriptors from a group of candidate subsets or how to modify existing descriptor subsets and even incorporate new descriptors according to his or her own knowledge of the target property.ConclusionsThe reported experiences showed the suitability of our software for selecting sets of descriptors with low cardinality, high interpretability, low redundancy and high statistical performance in a visual exploratory way. Therefore, it is possible to conclude that the resulting tool allows the integration of a chemist’s expertise in the descriptor selection process with a low cognitive effort in contrast with the alternative of using an ad-hoc manual analysis of the selected descriptors.Graphical abstractVIDEAN allows the visual analysis of candidate subsets of descriptors for QSAR/QSPR. In the two panels on the top, users can interactively explore numerical correlations as well as co-occurrences in the candidate subsets through two interactive graphs.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-015-0092-4) contains supplementary material, which is available to authorized users.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…A DT is composed of a hierarchical arrangement of nodes and branches in which the nodes represent the molecular descriptors, whereas the branches refer to decision rules to categorize compounds as actives and inactives. DT has been successfully applied in the analysis of various types of compounds, such as aromatase inhibitors, 26 volatile organic compounds, 31 and cytochrome P450-interacting compounds. 32 A DT was constructed with WEKA, version 3.6, 33 using the J48 algorithm (a Java implementation of the C4.5 algorithm).…”

Section: Methodsmentioning

confidence: 99%

Navigating the chemical space of dipeptidyl peptidase-4 inhibitors

Shoombuatong¹,

Prachayasittikul²,

Anuwongcharoen³

et al. 2015

DDDT

View full text Add to dashboard Cite

This study represents the first large-scale study on the chemical space of inhibitors of dipeptidyl peptidase-4 (DPP4), which is a potential therapeutic protein target for the treatment of diabetes mellitus. Herein, a large set of 2,937 compounds evaluated for their ability to inhibit DPP4 was compiled from the literature. Molecular descriptors were generated from the geometrically optimized low-energy conformers of these compounds at the semiempirical AM1 level. The origins of DPP4 inhibitory activity were elucidated from computed molecular descriptors that accounted for the unique physicochemical properties inherently present in the active and inactive sets of compounds as defined by their respective half maximal inhibitory concentration values of less than 1 μM and greater than 10 μM, respectively. Decision tree analysis revealed the importance of molecular weight, total energy of a molecule, topological polar surface area, lowest unoccupied molecular orbital, and number of hydrogen-bond donors, which correspond to molecular size, energy, surface polarity, electron acceptors, and hydrogen bond donors, respectively. The prediction model was subjected to rigorous independent testing via three external sets. Scaffold and chemical fragment analysis was also performed on these active and inactive sets of compounds to shed light on the distinguishing features of the functional moieties. Docking of representative active DPP4 inhibitors was also performed to unravel key interacting residues. The results of this study are anticipated to be useful in guiding the rational design of novel and robust DPP4 inhibitors for the treatment of diabetes.

show abstract

“…Assessing each of these meta-models with different random seed numbers slightly decreased the performance for one of them and increased it for the other (mean balanced accuracies for five repeated runs with different seed numbers were 73.56% and 74.27%, respectively; standard deviations 0.47% and 0.44%). The inclusion of dose among the predictors in the meta-models only slightly (if at all) increased the performance compared with the meta-models built without the dose, but we preferred to include it on the basis of domain knowledge [22,23]. Meta-models built similarly with support vector machines (SVM), k-nearest neighbors (knn and its Rweka implementation, IBk) and naïve Bayes algorithms had a slightly lower performance in terms of both balanced accuracy and sensitivity than those built with random forests.…”

Section: Performances Of Modelsmentioning

confidence: 99%

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

Ancuceanu

Hovaneț

Anghel

et al. 2020

IJMS

View full text Add to dashboard Cite

Drug-induced liver injury (DILI) remains one of the challenges in the safety profile of both authorized and candidate drugs, and predicting hepatotoxicity from the chemical structure of a substance remains a task worth pursuing. Such an approach is coherent with the current tendency for replacing non-clinical tests with in vitro or in silico alternatives. In 2016, a group of researchers from the FDA published an improved annotated list of drugs with respect to their DILI risk, constituting “the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans” (DILIrank). This paper is one of the few attempting to predict liver toxicity using the DILIrank dataset. Molecular descriptors were computed with the Dragon 7.0 software, and a variety of feature selection and machine learning algorithms were implemented in the R computing environment. Nested (double) cross-validation was used to externally validate the models selected. A total of 78 models with reasonable performance were selected and stacked through several approaches, including the building of multiple meta-models. The performance of the stacked models was slightly superior to other models published. The models were applied in a virtual screening exercise on over 100,000 compounds from the ZINC database and about 20% of them were predicted to be non-hepatotoxic.

show abstract

QSPR Models for Predicting Log Pliver Values for Volatile Organic Compounds Combining Statistical Methods and Domain Knowledge

Cited by 14 publications

References 31 publications

Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods

Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods

Navigating the chemical space of dipeptidyl peptidase-4 inhibitors

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

Contact Info

Product

Resources

About