A Distance-Based Boolean Applicability Domain for Classification of High Throughput Screening Data

Berenger, Francois; Yamanishi, Yoshihiro

doi:10.1021/acs.jcim.8b00499

Cited by 17 publications

(15 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The "applicability domain" (AD) is a tool used to assess whether a QSAR model may be employed to predict, in a valid manner, the class label of a test compound; such a "prediction" is only valid if the assumptions on which the model was built are still met for the test compound [28]. If the prediction exercise involves an extrapolation from the feature space, the result of this exercise cannot be relied upon.…”

Section: Outliers Applicability Domain and Wrongly Classified Drugsmentioning

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

Section: Outliers Applicability Domain and Wrongly Classified Drugsmentioning

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

show abstract

“…Most research articles in the area address AD determination using a standalone method, where different strategies and statistical measures are adopted to determine AD boundaries [10]. A good number of them focus on defining different molecular similarity criteria for identifying outliers, which are then excluded from the AD of the model [53][54][55]. Klingspohn et al [10] performed a comprehensive study in order to define a taxonomy of AD methods and find the best approaches for estimating the AD of different classification methods.…”

Section: Applicability Domain and Interpretability Of Prediction Modelsmentioning

confidence: 99%

Neural-based approaches to overcome feature selection and applicability domain in drug-related property prediction

Sabando

Ponzoni

Soto

2019

Applied Soft Computing

View full text Add to dashboard Cite

In the fields of pharmaceutical research and biomedical sciences, QSAR modeling is an established approach during drug discovery for prediction of biological activity of drug candidates. Yet, QSAR modeling poses a series of open challenges. First, chemical compounds are represented on a high-dimensional space and thus feature selection is typically applied, although this task entails a challenging combinatorial problem with potential loss of information. Second, the definition of the applicability domain of a QSAR model is a desirable aspect to determine the reliability of predictions on unseen chemicals, which is often difficult to assess due to the extent of the chemical space. Finally, interpretability of these models is also a critical issue for drug designers. The purpose of this work is to thoroughly assess the application of neural-based methods and recent advances deep learning for QSAR modeling. We hypothesize that neural-based methods can overcome the need to perform a descriptor selection phase. We developed three QSAR models based on neural networks for prediction of relevant chemical and biomedical properties that, in the absence of any feature selection step, can outperform the state-of-the-art models for such properties. We also implemented an embedded applicability domain technique based on network output probabilities that proved to be effective; its application improved the predictive performance of the model. Finally, we proposed the use of a post hoc feature analysis technique based on an aggregation of network weights, which enabled effective detection of relevant features in the model.

show abstract

“…The "applicability domain" (AD) is a concept meant to evaluate if a model may be validly applied to predict the effect of a candidate compound; such validity is conditioned on the satisfaction of the assumptions applied in the construction of the model [31]. If the new substance whose activity we are trying to predict differs substantially from those on which a QSAR a model was based, such a prediction cannot be trusted.…”

Section: Applicability Domainmentioning

confidence: 99%

Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-src Tyrosine Kinase

Ancuceanu

Tamba

Stoicescu³

et al. 2019

IJMS

View full text Add to dashboard Cite

A prototype of a family of at least nine members, cellular Src tyrosine kinase is a therapeutically interesting target because its inhibition might be of interest not only in a number of malignancies, but also in a diverse array of conditions, from neurodegenerative pathologies to certain viral infections. Computational methods in drug discovery are considerably cheaper than conventional methods and offer opportunities of screening very large numbers of compounds in conditions that would be simply impossible within the wet lab experimental settings. We explored the use of global quantitative structure-activity relationship (QSAR) models and molecular ligand docking in the discovery of new c-src tyrosine kinase inhibitors. Using a dataset of 1038 compounds from ChEMBL database, we developed over 350 QSAR classification models. A total of 49 models with reasonably good performance were selected and the models were assembled by stacking with a simple majority vote and used for the virtual screening of over 100,000 compounds. A total of 744 compounds were predicted by at least 50% of the QSAR models as active, 147 compounds were within the applicability domain and predicted by at least 75% of the models to be active. The latter 147 compounds were submitted to molecular ligand docking using AutoDock Vina and LeDock, and 89 were predicted to be active based on the energy of binding.

show abstract

A Distance-Based Boolean Applicability Domain for Classification of High Throughput Screening Data

Cited by 17 publications

References 57 publications

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

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

Neural-based approaches to overcome feature selection and applicability domain in drug-related property prediction

Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-src Tyrosine Kinase

Contact Info

Product

Resources

About