Reshaped<scp>Sequential Replacement</scp>for variable selection in QSPR: comparison with other reference methods

Grisoni, Francesca; Cassotti, Matteo; Todeschini, Roberto

doi:10.1002/cem.2603

Cited by 18 publications

(14 citation statements)

References 35 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Variable selection and modelling. The Genetic Algorithms (GA) [ 23 ], a benchmark variable selection method characterized by an optimal trade-off between computational time and exploration/exploitation ability [ 24 ], were used to retain the most relevant subsets of variables. A refined two-step GA procedure (see Materials and Methods) was applied on the training set descriptors in combination with six classification techniques: (a) Classification and Regression Trees (CART) [ 25 ]; (b) k -Nearest Neighbor ( k -NN) [ 26 ]; (c) N -Nearest Neighbors (N3) [ 27 ]; (d) Binned Nearest Neighbors (BNN) [ 27 ]; (e) Linear Discriminant Analysis (LDA) [ 28 ]; and (f) Partial Least Squares Analysis (PLSDA) [ 29 ].…”

Section: Resultsmentioning

confidence: 99%

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Nembri

Grisoni

Consonni

et al. 2016

IJMS

View full text Add to dashboard Cite

Cytochromes P450 (CYP) are the main actors in the oxidation of xenobiotics and play a crucial role in drug safety, persistence, bioactivation, and drug-drug/food-drug interaction. This work aims to develop Quantitative Structure-Activity Relationship (QSAR) models to predict the drug interaction with two of the most important CYP isoforms, namely 2C9 and 3A4. The presented models are calibrated on 9122 drug-like compounds, using three different modelling approaches and two types of molecular description (classical molecular descriptors and binary fingerprints). For each isoform, three classification models are presented, based on a different approach and with different advantages: (1) a very simple and interpretable classification tree; (2) a local (k-Nearest Neighbor) model based classical descriptors and; (3) a model based on a recently proposed local classifier (N-Nearest Neighbor) on binary fingerprints. The salient features of the work are (1) the thorough model validation and the applicability domain assessment; (2) the descriptor interpretation, which highlighted the crucial aspects of P450-drug interaction; and (3) the consensus aggregation of models, which largely increased the prediction accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Nembri

Grisoni

Consonni

et al. 2016

IJMS

View full text Add to dashboard Cite

show abstract

“…Seven regression strategies were coupled with 2 variable selection methods (Table S2), namely (i) genetic algorithms (Holland ), which are a benchmark selection method, and (ii) reshaped sequential replacement (Cassotti et al ), which has a good exploration ability of the descriptors’ space (Grisoni et al ). The final models were selected to ensure the best compromise between simplicity, easy‐to‐interpret molecular descriptors and accuracy.…”

Section: Methodsmentioning

confidence: 99%

Acceptable‐by‐design QSARs to predict the dietary biomagnification of organic chemicals in fish

Grisoni

Consonni

Vighi

2018

Integr Envir Assess & Manag

View full text Add to dashboard Cite

EDITOR'S NOTE:This article was generated from the session "Predictive models in ecotoxicology: Bridging the gap between scientific progress and regulatory applicability," presented at the 27th SETAC Europe Annual Meeting (May 2017, Brussels, Belgium). The session considered approaches used in ecotoxicology for understanding and predicting the effects of chemicals, from QSAR to ecological modelling. This series aims to critically analyze and debate application examples and future developments to increase the acceptability of predictive models by regulators, managers, NGOs, and other stakeholders. ABSTRACTThis work presents the first-time QSAR approach to predict the laboratory-based fish biomagnification factor (BMF) of organic chemicals, to be used as a supporting tool for assessing bioaccumulation at the regulatory level. The developed strategy is based on 2 levels of prediction, with a varying trade-off between interpretability and performance according to the user's needs. We designed our models to be intrinsically acceptable at the regulatory level (in what we defined as "acceptableby-design" strategy), by (i) complying with OECD principles directly in the approach development phase, (ii) choosing easy-toapply modeling techniques, (iii) preferring simple descriptors when possible, and (iv) striving to provide data-driven mechanistic insights. Our novel tool has an error comparable to the observed experimental inter-and intraspecies variability and is stable on borderline compounds (root mean square error [RMSE] ranging from RMSE ¼ 0.45 to RMSE ¼ 0.45 log units on test data). Additionally, the models' molecular descriptors are carefully described and interpreted, allowing us to gather additional mechanistic insights into the structural features controlling the dietary bioaccumulation of chemicals in fish. To improve the transparency and promote the application of the model, the data set and the stand alone prediction tool are provided free of charge at https://github.com/grisoniFr/bmf_qsar Integr Environ Assess Manag 2019;15:51-63. C 2018 SETAC

show abstract

“…The Canonical measure of correlation (CMC) index, with the threshold value of 0.3, was used for screening the “tabu” descriptors. Roulette wheel: The initialization of the population was based on the calculated CMC index for each descriptor, whereby the descriptors with the higher CMC index had higher probability to be selected. Randomization test: The real model error is compared with the random classification error (random error rate (RER) test), that is, with the error rate obtained if the cases are randomly assigned to the classes, and final model is accepted if the real error rate is smaller than the corresponding RER value. Nested models: The final population of models was checked in the terms of complexity and performance. The model is rejected if its higher complexity is not balanced by higher performance. Model distance and correlation: The canonical measure of distance (CMD) and CMC indices were used to determine whether the final models with different variables are actually different in their nature …”

Section: Methodsmentioning

confidence: 99%

From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides

Antanasijević

Trišović

et al. 2017

Mol. Pharmaceutics

View full text Add to dashboard Cite

Succinimides, which contain a pharmacophore responsible for anticonvulsant activity, are frequently used antiepileptic drugs and the synthesis of their new derivatives with improved efficacy and tolerability presents an important task. Nowadays, multitarget/tasking methodologies focused on quantitative-structure activity relationships (mt-QSAR/mtk-QSAR) have an important role in the rational design of drugs since they enable simultaneous prediction of several standard measures of biological activities at diverse experimental conditions and against different biological targets. Relating to this very topic, the mt-QSAR/mtk-QSAR methodology can give only binary classification models, and as such, in this study a regression mtk-QSAR (rmtk-QSAR) model based on a novel modular neural network (MNN) has been proposed. The MNN uses standard classification mtk-QSAR models as input modules, while the regression is performed by the output module. The rmtk-QSAR model has been successfully developed for the simultaneous prediction of anticonvulsant activity and neurotoxicity of succinimides, with a satisfactory accuracy in testing (R = 0.87). Thus, the proposed mtk-QSAR regression method can be regarded as a viable alternative to the standard QSAR methodology.

show abstract

ReshapedSequential Replacementfor variable selection in QSPR: comparison with other reference methods

Cited by 18 publications

References 35 publications

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Acceptable‐by‐design QSARs to predict the dietary biomagnification of organic chemicals in fish

From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides

Contact Info

Product

Resources

About