Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Zorn, Kimberley M.; Foil, Daniel H.; Lane, Thomas R.; Russo, Daniel P.; Hillwalker, Wendy; Feifarek, David J; Jones, Frank E.; Klaren, William D; Brinkman, Ashley M; Ekins, Sean

doi:10.1021/acs.est.0c03982

Cited by 36 publications

(48 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have shown that ECFP6 fingerprints compare favorably with other descriptors. 54 We have compared Assay Central with other machine learning methods for a relatively small number of targets such as drug-induced liver injury, 52 rat acute oral toxicity, 53 estrogen receptor, 54,55 androgen receptor, 56 GSK3β 57 M. tuberculosis, 58,59 non-nucleoside reverse transcriptase, and whole cell HIV. 60 In general, we have found from our earlier studies that while DNN generally performed the best for five-fold cross-validation, with external test sets, this superiority was not observed and generally Assay Central performed comparably with SVM classification or DNN.…”

Section: ■ Discussionmentioning

confidence: 99%

“…29 This study may be enlightening as it echoes our earlier findings on individual datasets after extensive manual curation. 52,53,[55][56][57][58][59][60]82 It also goes some way further in using external validation with these methods for toxicology and drug discovery properties. Now that we have generated such a vast array of over 5000 machine learning models, it presents opportunities for using them for predicting the potential of new molecules to interact with targets of interest or avoiding others (such as PXR and hERG) that may result in undesirable effects.…”

Section: ■ Discussionmentioning

confidence: 99%

“…All of the preceding examples have in common that few, if any, used prospective prediction as a form of validation. The main aim of this study was to evaluate a Bayesian method, Assay Central, which we have previously used in several examples where we have compared it versus other machine learning methods against a relatively small number of datasets or targets such as drug-induced liver injury, rat acute oral toxicity, estrogen receptor, , androgen receptor, GSK3β, Mycobacterium tuberculosis, , non-nucleoside reverse transcriptase, and whole cell HIV . Our evaluation has now been expanded with this study to over 5000 CHEMBL datasets and provides statistics and data visualization methods in order to assess each algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

et al. 2020

Self Cite

View full text Add to dashboard Cite

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies, we and others have applied multiple machine learning algorithms and modeling metrics and, in some cases, compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and in comparison of our proprietary software Assay Central with random forest, k-nearest neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (three layers). Model performance was assessed using an array of fivefold cross-validation metrics including area-under-the-curve, F1 score, Cohen’s kappa, and Matthews correlation coefficient. Based on ranked normalized scores for the metrics or datasets, all methods appeared comparable, while the distance from the top indicated that Assay Central and support vector classification were comparable. Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case. If anything, Assay Central may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay Central performance, although support vector classification seems to be a strong competitor. We also applied Assay Central to perform prospective predictions for the toxicity targets PXR and hERG to further validate these models. This work appears to be the largest scale comparison of these machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors, and machine learning algorithms and further refine the methods for evaluating and comparing such models.

show abstract

Section: ■ Discussionmentioning

confidence: 99%

Section: ■ Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…To address this concern, a discriminator for the multilayer perceptron (MLP) was designed and constructed to be attached for assessment. Applying supervised machine learning classifiers is a well-accepted strategy in virtual screening, with successful stories reported [ 64 , 65 , 66 , 67 ]. The inclusion of the discriminator further closes the in silico design-test loop in this practice.…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligent Deep Learning Molecular Generative Modeling of Scaffold-Focused and Cannabinoid CB2 Target-Specific Small-Molecule Sublibraries

Bian

Xie

2022

Cells

View full text Add to dashboard Cite

Design and generation of high-quality target- and scaffold-specific small molecules is an important strategy for the discovery of unique and potent bioactive drug molecules. To achieve this goal, authors have developed the deep-learning molecule generation model (DeepMGM) and applied it for the de novo molecular generation of scaffold-focused small-molecule libraries. In this study, a recurrent neural network (RNN) using long short-term memory (LSTM) units was trained with drug-like molecules to result in a general model (g-DeepMGM). Sampling practices on indole and purine scaffolds illustrate the feasibility of creating scaffold-focused chemical libraries based on machine intelligence. Subsequently, a target-specific model (t-DeepMGM) for cannabinoid receptor 2 (CB2) was constructed following the transfer learning process of known CB2 ligands. Sampling outcomes can present similar properties to the reported active molecules. Finally, a discriminator was trained and attached to the DeepMGM to result in an in silico molecular design-test circle. Medicinal chemistry synthesis and biological validation was performed to further investigate the generation outcome, showing that XIE9137 was identified as a potential allosteric modulator of CB2. This study demonstrates how recent progress in deep learning intelligence can benefit drug discovery, especially in de novo molecular design and chemical library generation.

show abstract

“…Assay Central TM is proprietary software for curating high-quality datasets, generating Bayesian machine learning models with extended-connectivity fingerprints (ECFP6) generated from the CDK library 56 , and making prospective predictions of potential for bioactivity 1, 51-53, 57-64 . We have previously described this software in detail 1,[51][52][53][57][58][59][60][61][62][63][64] as well as the interpretation of prediction scores 54,65 , and the metrics generated from internal five-fold cross-validation used to evaluate and compare predictive performances. These metrics include, but are not limited to, ROC score 51 , Cohen's kappa (CK) 66,67 , and Matthew's correlation coefficient (MCC) 68 as described by us previously.…”

Section: Machine Learning -Assay Central Tmmentioning

confidence: 99%

A Very Large-Scale Bioactivity Comparison of Deep Learning and Multiple Machine Learning Algorithms for Drug Discovery

Lane¹,

Foil²,

Minerali³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies we have applied multiple machine learning algorithms, modeling metrics and in some cases compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and comparison of our proprietary software Assay CentralTM with random forest, k-Nearest Neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (3 levels). Model performance <a>was</a> assessed using an array of five-fold cross-validation metrics including area-under-the-curve, F1 score, Cohen’s kappa and Matthews correlation coefficient. <a>Based on ranked normalized scores for the metrics or datasets all methods appeared comparable while the distance from the top indicated Assay CentralTM and support vector classification were comparable. </a>Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case where minimal tuning was performed of any of the methods. If anything, Assay CentralTM may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay CentralTMperformance, but support vector classification seems to be a strong competitor. We also apply Assay CentralTM to prospective predictions for PXR and hERG to further validate these models. This work currently appears to be the largest comparison of machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors and algorithms, as well as further refining methods for evaluating and comparing models.

show abstract

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Cited by 36 publications

References 59 publications

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Artificial Intelligent Deep Learning Molecular Generative Modeling of Scaffold-Focused and Cannabinoid CB2 Target-Specific Small-Molecule Sublibraries

A Very Large-Scale Bioactivity Comparison of Deep Learning and Multiple Machine Learning Algorithms for Drug Discovery

Contact Info

Product

Resources

About