Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data

Idakwo, Gabriel; Thangapandian, Sundarapandian; Luttrell, Joseph; Zhou, Zhaoxian; Zhang, Chaoyang; Gong, Ping

doi:10.3389/fphys.2019.01044

Cited by 40 publications

(53 citation statements)

References 53 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the best classifiers of this study achieved the same level of performance as the winners of the Tox21 Data Challenge as a whole, we believe that there is still plenty of room for further improvement. Given the exceptionally outstanding performance of DeepTox [ 25 ] and our own experience with deep learning-based chemical toxicity classification [ 70 ], our future plan is to replace RF with a deep learning algorithm like deep neural networks as the base classifier and combine it with class rebalancing techniques to build novel deep learning models for SAR-based chemical toxicity prediction. We are also interested in pursuing a novel approach by integrating MCP, resampling and ensemble strategies to further improve the robustness and performance of imbalanced learning.…”

Section: Discussionmentioning

confidence: 99%

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

et al. 2020

Self Cite

View full text Add to dashboard Cite

The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure–Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for > 10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman’s aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g., > 28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

show abstract

Section: Discussionmentioning

confidence: 99%

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although the above described AA models all use CP, they are only partly directly comparable as underlying data, techniques and/or features differ (see Table 4). Note that some other QSAR models for AA have been published, based on similar data, using random forest, deep learning [53], and the Case Ultra system [54]. Since set-up and reported performance measures differ from this CP study, they can not directly be compared.…”

Section: Conformal Predictors-validation Of Aa Modelmentioning

confidence: 98%

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Morger¹,

Mathea²,

Achenbach³

et al. 2020

J Cheminform

View full text Add to dashboard Cite

Risk assessment of newly synthesised chemicals is a prerequisite for regulatory approval. In this context, in silico methods have great potential to reduce time, cost, and ultimately animal testing as they make use of the ever-growing amount of available toxicity data. Here, KnowTox is presented, a novel pipeline that combines three different in silico toxicology approaches to allow for confident prediction of potentially toxic effects of query compounds, i.e. machine learning models for 88 endpoints, alerts for 919 toxic substructures, and computational support for read-across. It is mainly based on the ToxCast dataset, containing after preprocessing a sparse matrix of 7912 compounds tested against 985 endpoints. When applying machine learning models, applicability and reliability of predictions for new chemicals are of utmost importance. Therefore, first, the conformal prediction technique was deployed, comprising an additional calibration step and per definition creating internally valid predictors at a given significance level. Second, to further improve validity and information efficiency, two adaptations are suggested, exemplified at the androgen receptor antagonism endpoint. An absolute increase in validity of 23% on the in-house dataset of 534 compounds could be achieved by introducing KNNRegressor normalisation. This increase in validity comes at the cost of efficiency, which could again be improved by 20% for the initial ToxCast model by balancing the dataset during model training. Finally, the value of the developed pipeline for risk assessment is discussed using two in-house triazole molecules. Compared to a single toxicity prediction method, complementing the outputs of different approaches can have a higher impact on guiding toxicity testing and de-selecting most likely harmful development-candidate compounds early in the development process.

show abstract

“…(Idakwo et al, 2019;Mansouri et al, 2020), whereas we used binary classification models to identify potential binders and non-binders. Results reveal that our SVM model has a higher accuracy and considerably higher sensitivity and specificity in identifying the binders and non-binders when compared to the previously published models (Idakwo et al, 2019;Mansouri et al, 2020). Together, these results indicate that our model could be very useful in the prediction of binders and non-binders of AR receptor.…”

Section: Model Based On Binary Fingerprintsmentioning

confidence: 99%

Structure-Based Virtual Screening of Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) as Endocrine Disruptors of Androgen Receptor Activity Using Molecular Docking and Machine Learning

Ramaprasad¹,

Tachachartvanich²,

Fourches³

et al. 2020

Preprint

View full text Add to dashboard Cite

Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) pose a substantial threat as endocrine disruptors, and thus early identification of those that may interact with steroid hormone receptors, such as the androgen receptor (AR), is critical. In this study we screened 5,206 PFASs from the CompTox database against the different binding sites on the AR using both molecular docking and machine learning techniques. We developed support vector machine models trained on Tox21 data to classify the active and inactive PFASs for AR using different chemical fingerprints as features. The maximum accuracy was 95.01% and Matthew’s correlation coefficient (MCC) was 0.76 respectively, based on MACCS fingerprints (MACCSFP). The combination of docking-based screening and machine learning models identified 29 PFASs that have strong potential for activity against the AR and should be considered priority chemicals for biological toxicity testing.

show abstract

Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data

Cited by 40 publications

References 53 publications

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Structure-Based Virtual Screening of Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) as Endocrine Disruptors of Androgen Receptor Activity Using Molecular Docking and Machine Learning

Contact Info

Product

Resources

About