Acute Toxicity-Supported Chronic Toxicity Prediction: A k-Nearest Neighbor Coupled Read-Across Strategy

Abstract

A k-nearest neighbor (k-NN) classification model was constructed for 118 RDT NEDO (Repeated Dose Toxicity New Energy and industrial technology Development Organization; currently known as the Hazard Evaluation Support System (HESS)) database chemicals, employing two acute toxicity (LD50)-based classes as a response and using a series of eight PaDEL software-derived fingerprints as predictor variables. A model developed using Estate type fingerprints correctly predicted the LD50 classes for 70 of 94 training set chemicals and 19 of 24 test set chemicals. An individual category was formed for each of the chemicals by extracting its corresponding k-analogs that were identified by k-NN classification. These categories were used to perform the read-across study for prediction of the chronic toxicity, i.e., Lowest Observed Effect Levels (LOEL). We have successfully predicted the LOELs of 54 of 70 training set chemicals (77%) and 14 of 19 test set chemicals (74%) to within an order of magnitude from their experimental LOEL values. Given the success thus far, we conclude that if the k-NN model predicts LD50 classes correctly for a certain chemical, then the k-analogs of such a chemical can be successfully used for data gap filling for the LOEL. This model should support the in silico prediction of repeated dose toxicity.

Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis

“…By comparing their performances, it was found that RF usually outperformed [ 91 ]. Using the k-NN algorithm, Chavan et al even tried to predict the chronic toxicity of chemical substances by combining acute toxicity information with molecular fingerprints such as MACCS and CDK [ 93 ]. These studies demonstrated that chemical properties can help improve accuracy of toxicity prediction.…”

Predicting Environmental Chemical Toxicity using a New Hybrid Deep Machine Learning Method

“…To predict oral acute toxicity (LD50), regression models are developed with a confined applicability domain to improve prediction accuracy 1,4 . Chavan et al used k-Nearest Neighbor (KNN) method to predict the acute toxicity of chemicals with 79.17% accuracy 5 . Cherkasov et al predicted the antibacterial activity of chemicals with 93% accuracy using the Artificial Neural Network (ANN) method for Quantitative Structure-Activity Relationship (QSAR) model 6 .…”

A k-nearest neighbor classification of hERG K+ channel blockers

“…The recent development of open source fingerprints, such as PaDEL fingerprints, which are libraries of descriptors [ 24 ], allows for ready access to tools for predicting biological endpoints. A recent report on the use of PaDEL fingerprints in conjunction with a k -NN strategy aimed at the prediction of chronic toxicity [ 25 ] prompted us to apply this approach to hERG-channel blockers, a far more focused system. It was envisaged that publicly available data on a series of hERG-channel blockers could function as a starting point for model construction, and a series of 1953 PubChem compounds could act as basis for validation.…”