Utilizing high throughput screening data for predictive toxicology models: protocols and application to MLSCN assays

Abstract

Computational toxicology is emerging as an encouraging alternative to experimental testing. The Molecular Libraries Screening Center Network (MLSCN) as part of the NIH Molecular Libraries Roadmap has recently started generating large and diverse screening datasets, which are publicly available in PubChem. In this report, we investigate various aspects of developing computational models to predict cell toxicity based on cell proliferation screening data generated in the MLSCN. By capturing feature-based information in those datasets, such predictive models would be useful in evaluating cell-based screening results in general (for example from reporter assays) and could be used as an aid to identify and eliminate potentially undesired compounds. Specifically we present the results of random forest ensemble models developed using different cell proliferation datasets and highlight protocols to take into account their extremely imbalanced nature. Depending on the nature of the datasets and the descriptors employed we were able to achieve percentage correct classification rates between 70% and 85% on the prediction set, though the accuracy rate dropped significantly when the models were applied to in vivo data. In this context we also compare the MLSCN cell proliferation results with animal acute toxicity data to investigate to what extent animal toxicity can be correlated and potentially predicted by proliferation results. Finally, we present a visualization technique that allows one to compare a new dataset to the training set of the models to decide whether the new dataset may be reliably predicted.

Predicting the biological activities of triazole derivatives as SGLT2 inhibitors using multilayer perceptron neural network, support vector machine, and projection pursuit regression models

“…Δ is the sum of the Kronecker deltas, that is, the number of atom pairs at a distance equal to 6. [42,43]. Its value is directly proportional to the number of atoms and inversely proportional to the number of atom pairs at a distance equal to 6.…”

Developing Best Practices for Descriptor‐Based Property Prediction: Appropriate Matching of Datasets, Descriptors, Methods, and Expectations

“…With a considerable thrust from the National Institute of Health, the Molecular Libraries Initiative has brought assay results and methodologies into the public domain [27]. Parallel advances in computational power have enabled researchers to take advantage [28] of these multiple highthroughput assays, which are now employed to describe both on-and off-target drug effects by creating an activity profile for each compound tested.…”

On the interpretation and interpretability of quantitative structure–activity relationship models

“…Though fingerprints were originally developed for searching chemical databases, they have proven to be useful as descriptors in developing a variety of predictive modeling studies [12,33,45,51,92,117]. The goal of any fingerprint is to characterize the substructures present in a molecule.…”