The Predictive Analytics Toolkit (PAT): User-friendly predictive analytics for advancing new approach methodologies (NAMs)
Louis Anthony Cox, Ted W. Simon, Richard A. Becker · Computational Toxicology · 2019
Advanced test systems and knowledge of biology, how chemical exposures occur, and the mechanisms, pathways and dose-dependent changes that can lead to toxicity are rapidly catalyzing the transformation away from traditional approaches to new approach methodologies for predicting potential hazards and risks. The explicit incorporation of inference modeling as an integral component of NAMs requires evaluation and transparent documentation of inference model robustness and predictivity. The Predictive Analytics Toolkit, described herein, was developed to facilitate such analyses. PAT is a free, user-friendly, cloud-based web platform that provides automated development and testing of prediction models. PAT provides simplified access to the analytics power of a vast array of R packages for detecting, analyzing, quantifying, and visualizing associations and other relations (such as information relations among multiple variables) in user uploaded Excel datasets using standardized, well-documented, and well-supported algorithms.