Large scale meta-analysis of preclinical toxicity data for target characterisation and hypotheses generation

Cross study analyses of SEND data: toxicity profile classification

A SEND toxicology data transformation, harmonization, and analysis platform were created to improve the identification of unique findings related to the intended target, species, and duration of dosing using data from multiple studies. The lack of a standardized digital format for data analysis had impeded large-scale analysis of in vivo toxicology studies. The CDISC SEND standard enables the analysis of data from multiple studies performed by different laboratories. This work describes methods to analyze data and automate cross-study analysis of toxicology studies. Cross-study analysis can be used to understand a single compound's toxicity profile across all studies performed and/or to evaluate on-target versus off-target toxicity for multiple compounds intended for the same pharmacological target. This work involved development of data harmonization/transformation strategies to enable cross-study analysis of both numerical and categorical SEND data. Four de-identified SEND datasets from the BioCelerate database were used for the analyses. Toxicity profiles for key organ systems were developed for liver, kidney, male reproductive tract, endocrine system, and hematopoietic system using SEND domains. A cross-study analysis dashboard with a built-in user-defined scoring system was created for custom analyses, including visualizations to evaluate data at the organ system level and drill down into individual animal data. This data analysis provides the tools for scientists to compare toxicity profiles across multiple studies using SEND. A cross-study analysis of 2 different compounds intended for the same pharmacological target is described and the analyses indicate potential on-target effects to liver, kidney, and hematopoietic systems.

Replacing concurrent controls with virtual control groups in rat toxicity studies

Virtual control groups (VCGs) in nonclinical toxicity represent the concept of using appropriate historical control data for replacing concurrent control group animals. Historical control data collected from standardized studies can serve as base for constructing VCGs and legacy study reports can be used as a benchmark to evaluate the VCG performance. Replacing concurrent controls of legacy studies with VCGs should ideally reproduce the results of these studies. Based on three four-week rat oral toxicity legacy studies with varying degrees of toxicity findings we developed a concept to evaluate VCG performance on different levels: the ability of VCGs to (i) reproduce statistically significant deviations from the concurrent control, (ii) reproduce test substance-related effects, and (iii) reproduce the conclusion of the toxicity study in terms of threshold dose, target organs, toxicological biomarkers (clinical pathology) and reversibility. Although VCGs have shown a low to moderate ability to reproduce statistical results, the general study conclusions remained unchanged. Our results provide a first indication that carefully selected historical control data can be used to replace concurrent control without impairing the general study conclusion. Additionally, the developed procedures and workflows lay the foundation for the future validation of virtual controls for a use in regulatory toxicology.

Quantitative Systems Pharmacology and Machine Learning: A Match Made in Heaven or Hell?

As pharmaceutical development moves from early-stage in vitro experimentation to later in vivo and subsequent clinical trials, data and knowledge are acquired across multiple time and length scales, from the subcellular to whole patient cohort scale. Realizing the potential of this data for informing decision making in pharmaceutical development requires the individual and combined application of machine learning (ML) and mechanistic multiscale mathematical modeling approaches. Here we outline how these two approaches, both individually and in tandem, can be applied at different stages of the drug discovery and development pipeline to inform decision making compound development. The importance of discerning between knowledge and data are highlighted in informing the initial use of ML or mechanistic quantitative systems pharmacology (QSP) models. We discuss the application of sensitivity and structural identifiability analyses of QSP models in informing future experimental studies to which ML may be applied, as well as how ML approaches can be used to inform mechanistic model development. Relevant literature studies are highlighted and we close by discussing caveats regarding the application of each approach in an age of constant data acquisition. SIGNIFICANCE STATEMENT: We consider when best to apply machine learning (ML) and mechanistic quantitative systems pharmacology (QSP) approaches in the context of the drug discovery and development pipeline. We discuss the importance of prior knowledge and data available for the system of interest and how this informs the individual and combined application of ML and QSP approaches at each stage of the pipeline.