Develop an organoid-based predictive toxicology model [Case study]

SciBite / Knowledge Hub / Resources / Develop an organoid-based predictive toxicology model [Case study]

White-necked Jacobin (Florisuga mellivora)

Discover how a major pharma company was able to develop an organoid-based predictive toxicology model with the support of Elsevier’s domain experts and curated datasets.

Introduction

Historically, companies have relied on animal testing to identify safety issues pre-clinically. However, animal safety data often do not translate well to humans, are costly, and raise ethical concerns. The demand for early-stage safety issue identification in drug development is constrained by the limitations of conducting numerous animal studies simultaneously. To address these challenges, researchers are developing more advanced in silico and in vitro systems aimed at replacing animal research with more accurate, cost-effective, scalable, and reliable alternatives.

In one notable case, a top 10 pharmaceutical company’s R&D toxicology group collaborated with Elsevier to develop an organoid-based predictive toxicology model. Elsevier provided a machine-readable custom data set to support this effort. This data set included a ranked list of drugs with detailed information on the incidence and severity of specific adverse events, which was essential for establishing an evidence-based calibration curve for accurate predictions.

The Challenge:

The R&D toxicology group aimed to develop a predictive toxicology model to assess the likelihood of drug candidates causing a specific adverse event
They needed an extensive list of drugs and their potential to cause the adverse event, but publicly available data were unstructured and difficult to access in bulk

The Solution:

Elsevier provided data harvesting and structuring services, extracting relevant data for a wide variety of FDA-approved drugs
The data included clinical trial, drug-labeling, and post-marketing surveillance information on adverse event incidence and severity
Elsevier cleaned, normalized, and annotated the data to account for various factors such as drug name abbreviations, formulation, dose, route of administration, and therapy type

Impacts for the Company:

Elsevier delivered a custom, annotated data set listing approximately 900 FDA-approved drugs, analyzed and ranked for their adverse effect risk
This saved the client significant time and money and informed a model to screen out compounds likely to fail at the clinical stage
The data provided a foundation for establishing a predictive toxicology model and can be extended to other adverse drug events

Discover how Elsevier helped a top pharma develop an organoid-based predictive toxicology model using comprehensive, custom datasets.

Download

Share this article

Relevant resources, events and news

https://scibite.com/knowledge-hub/resources/datasets-for-drug-discovery-use-case/ thumbnail image

Resource Datasets for drug discovery [Use Case]

Discover trusted datasets for drug discovery to enhance virtual screening, target identification, biomarker prioritization, and treatment assessments.

Datasets