Computational Toxicology

Chapter 14Developing Next Generation Tools for Computational Toxicology

Alex M. Clark¹, Kimberley M. Zorn², Mary A. Lingerfelt² and Sean Ekins²

¹Molecular Materials Informatics, Inc., Montreal, Quebec, Canada

²Collaborations Pharmaceuticals, Inc., Raleigh, NC, USA

Chapter Menu

1. Introduction
2. Developing Apps for Chemistry
3. Green Chemistry
4. Polypharma and Assay Central
5. Conclusion

14.1 Introduction

Public sources of open data from repositories like ChEMBL, PubChem, ToxCast, and so on can represent an ideal starting point for drug discovery and computational toxicology efforts and increasingly these datasets may also be useful for absorption, metabolism, excretion and toxicity (ADMET) modeling. However, this manually curated data is not in a form that is immediately accessible for computational model building. Being able to use transparent computational models simultaneously for visualizing activity trends for multiple targets (for diseases and ADMET) removes the burden of curation or purchasing and maintaining expensive software, and drastically simplifies the addition of new data. It also represents a new frontier of drug discovery as a world of small, agile distributed R&D organizations has access to valuable public datasets that can inform their research. The effort required to preprocess, filter, merge, validate, and normalize the structure and activity data requires a great deal of software expertise and medicinal chemistry domain knowledge, which are key skill sets that ...