Development of an Infrastructure for the Prediction of Biological Endpoints in Industrial Environments. Lessons Learned at the eTOX Project.

Manuel Pastor,Ferran Sanz,Jordi Quintana

doi:10.3389/fphar.2018.01147

Manuel Pastor, Ferran Sanz + Show 1 more

Open Access

https://doi.org/10.3389/fphar.2018.01147

Copy DOI

Abstract

In silico methods are increasingly being used for assessing the chemical safety of substances, as a part of integrated approaches involving in vitro and in vivo experiments. A paradigmatic example of these strategies is the eTOX project http://www.etoxproject.eu, funded by the European Innovative Medicines Initiative (IMI), which aimed at producing high quality predictions of in vivo toxicity of drug candidates and resulted in generating about 200 models for diverse endpoints of toxicological interest. In an industry-oriented project like eTOX, apart from the predictive quality, the models need to meet other quality parameters related to the procedures for their generation and their intended use. For example, when the models are used for predicting the properties of drug candidates, the prediction system must guarantee the complete confidentiality of the compound structures. The interface of the system must be designed to provide non-expert users all the information required to choose the models and appropriately interpret the results. Moreover, procedures like installation, maintenance, documentation, validation and versioning, which are common in software development, must be also implemented for the models and for the prediction platform in which they are implemented. In this article we describe our experience in the eTOX project and the lessons learned after 7 years of close collaboration between industrial and academic partners. We believe that some of the solutions found and the tools developed could be useful for supporting similar initiatives in the future.

Highlights

In silico methods are increasingly being used in the assessment of the chemical safety of chemicals as a part of integrated approaches, in which computational tools are used to synergically complement the experimental methods, with the aim of generating better and more efficient predictions of the potential toxicological liabilities of the compounds under study (Luechtefeld et al, 2018)
We wish to share our experiences in an aspect that is often overlooked in this kind of projects, which is how to translate predictive models generated by academia or by Small-Medium Enterprises (SMEs) into a production environment where they can be routinely applied
There is an additional difficulty if we intend to use the models in industrial environments, if the structures of the compounds should be treated as confidential

Summary

Introduction

In silico methods are increasingly being used in the assessment of the chemical safety of chemicals as a part of integrated approaches, in which computational tools are used to synergically complement the experimental methods, with the aim of generating better and more efficient predictions of the potential toxicological liabilities of the compounds under study (Luechtefeld et al, 2018). Ambitious collaborative initiatives in this field have been set up with the aim of increasing the availability of relevant data frameworks and developing the aforementioned integrative approaches on top of those data Among these initiatives, EU-ToxRisk (Daneshian et al, 2016), HESS (Sakuratani et al, 2013), TransQST (Maldonado et al, 2017), iPiE (Bravo et al, 2016) and eTOX (Cases et al, 2014; Sanz et al, 2017; Steger-Hartmann and Pognan, 2018) deserve to be highlighted. In the present article we describe the most significant lessons learned in eTOX, describing some of the problems we identified and describing the solutions applied to solve or mitigate them Most of these solutions are the result of long hours of discussion, where we learned to understand each other’s points of view

Results

Discussion

Conclusion