Integrating bioinformatics and chemoinformatics approaches for the development of Expert systems allowing the in silico prediction of toxicities
Integrating bioinformatics and chemoinformatics approaches for the development o


Start Date
End Date
IMI1 - Call 1
Grant agreement number

Type of Action: 
RIA (Research and Innovation Action)

IMI Funding
6 910 018
EFPIA in kind
10 157 590
1 719 500
Total Cost
18 787 108


If we could reliably predict side effects in the initial phases of drug development, this would lower the failure rate in later phases, significantly reduce the number of animal tests needed, and accelerate the development of new drugs. The eTOX project broke ground in that it enabled pharmaceutical companies to share their data on the toxicity of drug-like compounds for the first time on a large scale. This resulted in the creation of a large database, which can now be mined for further insights, including predictions on whether or not a particular compound is likely to have an adverse effect on patients. This is already helping pharmaceutical companies to make better-informed decisions in their pursuit of developing safer drugs, while at the same time reducing the use of animals in drug research.

Studies designed to predict adverse side effects in the initial phases of drug development are very important as they lower the failure rate in later phases, ensuring that companies invest resources in only the most promising drugs, and that only safe drugs reach patients. In order to improve drug safety, the pharmaceutical industry has produced vast amounts of preclinical toxicology data needed to develop compounds into drugs. After fulfilling its initial purpose, this data used to rest in individual companies’ archives, despite the fact that a lot of further knowledge could be extracted from it. However, companies used to consider this data as part of their competitive space, and so kept it to themselves.

By bringing together top experts in toxicology, knowledge management, bioinformatics, chemo-informatics, biostatistics and software development, the eTOX project set out to bring together this treasure trove of toxicological information into one database, so that it could be shared among companies for the first time, and probed for further insights. The result is a unique toxicology information database, eTOXsys, which now contains information from over 8 000 toxicity studies on almost 2 000 compounds, of which around a fifth are approved drugs. The studies done on these compounds amount to about 9 million data points about the toxicology of those compounds. This database is now commercially accessible and can be searched and mined, thanks to the tools that have been built by the academic part of the consortium.

More than 200 predictive computer-based models

Building on this treasure trove of toxicology data, which has been organised and standardised, the consortium further constructed more than 200 predictive computer-based models that have the ability to give researchers an idea of the potential toxicity of future drug-like compounds. These models make their predictions by using the complex relationships between the structure of a substance, its metabolism and disposition, and its toxic effects in the body. They enable researchers to better predict potential side effects that would otherwise only be discovered in a later stage of the drug development or when the drug is already on the market.

These computer models have been annotated in terms of the data and methods used for developing them. The academic partners in the project also developed eTOXlab, a platform for the development and maintenance of these models.

Developing a standardised language

One of the obstacles to extracting further insights from this wealth of toxicology data was that there was no common terminology between different researchers and companies. In order for all this toxicological data to be useful for further analysis, eTOX had to construct standardised terminology (ontologies). As part of this process, project researchers looked over more than 20 million entry lines, reducing more than 80 000 terms used in the initial data sources to under 7 000 preferred terms. These ontologies are now publicly available through the OntoBrowser tool and will be a valuable asset for future research.

Reducing the use of animals in research

The database and models developed within eTOX have also contributed to reducing the use of animals in research. For example, until now, pharmaceutical companies working on similar targets used to synthesise competitor compounds in order to perform laboratory studies to compare the toxicity of competitors’ compounds with their in-house candidates. Since their competitors’ toxicological data can now be found in the eTOXsys database, they no longer need to do this. According to project coordinators, there are already multiple examples of cases where information provided by eTOXsys prevented companies from running new studies on animals.

For the benefit of industry, academia, SMEs

The industry is already benefitting from the tools developed in this project, especially the eTOXsys database. For example, if a company is developing a new compound with a toxicity that is disturbing, their research teams can now go to the database to try to find a similar compound with a similar structure or a similar effect in a similar species. This is already saving time and resources, and allowing drug makers to make better-informed decisions, which could ultimately lead to safer drugs for patients. Thanks to eTOX, the industry also gained access to academic knowledge and skills, which they don’t have internally.

The academic partners have in turn benefited from learning to work together with the pharmaceutical companies, and having access to toxicity data from the industry that they otherwise would not have. The project also enabled them to develop new computer models for predicting the toxicity of drugs, as well as tools and technologies for sharing all this data.

The SMEs in the project benefitted from working with their main customers in the pharmaceutical industry, and getting to know more about who their customers are, what they want, how they think and what they do. Additionally, SMEs have gained a new business as a result of this project: eTOXsys is now commercially available and two SMEs are in charge of maintaining and managing it.

What’s next?

eTOX gave rise to a successor IMI project, eTRANSAFE, which will assess the validity of the predictive value of animal data for human safety. This successor project has the potential to modify the way researchers conduct preclinical studies, and could potentially have an even bigger impact than eTOX.

Read the interview with project coordinators

Achievements & News

‘We found a way to share the unsharable’ – an interview with the eTOX project coordinators
September 2018

If we could reliably predict side effects in the initial phases of drug development, this would lower the failure rate in later phases, significantly reduce the number of animal tests needed, and accelerate the development of new drugs. The eTOX project broke new ground in that it enabled pharmaceutical companies to share their data on the toxicity of drug-like compounds for the first time on a large scale. ###This resulted in the creation of a large database, which can now be mined for further insights, including predictions on whether or not a particular compound is likely to have an adverse effect on patients. In an interview with the IMI Programme Office, project coordinator Francois Pognan of Novartis, and academic coordinator Ferran Sanz of Institut Hospital del Mar d'Investigacions Mèdiques, explain how the tools developed by the project are already helping pharmaceutical companies make better-informed decisions in their pursuit of developing safer drugs for patients. ‘Just the fact that we were able to share all this data between companies, who are normally competitors, is a big achievement,' said Pognan. ‘We found a way to share the unsharable.’

Safety project eTOX showcases legacy
November 2017

Scientists from IMI’s safety project eTOX have described their impressive legacy in a paper in Nature Reviews Drug Discovery. The heart of the project was an immense, shared database based on information provided by EFPIA companies from their own preclinical drug toxicity studies. By the end of the project, the database had information from over 8 000 toxicity studies on almost 2 000 compounds, of which around a fifth are approved drugs. ### The team used the database to build 200 computer-based models that provide a probability of the likelihood that compounds will interact with molecular targets or be toxic to vital organs like the heart or liver. The tools, which were validated by project partners, display their results in way that makes them easy to visualise and interpret. eTOX partners are now using the database and tools in their daily work. As they are computer-based, the tools could also help to reduce the use of animals in research. In the paper, the researchers explain how they addressed the pharmaceutical companies’ concerns about sharing their data: ‘This required a combination of legal (consortium agreement), technical (database installed behind companies' firewalls and models implemented within self-contained virtual machines), organizational (the 'honest broker' concept), psychological (trust gained through collaboration), political (data-sharing pressure, such as the FAIR (Findability, Accessibility, Interoperability and Reusability) principles) and social (snowball effect) solutions.’ Today, the work begun under eTOX continues through other projects, including TransQST and eTRANSAFE.

AstraZeneca opens up preclinical safety data to scientific community
September 2017

Part of AstraZeneca’s contribution to the IMI project eTOX was in the form of extensive data on the safety/toxicity profiles of (potential) medicines.### Now, the company has decided to make the data provided to eTOX available to the wider scientific community through the company’s Open Innovation portal. ‘Following on from the success of the eTOX project, we are keen to further broaden access to our preclinical safety data in order to help advance the mechanistic understanding and prediction of drug safety and bring safer medicines to patients faster,’ said AstraZeneca’s Nigel Greene. In a statement on the project website, the eTOX team notes that the project ‘has signified a paradigm change in the pharmaceutical industry’s willingness to openly share legacy data for the benefit of the wider toxicology community’. The eTOX project resulted in a number of tools for toxicologists, many of which have been made available to the wider scientific community.

eTOX in the spotlight in special issue of Molecular Informatics
March 2013

IMI’s drug toxicity project eTOX features in a special issue of the journal Molecular Informatics dedicated to advances in computational technology, a field where eTOX is making significant progress with its computer-based tools and models to predict drug toxicity.### The challenges in the field are set out in a guest editorial by eTOX team member Thomas Steger-Hartmann of Bayer. The issue itself includes two contributions from eTOX. One article  presents the eTOX public library, which is described as ‘a useful resource for affording the in silico toxicity prediction of novel drug candidates’. A second article discusses the challenge of screening potential drugs for unintended side effects.

eTOX explains ontologies
November 2012

One of the goals of IMI project eTOX is to predict safety issues in silico (i.e. using computer models) by learning from companies’ existing preclinical data. The extraction of reports containing this data is now well advanced, raising the issue of standardisation.### The question facing eTOX is: how can the project make sure that everybody uses the same term to describe the same thing? The answer lies in  ontologies: the description of preferred terms and synonyms to be used in various places, as well as the relationships between the terms. Within eTOX, many ontologies are employed. Some of these are already available in the public domain in order to increase interoperability, while others have been created by the consortium because nothing was available yet. These new ontologies will be released into the public domain and discussed with interested partners (e.g. CDISC and IMI project OpenPhacts). The consortium will also release its annotation software, the first truly collaborative interface dedicated to crowd sourcing of ontology annotations.

eTOX library goes public
October 2012

Since its launch in April 2010, IMI toxicology project eTOX has been compiling a vast library of information and data on the toxicology field.### Now the project team has decided to make its eTOX Library available to the public, so that scientists outside eTOX can benefit from it. The library has three sections. Under Articles, the project provides links to relevant journal articles; each reference has a list of keywords and a synopsis highlighting the article’s relevance to eTOX’s goals. The Journals section includes links to journals that cover toxicology issues, and the Links section includes links to public databases, computer modelling tools, projects, and more. For their part, eTOX researchers are using the library to identify new data that can be integrated into the project’s databases, find out about new computational models, and identify potential drug targets and biological markers relevant to toxicity. The library is updated regularly.

eTOX makes progress on predictive toxicology
April 2012

IMI project eTOX is making progress towards its goal of developing a predictive toxicology system called eTOXsys, which is now at the prototype stage.### In a recent article in the International Journal of Molecular Sciences, the eTOX partners describe eTOXsys as 'a software tool able to provide useful toxicological risk and hazard assessment.' Users will simply need to enter a small amount of information, such as the structure of the compound they are interested in, and the system will use a series of advanced models to deliver information on the likelihood of potential toxicity of the compound. The system will base its risk assessment on predictive tools built on data held in diverse databases, coming from public sources and, most notably, legacy toxicity reports held by participating pharmaceutical companies, in what constitutes an unprecedented concerted effort at the international level. The data is currently being extracted, formatted and analysed by tools developed by the eTOX project. According to the project team, eTOXsys should significantly improve the quality of the current state of the art when it comes to computational predictions of the toxicity of new drug candidates.

eTOX SMEs speak out
October 2011

Four small and medium-sized enterprises (SMEs) working on IMI’s eTOX project have highlighted the importance of their contribution to the project in a letter published in Nature Biotechnology.### In their letter, the four SMEs note that they all have a proven track record for scientific innovation and possess state of the art technologies that are considered ‘innovative and valuable’ to achieve the project’s goals.The companies state that they: ‘represent an expert ensemble of innovative biochemoinformatics companies and thus offer an optimal complement to the rest of the eTOX consortium that will ensure that novel approaches to predictive toxicology are developed and implemented in an efficient integrated system’. They also note that in their opinion, ‘EFPIA members’ access to SME’s [intellectual property] should not be considered an argument against, or limitation when, applying to an IMI project’.

eTOX in heart toxicity test breakthrough
May 2011

Scientists in the IMI project eTOX  have developed a computer model to test potential medicines for cardiotoxicity. Currently, many promising drug candidates fail because they turn out to cause serious heart problems in patients.### The new eTOX system should help researchers pick up on these problems earlier on in the drug development process. Users simply have to enter the molecular formula of the compound into the tool, and the system generates a simulated ECG (electrocardiograph). Clinicians routinely use ECGs to diagnose heart problems in their patients; in the same way, users can study the simulated ECG generated by the eTOX system to determine whether or not a compound is toxic to the heart. ‘It provides better results than the currently used computational systems,’ commented eTOX project coordinator Ferran Sanz of Fundació IMIM in Spain. Details of the new tool are published in the Journal of Chemical Information and Modelling.

Participants Show participants on map

EFPIA companies
  • Astrazeneca AB, Södertälje, Sweden
  • Bayer Pharma AG, Berlin, Germany
  • Boehringer Ingelheim Internationalgmbh, Ingelheim, Germany
  • Esteve Pharmaceuticals, SA, Barcelona, Spain
  • F. Hoffmann-La Roche AG, Basel, Switzerland
  • Glaxosmithkline Research And Development LTD., Brentford, Middlesex, United Kingdom
  • H. Lundbeck As, Valby, Denmark
  • Institut De Recherches Internationales Servier Iris, Suresnes, France
  • Janssen Pharmaceutica Nv, Beerse, Belgium
  • Novartis Pharma AG, Basel, Switzerland
  • Pfizer Limited, Sandwich, Kent , United Kingdom
  • Sanofi-Aventis Deutschland GMBH, Frankfurt / Main, Germany
  • UCB Pharma SA, Brussels, Belgium
Universities, research organisations, public bodies, non-profit groups
  • Danmarks Tekniske Universitet, Kgs. Lyngby, Denmark
  • Erasmus Universitair Medisch Centrum Rotterdam, Rotterdam, Netherlands
  • European Molecular Biology Laboratory, Heidelberg, Germany
  • Fraunhofer Gesellschaft Zur Forderung Der Angewandten Forschung Ev, München, Germany
  • Fundacio Institut Hospital Del Mar D Investigacions Mediques, Barcelona, Spain
  • Fundacion Sector Publico Estatal Centro Nacional Investigaciones Oncologicas Carlos Iii, Madrid, Spain
  • Lhasa Limited, Leeds, United Kingdom
  • Liverpool John Moores University, Liverpool, United Kingdom
  • Stichting Vu, Amsterdam, Netherlands
  • Universitat Politecnica De Valencia, Valencia, Spain
  • Universitat Wien, Vienna, Austria
  • University Of Leicester, Leicester, United Kingdom
Small and medium-sized enterprises (SMEs)
  • Chemotargets S.L., Barcelona, Spain
  • Inte:Ligand Software-Entwicklungs-Und Consulting GMBH, Vienna, Austria
  • Lead Molecular Design S.L., Sant Cugat del Vallès, Spain
  • Molecular Networks GMBH Computerchemie, Erlangen, Germany
  • Synapse Research Management Partners SL, Barcelona, Spain
Third parties
  • Consorcio Mar Parc De Salut De Barcelona, Barcelona, Spain
  • Universidad Pompeu Fabra, Barcelona, Spain
Project coordinator
François Pognan
Novartis Pharma AG
Managing entity
Ferran Sanz
Fundació Institut Mar d'investigacions Mèdiques lMlM