Search

Early prediction of safety issues in drug development is at the same time highly desirable and highly challenging. Recent advances emphasize the importance of understanding the whole chain of causal events leading to observable toxic outcomes. Here we describe an integrative modeling strategy based on these ideas that guided the design of eTOXsys, the prediction system used by the eTOX project. Essentially, eTOXsys consists of a central server that marshals requests to a collection of independent prediction models and offers a single user interface to the whole system. Every of such model lives in a self-contained virtual machine easy to maintain and install. All models produce toxicity-relevant predictions on their own but the results of some can be further integrated and upgrade its scale, yielding in vivo toxicity predictions. Technical aspects related with model implementation, maintenance and documentation are also discussed here. Finally, the kind of models currently implemented in eTOXsys is illustrated presenting three example models making use of diverse methodology (3D-QSAR and decision trees, Molecular Dynamics simulations and Linear Interaction Energy theory, and fingerprint-based QSAR).

The technological evolution of the 1990s in both combinatorial chemistry and high-throughput screening created the demand for rapid access to the compound deck to support the screening process. The common strategy within the pharmaceutical industry is to store the screening library in DMSO solution. Several studies have shown that a percentage of these compounds decompose in solution, varying from a few percent of the total to a substantial part of the library. In the COMDECOM (COMpound DECOMposition) project, the compound stability of screening compounds in DMSO solution is monitored in an accelerated thermal, hydrolytic, and oxidative decomposition program. A large database with stability data is collected, and from this database, a predictive model is being developed. The aim of this program is to build an algorithm that can flag compounds that are likely to decompose-information that is considered to be of utmost importance (e.g., in the compound acquisition process and when evaluation screening results of library compounds, as well as in the determination of optimal storage conditions).

The high-quality in vivo preclinical safety data produced by the pharmaceutical industry during drug development, which follows numerous strict guidelines, are mostly not available in the public domain. These safety data are sometimes published as a condensed summary for the few compounds that reach the market, but the majority of studies are never made public and are often difficult to access in an automated way, even sometimes within the owning company itself. It is evident from many academic and industrial examples, that useful data mining and model development requires large and representative data sets and careful curation of the collected data. In 2010, under the auspices of the Innovative Medicines Initiative, the eTOX project started with the objective of extracting and sharing preclinical study data from paper or pdf archives of toxicology departments of the 13 participating pharmaceutical companies and using such data for establishing a detailed, well-curated database, which could then serve as source for read-across approaches (early assessment of the potential toxicity of a drug candidate by comparison of similar structure and/or effects) and training of predictive models. The paper describes the efforts undertaken to allow effective data sharing intellectual property (IP) protection and set up of adequate controlled vocabularies) and to establish the database (currently with over 4000 studies contributed by the pharma companies corresponding to more than 1400 compounds). In addition, the status of predictive models building and some specific features of the eTOX predictive system (eTOXsys) are presented as decision support knowledge-based tools for drug development process at an early stage. The research leading to these results has received support from the Innovative Medicines Initiative Joint Undertaking under grant agreement n° 115002 (eTOX), resources of which are composed of financial contribution from the European Union’s Seventh Framework Programme (FP7/2007-2013) and EFPIA companies’ in kind contributions. The authors would like to formally acknowledge the contribution to the eTOX project of all scientists and other staff involved

Two quantitative pKa prediction models for aliphatic carboxylic acids and for alcohols were developed by multiple linear-regression (MLR) analysis with empirical atomic descriptors. The acid and alcohol molecules were described by a set of five and four atomic descriptors, respectively. For the pKa model of 1122 aliphatic carboxylic acids, the squared correlation coefficient is 0.813 with a standard error of prediction of 0.423; for the pKa model of 288 alcohols, the squared correlation coefficient is 0.817 with a standard error of prediction of 0.755, respectively. The good predictive abilities of the models obtained were indicated by both cross-validation and by external validation. An atomic descriptor was developed to model the inductive effect of the neighboring atoms for a central atom in a molecule. The ability of the descriptor to measure the inductive effect of substituent groups was demonstrated by a good correlation of this descriptor with Taft sigma* constants in aliphatic carboxylic acids. It provides a new approach to estimate Taft sigma* constants directly from molecular structures. An algorithm using Kohonen neural networks for splitting a data set into a training set and a test set is also presented.

The choice of an appropriate structure coding scheme is the secret to success in QSAR studies. Depending on the problem at hand, 2D or 3D descriptors have to be chosen; the consideration of electronic effects might be crucial, conformational flexibility has to be of special concern. Artificial neural networks, both with unsupervised and with supervised learning schemes, are powerful tools for establishing relationships between structure and physical, chemical, or biological properties. The EROS system for the simulation of chemical reactions is briefly presented and its application to the degradation of s -triazine herbicides is shown. It is further shown how the simulation of chemical reactions can be combined with the simulation of infrared spectra for the efficient identification of the structure of degradation products.

Novel ways of coding the structure of chemical compounds are presented and their use for correlating biological activity is explored. These structure codes take account of the three-dimensional arrangement of the atoms in a molecule, or consider molecular surface properties. These molecular representations have been studied with large datasets; various applications to biological activity studies and the definition of chemical diversity will be presented.

Non-clinical safety assessment is often faced with the challenge of assessing candidate compounds with no or insufficient experimental data. Whereas relevant databases and reliable in silico tools exist for mutagenicity prediction, analogous resources for identifying potential organ toxicities are not as common or well developed. Scientists, therefore, have to resort to suboptimal procedures such as literature search and personal experience with similar compounds or classes. In parallel, there is a wealth of relevant data buried in the archives of the pharmaceutical industry that has not yet been leveraged. These data mainly exist in paper or pdf formats and, consequently, are difficult to search and analyze. In order to overcome these limitations and advance early safety assessment, 13 pharmaceutical companies, 11 academic partners and 6 small and medium-sized enterprises (SMEs) joined forces in the eTOX project, which started in January 2010 under the sponsorship of the European Innovative Medicines Initiative (IMI). Since the availability of a wide and representative collection of historical data is fundamental for generating reliable predictions, the main goals of the eTOX project were (i) to build a shared and mineable database containing a broad and relevant collection of data, constituted mainly by repeat-dose toxicity studies contributed by the pharmaceutical companies participating in the project, and (ii) to use the database and other sources of information for enabling more effective read-across and predictive modeling of safety endpoints.