Search

The International Council for Harmonization (ICH) M7 guideline describes a hazard assessment process for impurities that have the potential to be present in a drug substance or drug product. In the absence of adequate experimental bacterial mutagenicity data, (Q)SAR analysis may be used as a test to predict impurities' DNA reactive (mutagenic) potential. However, in certain situations, (Q)SAR software is unable to generate a positive or negative prediction either because of conflicting information or because the impurity is outside the applicability domain of the model. Such results present challenges in generating an overall mutagenicity prediction and highlight the importance of performing a thorough expert review. The following paper reviews pharmaceutical and regulatory experiences handling such situations. The paper also presents an analysis of proprietary data to help understand the likelihood of misclassifying a mutagenic impurity as non-mutagenic based on different combinations of (Q)SAR results. This information may be taken into consideration when supporting the (Q)SAR results with an expert review, especially when out-of-domain results are generated during a (Q)SAR evaluation.

Primary aromatic amines (pAAs) are attractive building blocks in medicinal chemistry programmes yet their potential for mutagenic activity causes real concern owing to the risk of genotoxicity-related drug attrition. In addition, despite the existence of a substantial body of experimental data, the prediction of aromatic amine mutagenicity still poses a significant challenge for in silico tools. Major contributors to this dilemma are the stability and physicochemical properties of a subset of aromatic amines that affords them capricious mutagenic properties in the Ames test. Such inconsistent mutagenic potential is also compounded by the inherent variability with the assay itself and underscores the need for a rigorous approach in executing the experimental protocol. In order to understand the utility of the in silico approach towards the prediction of pAAs mutagenicity and to widen the availability of mutagenicity data, a group of pharmaceutical companies has formed a consortium with the aim of exchanging their in-house data and making them publicly available for the first time. Summary data compiled during the first phase of this effort is disclosed here and its utility in conjunction with in silico prediction is discussed. Conclusions from this analysis highlight the critical role of expert judgement in rationalizing the experimental activity seen in the Ames test with predictions from in silico models. This collaboration demonstrates the value of sharing such data pre-competitively to aid in both the selection of Ames negative building blocks for drug development while simultaneously helping to develop better in silico tools.

The present publication surveys several applications of in silico (i.e., computational) toxicology approaches across different industries and institutions. It highlights the need to develop standardized protocols when conducting toxicity-related predictions. This contribution articulates the information needed for protocols to support in silico predictions for major toxicological endpoints of concern (e.g., genetic toxicity, carcinogenicity, acute toxicity, reproductive toxicity, developmental toxicity) across several industries and regulatory bodies. Such novel in silico toxicology (IST) protocols, when fully developed and implemented, will ensure in silico toxicological assessments are performed and evaluated in a consistent, reproducible, and well-documented manner across industries and regulatory bodies to support wider uptake and acceptance of the approaches. The development of IST protocols is an initiative developed through a collaboration among an international consortium to reflect the state-of-the-art in in silico toxicology for hazard identification and characterization. A general outline for describing the development of such protocols is included and it is based on in silico predictions and/or available experimental data for a defined series of relevant toxicological effects or mechanisms. The publication presents a novel approach for determining the reliability of in silico predictions alongside experimental data. In addition, we discuss how to determine the level of confidence in the assessment based on the relevance and reliability of the information.

Developing new small molecules that are bioactive is time-consuming, costly and rarely successful. As a mitigation strategy, we apply, for the first time, generative adversarial networks to de novo design of small molecules using a phenotype-based drug discovery approach. We trained our model on a set of 30,000 compounds and their respective morphological profiles extracted from high content images; no target information was used to train the model. Using this approach, we were able to automatically design agonist-like compounds of different molecular targets.

The assessment of skin sensitization has evolved over the past few years to include in vitro assessments of key events along the adverse outcome pathway and opportunistically capitalize on the strengths of in silico methods to support a weight of evidence assessment without conducting a test in animals. While in silico methods vary greatly in their purpose and format; there is a need to standardize the underlying principles on which such models are developed and to make transparent the implications for the uncertainty in the overall assessment. In this contribution, the relationship between skin sensitization relevant effects, mechanisms, and endpoints are built into a hazard assessment framework. Based on the relevance of the mechanisms and effects as well as the strengths and limitations of the experimental systems used to identify them, rules and principles are defined for deriving skin sensitization in silico assessments. Further, the assignments of reliability and confidence scores that reflect the overall strength of the assessment are discussed. This skin sensitization protocol supports the implementation and acceptance of in silico approaches for the prediction of skin sensitization.

Statistical-based and expert rule-based models built using public domain mutagenicity knowledge and data are routinely used for computational (Q)SAR assessments of pharmaceutical impurities in line with the approach recommended in the ICH M7 guideline. Knowledge from proprietary corporate mutagenicity databases could be used to increase the predictive performance for selected chemical classes as well as expand the applicability domain of these (Q)SAR models. This paper outlines a mechanism for sharing knowledge without the release of proprietary data. Primary aromatic amine mutagenicity was selected as a case study because this chemical class is often encountered in pharmaceutical impurity analysis and mutagenicity of aromatic amines is currently difficult to predict. As part of this analysis, a series of aromatic amine substructures were defined and the number of mutagenic and non-mutagenic examples for each chemical substructure calculated across a series of public and proprietary mutagenicity databases. This information was pooled across all sources to identify structural classes that activate or deactivate aromatic amine mutagenicity. This structure activity knowledge, in combination with newly released primary aromatic amine data, was incorporated into Leadscope's expert rule-based and statistical-based (Q)SAR models where increased predictive performance was demonstrated.

Finding new molecules with a desired biological activity is an extremely difficult task. In this context, artificial intelligence and generative models have been used for molecular de novo design and compound optimization. Herein, we report a generative model that bridges systems biology and molecular design, conditioning a generative adversarial network with transcriptomic data. By doing so, we can automatically design molecules that have a high probability to induce a desired transcriptomic profile. As long as the gene expression signature of the desired state is provided, this model is able to design active-like molecules for desired targets without any previous target annotation of the training compounds. Molecules designed by this model are more similar to active compounds than the ones identified by similarity of gene expression signatures. Overall, this method represents an alternative approach to bridge chemistry and biology in the long and difficult road of drug discovery., High quality hit identification remains a considerable challenge in de novo drug design. Here, the authors train a generative adversarial network with transcriptome profiles induced by a large set of compounds, enabling it to design molecules that are likely to induce desired expression profiles.

(Quantitative) structure-activity relationship or (Q)SAR predictions of DNA-reactive mutagenicity are important to support both the design of new chemicals and the assessment of impurities, degradants, metabolites, extractables and leachables, as well as existing chemicals. Aromatic N-oxides represent a class of compounds that are often considered alerting for mutagenicity yet the scientific rationale of this structural alert is not clear and has been questioned. Because aromatic N-oxide-containing compounds may be encountered as impurities, degradants and metabolites, it is important to accurately predict mutagenicity of this chemical class. This article analysed a series of publicly available aromatic N-oxide data in search of supporting information. The article also used a previously developed structure-activity relationship (SAR) fingerprint methodology where a series of aromatic N-oxide substructures was generated and matched against public and proprietary databases, including pharmaceutical data. An assessment of the number of mutagenic and non-mutagenic compounds matching each substructure across all sources was used to understand whether the general class or any specific subclasses appear to lead to mutagenicity. This analysis resulted in a downgrade of the general aromatic N-oxide alert. However, it was determined there were enough public and proprietary data to assign the quindioxin and related chemicals as well as benzo[c][1,2,5]oxadiazole 1-oxide subclasses as alerts. The overall results of this analysis were incorporated into Leadscope's expert-rule-based model to enhance its predictive accuracy.

A seminar and interactive workshop on “In silico Methods – Computational Alternatives to Animal Testing” was held in Berlin, Germany, organized by Annemarie Lang, Frank Butt- gereit and Andrea Volkamer at the Charite-Universitatsmedizin Berlin, on August 17-18, 2017. During the half-day seminar, the variety and applications of in silico methods as alternatives to animal testing were presented with room for scientific discus- sions with experts from academia, industry and the German fed- eral ministry (Fig. 1). Talks on computational systems biology were followed by detailed information on predictive toxicology in order to display the diversity of in silico methods and the potential to embrace them in current approaches (Hartung and Hoffmann, 2009; Luechtefeld and Hartung, 2017). The follow- ing interactive one-day Design Thinking Workshop was aimed at experts, interested researchers and PhD-students interested in the use of in silico as alternative methods to promote the 3Rs (Fig. 2). Forty participants took part in the seminar while the workshop was restricted to sixteen participants.

Endocrine disrupting chemicals raise a lot of interest and concern regarding their risk for human health and the environment. They represent a broad variety of natural and synthetic chemicals with different levels of endocrine activity evaluation. In particular, for high production volume chemicals, new methods are required to enable the evaluation of the vast number of chemicals for their potential to alter the endocrine system and prioritize them for deeper characterization. The ToxCast program from the US EPA provides data from high throughput screening assays to develop computational tools aimed at rapid in vitro bioactivity screening and prioritization. Using publicly available data (ToxCast and ToxRef databases), we evaluate whether in vitro assay evaluations could predict in vivo outcomes observed in rat long-term studies for more than 400 chemicals. We focus on effects observed in three endocrine and two sex accessory organs and 42 in vitro assays related to pathways associated with endocrine related toxicity. First, using simple statistical correlation we demonstrate that there is no mutual linear correlation between the selected in vitro assays and any in vivo outcome, with balanced accuracies around 50% for each assay-outcome pair. Then, by applying machine learning to investigate potential non-linear correlations, we show that the combination of different in vitro assays is not correlated with the long-term in vivo effects and cannot help to predict them since balanced accuracies are also around 50%. Moreover, the prediction based on in vitro assays is not better than the one based on classical QSAR methods. This study highlights that the selected in vitro assays do not provide information about in vivo outcomes observed in endocrine and associated organs in long-term rat in vivo studies and stresses the need for the development of in vitro assays that reflect the compounds’ pharmacokinetic properties.

In silico toxicology (IST) approaches to rapidly assess chemical hazard, and usage of such methods is increasing in all applications but especially for regulatory submissions, such as for assessing chemicals under REACH as well as the ICH M7 guideline for drug impurities. There are a number of obstacles to performing an IST assessment, including uncertainty in how such an assessment and associated expert review should be performed or what is fit for purpose, as well as a lack of confidence that the results will be accepted by colleagues, collaborators and regulatory authorities. To address this, a project to develop a series of IST protocols for different hazard endpoints has been initiated and this paper describes the genetic toxicity in silico (GIST) protocol. The protocol outlines a hazard assessment framework including key effects/mechanisms and their relationships to endpoints such as gene mutation and clastogenicity. IST models and data are reviewed that support the assessment of these effects/mechanisms along with defined approaches for combining the information and evaluating the confidence in the assessment. This protocol has been developed through a consortium of toxicologists, computational scientists, and regulatory scientists across several industries to support the implementation and acceptance of in silico approaches.

At the confluence of predictive and regulatory toxicologies, negative predictions may be the thin green line that prevents populations from being exposed to harm. Here, two novel approaches to making confident and robust negative in silico predictions for mutagenicity (as defined by the Ames test) have been evaluated. Analyses of 12 data sets containing >13,000 compounds, showed that negative predictivity is high (∼90%) for the best approach and features that either reduce the accuracy or certainty of negative predictions are identified as misclassified or unclassified respectively. However, negative predictivity remains high (and in excess of the prevalence of non-mutagens) even in the presence of these features, indicating that they are not flags for mutagenicity.

The relative wealth of bacterial mutagenicity data available in the public literature means that in silico quantitative/qualitative structure activity relationship (QSAR) systems can readily be built for this endpoint. A good means of evaluating the performance of such systems is to use private unpublished data sets, which generally represent a more distinct chemical space than publicly available test sets and, as a result, provide a greater challenge to the model. However, raw performance metrics should not be the only factor considered when judging this type of software since expert interpretation of the results obtained may allow for further improvements in predictivity. Enough information should be provided by a QSAR to allow the user to make general, scientifically-based arguments in order to assess and overrule predictions when necessary. With all this in mind, we sought to validate the performance of the statistics-based in vitro bacterial mutagenicity prediction system Sarah Nexus (version 1.1) against private test data sets supplied by nine different pharmaceutical companies. The results of these evaluations were then analysed in order to identify findings presented by the model which would be useful for the user to take into consideration when interpreting the results and making their final decision about the mutagenic potential of a given compound.

The ICH M7 guidelines for the assessment and control of DNA reactive (mutagenic) impurities in pharmaceuticals allows for the consideration of in silico predictions in place of in vitro studies. This represents a significant advance in the acceptance of (Q)SAR models and has resulted from positive interactions between modellers, regulatory agencies and industry with a shared purpose of developing effective processes to minimise risk. This paper discusses key scientific principles that should be applied when evaluating in silico predictions with a focus on accuracy and scientific rigour that will support a consistent and practical route to regulatory submission.

We describe a method for construction of specific types of Neural Networks composed of structures directly linked to the structure of the molecule under consideration. Each molecule can be represented by a unique neural connectivity problem (graph) which can be programmed onto a Cellular Neural Network. The idea was to translate chemical structures like small organic molecules or peptides into a self learning environment which is CNN based. In the case of small molecules, each cell of the CNN stands for one atom of the molecule under consideration. But in contrast to the standard CNN architecture where each cell is connected to the neighboring cells, only those cells of the feature net are connected for which there also exists a chemical bond in the molecule under consideration. This implies that the feature net topology varies from molecule to molecule. In the case of peptides, the amino acids that form the building blocks of the peptide are reflected by the CNN cells wherein the amino acid sequence defines the network topology. Unlike the standard CNN used for image processing, there are no input values like the input image that are fed into the feature net. Instead, all information about the input molecule is supplied to the feature net by means of the topology. The output of several feature nets is fed into a supervisor neural network which computes the final output value. The combination of several feature nets and a supervisor networks constitutes the Molecular Graph Network (MGN). The designed networks are used for selection of molecules representing wanted properties such as activity against specific diseases, interactions with other compounds, toxicity etc. and possibly being candidates to be tested further as new drugs.

The International Conference on Harmonization (ICH) M7 guidance for the assessment and control of DNA reactive impurities in pharmaceutical products includes the use of in silico prediction systems as part of the hazard identification and risk assessment strategy. This is the first internationally agreed guidance document to include the use of these types of approaches. The guideline requires the use of two complementary approaches, an expert rule-based method and a statistical algorithm. In addition, the guidance states that the output from these computer-based assessments can be reviewed using expert knowledge to provide additional support or resolve conflicting predictions. This approach is designed to maximize the sensitivity for correctly identifying DNA reactive compounds while providing a framework to reduce the number of compounds that need to be synthesized, purified and subsequently tested in an Ames assay. Using a data set of 801 chemicals and pharmaceutical intermediates, we have examined the relative predictive performances of some popular commercial in silico systems that are in common use across the pharmaceutical industry. The overall accuracy of each of these systems was fairly comparable ranging from 68% to 73%; however, the sensitivity of each system (i.e. how many Ames positive compounds are correctly identified) varied much more dramatically from 48% to 68%. We have explored how these systems can be combined under the ICH M7 guidance to enhance the detection of DNA reactive molecules. Finally, using four smaller sets of molecules, we have explored the value of expert knowledge in the review process, especially in cases where the two systems disagreed on their predictions, and the need for care when evaluating the predictions for large data sets.

The ICH M7 guideline describes a consistent approach to identify, categorize, and control DNA reactive, mutagenic, impurities in pharmaceutical products to limit the potential carcinogenic risk related to such impurities. This paper outlines a series of principles and procedures to consider when generating (Q)SAR assessments aligned with the ICH M7 guideline to be included in a regulatory submission. In the absence of adequate experimental data, the results from two complementary (Q)SAR methodologies may be combined to support an initial hazard classification. This may be followed by an assessment of additional information that serves as the basis for an expert review to support or refute the predictions. This paper elucidates scenarios where additional expert knowledge may be beneficial, what such an expert review may contain, and how the results and accompanying considerations may be documented. Furthermore, the use of these principles and procedures to yield a consistent and robust (Q)SAR-based argument to support impurity qualification for regulatory purposes is described in this manuscript.

Hepatotoxicity is one of the most frequently observed adverse effects resulting from exposure to a xenobiotic. For example, in pharmaceutical research and development it is one of the major reasons for drug withdrawals, clinical failures, and discontinuation of drug candidates. The development of faster and cheaper methods to assess hepatotoxicity that are both more sustainable and more informative is critically needed. The biological mechanisms and processes underpinning hepatotoxicity are summarized and experimental approaches to support the prediction of hepatotoxicity are described, including toxicokinetic considerations. The paper describes the increasingly important role of in silico approaches and highlights challenges to the adoption of these methods including the lack of a commonly agreed upon protocol for performing such an assessment and the need for in silico solutions that take dose into consideration. A proposed framework for the integration of in silico and experimental information is provided along with a case study describing how computational methods have been used to successfully respond to a regulatory question concerning non-genotoxic impurities in chemically synthesized pharmaceuticals.

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.