Search

Abstract Background Semantic web technologies are finding their way into the life sciences. Ontologies and semantic markup have already been used for more than a decade in molecular sciences, but have not found widespread use yet. The semantic web technology Resource Description Framework (RDF) and related methods show to be sufficiently versatile to change that situation. Results The work presented here focuses on linking RDF approaches to existing molecular chemometrics fields, including cheminformatics, QSAR modeling and proteochemometrics. Applications are presented that link RDF technologies to methods from statistics and cheminformatics, including data aggregation, visualization, chemical identification, and property prediction. They demonstrate how this can be done using various existing RDF standards and cheminformatics libraries. For example, we show how IC50 and Ki values are modeled for a number of biological targets using data from the ChEMBL database. Conclusions We have shown that existing RDF standards can suitably be integrated into existing molecular chemometrics methods. Platforms that unite these technologies, like Bioclipse, makes this even simpler and more transparent. Being able to create and share workflows that integrate data aggregation and analysis (visual and statistical) is beneficial to interoperability and reproducibility. The current work shows that RDF approaches are sufficiently powerful to support molecular chemometrics workflows.

Abstract Background Toxicity is a complex phenomenon involving the potential adverse effect on a range of biological functions. Predicting toxicity involves using a combination of experimental data (endpoints) and computational methods to generate a set of predictive models. Such models rely strongly on being able to integrate information from many sources. The required integration of biological and chemical information sources requires, however, a common language to express our knowledge ontologically, and interoperating services to build reliable predictive toxicology applications. Findings This article describes progress in extending the integrative bio- and cheminformatics platform Bioclipse to interoperate with OpenTox, a semantic web framework which supports open data exchange and toxicology model building. The Bioclipse workbench environment enables functionality from OpenTox web services and easy access to OpenTox resources for evaluating toxicity properties of query molecules. Relevant cases and interfaces based on ten neurotoxins are described to demonstrate the capabilities provided to the user. The integration takes advantage of semantic web technologies, thereby providing an open and simplifying communication standard. Additionally, the use of ontologies ensures proper interoperation and reliable integration of toxicity information from both experimental and computational sources. Conclusions A novel computational toxicity assessment platform was generated from integration of two open science platforms related to toxicology: Bioclipse, that combines a rich scriptable and graphical workbench environment for integration of diverse sets of information sources, and OpenTox, a platform for interoperable toxicology data and computational services. The combination provides improved reliability and operability for handling large data sets by the use of the Open Standards from the OpenTox Application Programming Interface. This enables simultaneous access to a variety of distributed predictive toxicology databases, and algorithm and model resources, taking advantage of the Bioclipse workbench handling the technical layers.

Abstract Background The Blue Obelisk movement was established in 2005 as a response to the lack of Open Data, Open Standards and Open Source (ODOSOS) in chemistry. It aims to make it easier to carry out chemistry research by promoting interoperability between chemistry software, encouraging cooperation between Open Source developers, and developing community resources and Open Standards. Results This contribution looks back on the work carried out by the Blue Obelisk in the past 5 years and surveys progress and remaining challenges in the areas of Open Data, Open Standards, and Open Source in chemistry. Conclusions We show that the Blue Obelisk has been very successful in bringing together researchers and developers with common interests in ODOSOS, leading to development of many useful resources freely available to the chemistry community.

Abstract Background Compound profiling and drug screening generates large amounts of data and is generally based on microplate assays. Current information systems used for handling this are mainly commercial, closed source, expensive, and heavyweight and there is a need for a flexible lightweight open system for handling plate design, and validation and preparation of data. Results A Bioclipse plugin consisting of a client part and a relational database was constructed. A multiple-step plate layout point-and-click interface was implemented inside Bioclipse. The system contains a data validation step, where outliers can be removed, and finally a plate report with all relevant calculated data, including dose-response curves. Conclusions Brunn is capable of handling the data from microplate assays. It can create dose-response curves and calculate IC50 values. Using a system of this sort facilitates work in the laboratory. Being able to reuse already constructed plates and plate layouts by starting out from an earlier step in the plate layout design process saves time and cuts down on error sources.

Abstract Background Predicting metabolic sites is important in the drug discovery process to aid in rapid compound optimisation. No interactive tool exists and most of the useful tools are quite expensive. Results Here a fast and reliable method to analyse ligands and visualise potential metabolic sites is presented which is based on annotated metabolic data, described by circular fingerprints. The method is available via the graphical workbench Bioclipse, which is equipped with advanced features in cheminformatics. Conclusions Due to the speed of predictions (less than 50 ms per molecule), scientists can get real time decision support when editing chemical structures. Bioclipse is a rich client, which means that all calculations are performed on the local computer and do not require network connection. Bioclipse and MetaPrint2D are free for all users, released under open source licenses, and available from http://www.bioclipse.net.

Abstract Background QSAR is a widely used method to relate chemical structures to responses or properties based on experimental observations. Much effort has been made to evaluate and validate the statistical modeling in QSAR, but these analyses treat the dataset as fixed. An overlooked but highly important issue is the validation of the setup of the dataset, which comprises addition of chemical structures as well as selection of descriptors and software implementations prior to calculations. This process is hampered by the lack of standards and exchange formats in the field, making it virtually impossible to reproduce and validate analyses and drastically constrain collaborations and re-use of data. Results We present a step towards standardizing QSAR analyses by defining interoperable and reproducible QSAR datasets, consisting of an open XML format (QSAR-ML) which builds on an open and extensible descriptor ontology. The ontology provides an extensible way of uniquely defining descriptors for use in QSAR experiments, and the exchange format supports multiple versioned implementations of these descriptors. Hence, a dataset described by QSAR-ML makes its setup completely reproducible. We also provide a reference implementation as a set of plugins for Bioclipse which simplifies setup of QSAR datasets, and allows for exporting in QSAR-ML as well as old-fashioned CSV formats. The implementation facilitates addition of new descriptor implementations from locally installed software and remote Web services; the latter is demonstrated with REST and XMPP Web services. Conclusions Standardized QSAR datasets open up new ways to store, query, and exchange data for subsequent analyses. QSAR-ML supports completely reproducible creation of datasets, solving the problems of defining which software components were used and their versions, and the descriptor ontology eliminates confusions regarding descriptors by defining them crisply. This makes is easy to join, extend, combine datasets and hence work collectively, but also allows for analyzing the effect descriptors have on the statistical model's performance. The presented Bioclipse plugins equip scientists with graphical tools that make QSAR-ML easily accessible for the community.

Abstract Background The omics fields promise to revolutionize our understanding of biology and biomedicine. However, their potential is compromised by the challenge to analyze the huge datasets produced. Analysis of omics data is plagued by the curse of dimensionality, resulting in imprecise estimates of model parameters and performance. Moreover, the integration of omics data with other data sources is difficult to shoehorn into classical statistical models. This has resulted in ad hoc approaches to address specific problems. Results We present a general approach to omics data analysis that alleviates these problems. By combining eScience and Bayesian methods, we retrieve scientific information and data from multiple sources and coherently incorporate them into large models. These models improve the accuracy of predictions and offer new insights into the underlying mechanisms. This "eScience-Bayes" approach is demonstrated in two proof-of-principle applications, one for breast cancer prognosis prediction from transcriptomic data and one for protein-protein interaction studies based on proteomic data. Conclusions Bayesian statistics provide the flexibility to tailor statistical models to the complex data structures in omics biology as well as permitting coherent integration of multiple data sources. However, Bayesian methods are in general computationally demanding and require specification of possibly thousands of prior distributions. eScience can help us overcome these difficulties. The eScience-Bayes thus approach permits us to fully leverage on the advantages of Bayesian methods, resulting in models with improved predictive performance that gives more information about the underlying biological system.

Abstract Background Contemporary biological research integrates neighboring scientific domains to answer complex questions in fields such as systems biology and drug discovery. This calls for tools that are intuitive to use, yet flexible to adapt to new tasks. Results Bioclipse is a free, open source workbench with advanced features for the life sciences. Version 2.0 constitutes a complete rewrite of Bioclipse, and delivers a stable, scalable integration platform for developers and an intuitive workbench for end users. All functionality is available both from the graphical user interface and from a built-in novel domain-specific language, supporting the scientist in interdisciplinary research and reproducible analyses through advanced visualization of the inputs and the results. New components for Bioclipse 2 include a rewritten editor for chemical structures, a table for multiple molecules that supports gigabyte-sized files, as well as a graphical editor for sequences and alignments. Conclusion Bioclipse 2 is equipped with advanced tools required to carry out complex analysis in the fields of bio- and cheminformatics. Developed as a Rich Client based on Eclipse, Bioclipse 2 leverages on today's powerful desktop computers for providing a responsive user interface, but also takes full advantage of the Web and networked (Web/Cloud) services for more demanding calculations or retrieval of data. The fact that Bioclipse 2 is based on an advanced and widely used service platform ensures wide extensibility, making it easy to add new algorithms, visualizations, as well as scripting commands. The intuitive tools for end users and the extensible architecture make Bioclipse 2 ideal for interdisciplinary and integrative research. Bioclipse 2 is released under the Eclipse Public License (EPL), a flexible open source license that allows additional plugins to be of any license. Bioclipse 2 is implemented in Java and supported on all major platforms; Source code and binaries are freely available at http://www.bioclipse.net.

Abstract Background Life sciences make heavily use of the web for both data provision and analysis. However, the increasing amount of available data and the diversity of analysis tools call for machine accessible interfaces in order to be effective. HTTP-based Web service technologies, like the Simple Object Access Protocol (SOAP) and REpresentational State Transfer (REST) services, are today the most common technologies for this in bioinformatics. However, these methods have severe drawbacks, including lack of discoverability, and the inability for services to send status notifications. Several complementary workarounds have been proposed, but the results are ad-hoc solutions of varying quality that can be difficult to use. Results We present a novel approach based on the open standard Extensible Messaging and Presence Protocol (XMPP), consisting of an extension (IO Data) to comprise discovery, asynchronous invocation, and definition of data types in the service. That XMPP cloud services are capable of asynchronous communication implies that clients do not have to poll repetitively for status, but the service sends the results back to the client upon completion. Implementations for Bioclipse and Taverna are presented, as are various XMPP cloud services in bio- and cheminformatics. Conclusion XMPP with its extensions is a powerful protocol for cloud services that demonstrate several advantages over traditional HTTP-based Web services: 1) services are discoverable without the need of an external registry, 2) asynchronous invocation eliminates the need for ad-hoc solutions like polling, and 3) input and output types defined in the service allows for generation of clients on the fly without the need of an external semantics description. The many advantages over existing technologies make XMPP a highly interesting candidate for next generation online services in bioinformatics.

Abstract Background There has been recent concern regarding the inability of predictive modeling approaches to generalize to new data. Some of the problems can be attributed to improper methods for model selection and assessment. Here, we have addressed this issue by introducing a novel and general framework, the C1C2, for simultaneous model selection and assessment. The framework relies on a partitioning of the data in order to separate model choice from model assessment in terms of used data. Since the number of conceivable models in general is vast, it was also of interest to investigate the employment of two automatic search methods, a genetic algorithm and a brute-force method, for model choice. As a demonstration, the C1C2 was applied to simulated and real-world datasets. A penalized linear model was assumed to reasonably approximate the true relation between the dependent and independent variables, thus reducing the model choice problem to a matter of variable selection and choice of penalizing parameter. We also studied the impact of assuming prior knowledge about the number of relevant variables on model choice and generalization error estimates. The results obtained with the C1C2 were compared to those obtained by employing repeated K-fold cross-validation for choosing and assessing a model. Results The C1C2 framework performed well at finding the true model in terms of choosing the correct variable subset and producing reasonable choices for the penalizing parameter, even in situations when the independent variables were highly correlated and when the number of observations was less than the number of variables. The C1C2 framework was also found to give accurate estimates of the generalization error. Prior information about the number of important independent variables improved the variable subset choice but reduced the accuracy of generalization error estimates. Using the genetic algorithm worsened the model choice but not the generalization error estimates, compared to using the brute-force method. The results obtained with repeated K-fold cross-validation were similar to those produced by the C1C2 in terms of model choice, however a lower accuracy of the generalization error estimates was observed. Conclusion The C1C2 framework was demonstrated to work well for finding the true model within a penalized linear model class and accurately assess its generalization error, even for datasets with many highly correlated independent variables, a low observation-to-variable ratio, and model assumption deviations. A complete separation of the model choice and the model assessment in terms of data used for each task improves the estimates of the generalization error.

Abstract Background A major obstacle in treatment of HIV is the ability of the virus to mutate rapidly into drug-resistant variants. A method for predicting the susceptibility of mutated HIV strains to antiviral agents would provide substantial clinical benefit as well as facilitate the development of new candidate drugs. Therefore, we used proteochemometrics to model the susceptibility of HIV to protease inhibitors in current use, utilizing descriptions of the physico-chemical properties of mutated HIV proteases and 3D structural property descriptions for the protease inhibitors. The descriptions were correlated to the susceptibility data of 828 unique HIV protease variants for seven protease inhibitors in current use; the data set comprised 4792 protease-inhibitor combinations. Results The model provided excellent predictability (R2 = 0.92, Q2 = 0.87) and identified general and specific features of drug resistance. The model's predictive ability was verified by external prediction in which the susceptibilities to each one of the seven inhibitors were omitted from the data set, one inhibitor at a time, and the data for the six remaining compounds were used to create new models. This analysis showed that the over all predictive ability for the omitted inhibitors was Q2 inhibitors = 0.72. Conclusion Our results show that a proteochemometric approach can provide generalized susceptibility predictions for new inhibitors. Our proteochemometric model can directly analyze inhibitor-protease interactions and facilitate treatment selection based on viral genotype. The model is available for public use, and is located at HIV Drug Research Centre.

Abstract Background There is a need for software applications that provide users with a complete and extensible toolkit for chemo- and bioinformatics accessible from a single workbench. Commercial packages are expensive and closed source, hence they do not allow end users to modify algorithms and add custom functionality. Existing open source projects are more focused on providing a framework for integrating existing, separately installed bioinformatics packages, rather than providing user-friendly interfaces. No open source chemoinformatics workbench has previously been published, and no sucessful attempts have been made to integrate chemo- and bioinformatics into a single framework. Results Bioclipse is an advanced workbench for resources in chemo- and bioinformatics, such as molecules, proteins, sequences, spectra, and scripts. It provides 2D-editing, 3D-visualization, file format conversion, calculation of chemical properties, and much more; all fully integrated into a user-friendly desktop application. Editing supports standard functions such as cut and paste, drag and drop, and undo/redo. Bioclipse is written in Java and based on the Eclipse Rich Client Platform with a state-of-the-art plugin architecture. This gives Bioclipse an advantage over other systems as it can easily be extended with functionality in any desired direction. Conclusion Bioclipse is a powerful workbench for bio- and chemoinformatics as well as an advanced integration platform. The rich functionality, intuitive user interface, and powerful plugin architecture make Bioclipse the most advanced and user-friendly open source workbench for chemo- and bioinformatics. Bioclipse is released under Eclipse Public License (EPL), an open source license which sets no constraints on external plugin licensing; it is totally open for both open source plugins as well as commercial ones. Bioclipse is freely available at http://www.bioclipse.net.

Modern quantitative image analysis techniques have enabled high-throughput, high-content imaging experiments. Image-based profiling leverages the rich information in images to identify similarities or differences among biological samples, rather than measuring a few features, as in high-content screening. Here, we review a decade of advancements and applications of Cell Painting, a microscopy-based cell-labeling assay aiming to capture a cell's state, introduced in 2013 to optimize and standardize image-based profiling. Cell Painting's ability to capture cellular responses to various perturbations has expanded owing to improvements in the protocol, adaptations for different perturbations, and enhanced methodologies for feature extraction, quality control, and batch-effect correction. Cell Painting is a versatile tool that has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects. Future advances will likely involve computational and experimental techniques, new publicly available datasets, and integration with other high-content data types., Competing Interests: Competing interests: S. Singh and A.E.C. serve as scientific advisors for companies that use image-based profiling and Cell Painting (A.E.C.: Recursion, SyzOnc, Quiver Bioscience; S. Singh: Waypoint Bio, Dewpoint Therapeutics, DeepCell) and receive honoraria for occasional talks at pharmaceutical and biotechnology companies. J.C.P. and O.S. declare ownership in Phenaros Pharmaceuticals. M.-A.T. and N.G. were formerly employed at AstraZeneca. M.-A.T. and N.G. are currently employed at Recursion Pharmaceuticals. The remaining authors declare no competing interests., (© 2024. Springer Nature America, Inc.)

Drug-induced liver injury (DILI) has been a significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. Over the last decade, the existing suite of in vitro proxy-DILI assays has generally improved at identifying compounds with hepatotoxicity. However, there is considerable interest in enhancing the in silico prediction of DILI because it allows for evaluating large sets of compounds more quickly and cost-effectively, particularly in the early stages of projects. In this study, we aim to study ML models for DILI prediction that first predict nine proxy-DILI labels and then use them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 888 compounds from the DILI data set (composed of DILIst and DILIrank) and tested them on a held-out external test set of 223 compounds from the DILI data set. The best model, DILIPredictor, attained an AUC-PR of 0.79. This model enabled the detection of the top 25 toxic compounds (2.68 LR+, positive likelihood ratio) compared to models using only structural features (1.65 LR+ score). Using feature interpretation from DILIPredictor, we identified the chemical substructures causing DILI and differentiated cases of DILI caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as nontoxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity and the potential for mechanism evaluation. DILIPredictor required only chemical structures as input for prediction and is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download.

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress in deep neural networks. This review highlights AI's role in analysis of HCI data from fixed and live-cell imaging, enabling novel label-free and multi-channel fluorescent screening methods, and improving compound profiling. HCI experiments are rapid and cost-effective, facilitating large data set accumulation for AI model training. However, the success of AI in drug discovery also depends on high-quality data, reproducible experiments, and robust validation to ensure model performance. Despite challenges like the need for annotated compounds and managing vast image data, AI's potential in phenotypic screening and drug profiling is significant. Future improvements in AI, including increased interpretability and integration of multiple modalities, are expected to solidify AI and HCI's role in drug discovery., Competing Interests: Declaration of competing interest OS and JCP declare ownership in Phenaros Pharmaceuticals AB, a company exploiting AI, automation and HCI for drug discovery., (Copyright © 2024 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Conformal prediction has seen many applications in pharmaceutical science, being able to calibrate outputs of machine learning models and producing valid prediction intervals. We here present the open source software CPSign that is a complete implementation of conformal prediction for cheminformatics modeling. CPSign implements inductive and transductive conformal prediction for classification and regression, and probabilistic prediction with the Venn-ABERS methodology. The main chemical representation is signatures but other types of descriptors are also supported. The main modeling methodology is support vector machines (SVMs), but additional modeling methods are supported via an extension mechanism, e.g. DeepLearning4J models. We also describe features for visualizing results from conformal models including calibration and efficiency plots, as well as features to publish predictive models as REST services. We compare CPSign against other common cheminformatics modeling approaches including random forest, and a directed message-passing neural network. The results show that CPSign produces robust predictive performance with comparative predictive efficiency, with superior runtime and lower hardware requirements compared to neural network based models. CPSign has been used in several studies and is in production-use in multiple organizations. The ability to work directly with chemical input files, perform descriptor calculation and modeling with SVM in the conformal prediction framework, with a single software package having a low footprint and fast execution time makes CPSign a convenient and yet flexible package for training, deploying, and predicting on chemical data. CPSign can be downloaded from GitHub at https://github.com/arosbio/cpsign .Scientific contribution CPSign provides a single software that allows users to perform data preprocessing, modeling and make predictions directly on chemical structures, using conformal and probabilistic prediction. Building and evaluating new models can be achieved at a high abstraction level, without sacrificing flexibility and predictive performance-showcased with a method evaluation against contemporary modeling approaches, where CPSign performs on par with a state-of-the-art deep learning based model., (© 2024. The Author(s).)

In the European regulatory context, rodent in vivo studies are the predominant source of neurotoxicity information. Although they form a cornerstone of neurotoxicological assessments, they are costly and the topic of ethical debate. While the public expects chemicals and products to be safe for the developing and mature nervous systems, considerable numbers of chemicals in commerce have not, or only to a limited extent, been assessed for their potential to cause neurotoxicity. As such, there is a societal push toward the replacement of animal models with in vitro or alternative methods. New approach methods (NAMs) can contribute to the regulatory knowledge base, increase chemical safety, and modernize chemical hazard and risk assessment. Provided they reach an acceptable level of regulatory relevance and reliability, NAMs may be considered as replacements for specific in vivo studies. The European Partnership for the Assessment of Risks from Chemicals (PARC) addresses challenges to the development and implementation of NAMs in chemical risk assessment. In collaboration with regulatory agencies, Project 5.2.1e (Neurotoxicity) aims to develop and evaluate NAMs for developmental neurotoxicity (DNT) and adult neurotoxicity (ANT) and to understand the applicability domain of specific NAMs for the detection of endocrine disruption and epigenetic perturbation. To speed up assay time and reduce costs, we identify early indicators of later-onset effects. Ultimately, we will assemble second-generation developmental neurotoxicity and first-generation adult neurotoxicity test batteries, both of which aim to provide regulatory hazard and risk assessors and industry stakeholders with robust, speedy, lower-cost, and informative next-generation hazard and risk assessment tools., Competing Interests: EF and KB are shareholders of the DNTOX GmbH offering neurotoxicity testing services. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Tal, Myhre, Fritsche, Rüegg, Craenen, Aiello-Holden, Agrillo, Babin, Escher, Dirven, Hellsten, Dolva, Hessel, Heusinkveld, Hadzhiev, Hurem, Jagiello, Judzinska, Klüver, Knoll-Gellida, Kühne, Leist, Lislien, Lyche, Müller, Colbourne, Neuhaus, Pallocca, Seeger, Scharkin, Scholz, Spjuth, Torres-Ruiz and Bartmann.)

Cell Painting assays generate morphological profiles that are versatile descriptors of biological systems and have been used to predict in vitro and in vivo drug effects. However, Cell Painting features extracted from classical software such as CellProfiler are based on statistical calculations and often not readily biologically interpretable. In this study, we propose a new feature space, which we call BioMorph, that maps these Cell Painting features with readouts from comprehensive Cell Health assays. We validated that the resulting BioMorph space effectively connected compounds not only with the morphological features associated with their bioactivity but with deeper insights into phenotypic characteristics and cellular processes associated with the given bioactivity. The BioMorph space revealed the mechanism of action for individual compounds, including dual-acting compounds such as emetine, an inhibitor of both protein synthesis and DNA replication. Overall, BioMorph space offers a biologically relevant way to interpret the cell morphological features derived using software such as CellProfiler and to generate hypotheses for experimental validation.

Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities of chemical and biological data to predict cardiotoxicity, using the recently released DICTrank data set from the United States FDA. We found that such data, including protein targets, especially those related to ion channels (e.g., hERG), physicochemical properties (e.g., electrotopological state), and peak concentration in plasma offer strong predictive ability for DICT. Compounds annotated with mechanisms of action such as cyclooxygenase inhibition could distinguish between most-concern and no-concern DICT. Cell Painting features for ER stress discerned most-concern cardiotoxic from nontoxic compounds. Models based on physicochemical properties provided substantial predictive accuracy (AUCPR = 0.93). With the availability of omics data in the future, using biological data promises enhanced predictability and deeper mechanistic insights, paving the way for safer drug development. All models from this study are available at https://broad.io/DICTrank_Predictor.

Toxicology has been an active research field for many decades, with academic, industrial and government involvement. Modern omics and computational approaches are changing the field, from merely disease-specific observational models into target-specific predictive models. Traditionally, toxicology has strong links with other fields such as biology, chemistry, pharmacology and medicine. With the rise of synthetic and new engineered materials, alongside ongoing prioritisation needs in chemical risk assessment for existing chemicals, early predictive evaluations are becoming of utmost importance to both scientific and regulatory purposes. ELIXIR is an intergovernmental organisation that brings together life science resources from across Europe. To coordinate the linkage of various life science efforts around modern predictive toxicology, the establishment of a new ELIXIR Community is seen as instrumental. In the past few years, joint efforts, building on incidental overlap, have been piloted in the context of ELIXIR. For example, the EU-ToxRisk, diXa, HeCaToS, transQST, and the nanotoxicology community have worked with the ELIXIR TeSS, Bioschemas, and Compute Platforms and activities. In 2018, a core group of interested parties wrote a proposal, outlining a sketch of what this new ELIXIR Toxicology Community would look like. A recent workshop (held September 30th to October 1st, 2020) extended this into an ELIXIR Toxicology roadmap and a shortlist of limited investment-high gain collaborations to give body to this new community. This Whitepaper outlines the results of these efforts and defines our vision of the ELIXIR Toxicology Community and how it complements other ELIXIR activities., Competing Interests: No competing interests were disclosed., (Copyright: © 2023 Martens M et al.)

Fluorescence staining techniques, such as Cell Painting, together with fluorescence microscopy have proven invaluable for visualizing and quantifying the effects that drugs and other perturbations have on cultured cells. However, fluorescence microscopy is expensive, time-consuming, labor-intensive, and the stains applied can be cytotoxic, interfering with the activity under study. The simplest form of microscopy, brightfield microscopy, lacks these downsides, but the images produced have low contrast and the cellular compartments are difficult to discern. Nevertheless, by harnessing deep learning, these brightfield images may still be sufficient for various predictive purposes. In this study, we compared the predictive performance of models trained on fluorescence images to those trained on brightfield images for predicting the mechanism of action (MoA) of different drugs. We also extracted CellProfiler features from the fluorescence images and used them to benchmark the performance. Overall, we found comparable and largely correlated predictive performance for the two imaging modalities. This is promising for future studies of MoAs in time-lapse experiments for which using fluorescence images is problematic. Explorations based on explainable AI techniques also provided valuable insights regarding compounds that were better predicted by one modality over the other., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Harrison et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

In past times, the analysis of endocrine disrupting properties of chemicals has mainly been focused on (anti-)estrogenic or (anti-)androgenic properties, as well as on aspects of steroidogenesis and the modulation of thyroid signaling. More recently, disruption of energy metabolism and related signaling pathways by exogenous substances, so-called metabolism-disrupting chemicals (MDCs) have come into focus. While general effects such as body and organ weight changes are routinely monitored in animal studies, there is a clear lack of mechanistic test systems to determine and characterize the metabolism-disrupting potential of chemicals. In order to contribute to filling this gap, one of the project within EU-funded Partnership for the Assessment of Risks of Chemicals (PARC) aims at developing novel in vitro methods for the detection of endocrine metabolic disruptors. Efforts will comprise projects related to specific signaling pathways, for example, involving mTOR or xenobiotic-sensing nuclear receptors, studies on hepatocytes, adipocytes and pancreatic beta cells covering metabolic and morphological endpoints, as well as metabolism-related zebrafish-based tests as an alternative to classic rodent bioassays. This paper provides an overview of the approaches and methods of these PARC projects and how this will contribute to the improvement of the toxicological toolbox to identify substances with endocrine disrupting properties and to decipher their mechanisms of action., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The handling editor TV declared a shared research group PARC PROJECT: European Partnership on the Assessment of Risks from Chemicals (PARC) with the authors at the time of review., (Copyright © 2023 Braeuning, Balaguer, Bourguet, Carreras-Puigvert, Feiertag, Kamstra, Knapen, Lichtenstein, Marx-Stoelting, Rietdijk, Schubert, Spjuth, Stinckens, Thedieck, van den Boom, Vergauwen, von Bergen, Wewer and Zalko.)

The applicability domain of machine learning models trained on structural fingerprints for the prediction of biological endpoints is often limited by the lack of diversity of chemical space of the training data. In this work, we developed similarity-based merger models which combined the outputs of individual models trained on cell morphology (based on Cell Painting) and chemical structure (based on chemical fingerprints) and the structural and morphological similarities of the compounds in the test dataset to compounds in the training dataset. We applied these similarity-based merger models using logistic regression models on the predictions and similarities as features and predicted assay hit calls of 177 assays from ChEMBL, PubChem and the Broad Institute (where the required Cell Painting annotations were available). We found that the similarity-based merger models outperformed other models with an additional 20% assays (79 out of 177 assays) with an AUC > 0.70 compared with 65 out of 177 assays using structural models and 50 out of 177 assays using Cell Painting models. Our results demonstrated that similarity-based merger models combining structure and cell morphology models can more accurately predict a wide range of biological assay outcomes and further expanded the applicability domain by better extrapolating to new structural and morphology spaces., (© 2023. The Author(s).)

Progressive multiple sclerosis (PMS) is currently diagnosed retrospectively. Here, we work toward a set of biomarkers that could assist in early diagnosis of PMS. A selection of cerebrospinal fluid metabolites (n = 15) was shown to differentiate between PMS and its preceding phenotype in an independent cohort (AUC = 0.93). Complementing the classifier with conformal prediction showed that highly confident predictions could be made, and that three out of eight patients developing PMS within three years of sample collection were predicted as PMS at that time point. Finally, this methodology was applied to PMS patients as part of a clinical trial for intrathecal treatment with rituximab. The methodology showed that 68% of the patients decreased their similarity to the PMS phenotype one year after treatment. In conclusion, the inclusion of confidence predictors contributes with more information compared to traditional machine learning, and this information is relevant for disease monitoring., Competing Interests: The authors declare no competing interests., (© 2023 The Authors.)

There is an ongoing aim to replace animal and in vitro laboratory models with in silico methods. Such replacement requires the successful validation and comparably good performance of the alternative methods. We have developed an in silico prediction system for human clinical pharmacokinetics, based on machine learning, conformal prediction and a new physiologically-based pharmacokinetic model, i.e. ANDROMEDA. The objectives of this study were: a) to evaluate how well ANDROMEDA predicts the human clinical pharmacokinetics of a previously proposed benchmarking data set comprising 24 physicochemically diverse drugs and 28 small drug molecules new to the market in 2021; b) to compare its predictive performance with that of laboratory methods; and c) to investigate and describe the pharmacokinetic characteristics of the modern drugs. Median and maximum prediction errors for the selected major parameters were ca 1.2 to 2.5-fold and 16-fold for both data sets, respectively. Prediction accuracy was on par with, or better than, the best laboratory-based prediction methods (superior performance for a vast majority of the comparisons), and the prediction range was considerably broader. The modern drugs have higher average molecular weight than those in the benchmarking set from 15 years earlier ( ca 200 g/mol higher), and were predicted to (generally) have relatively complex pharmacokinetics, including permeability and dissolution limitations and significant renal, biliary and/or gut-wall elimination. In conclusion, the results were overall better than those obtained with laboratory methods, and thus serve to further validate the ANDROMEDA in silico system for the prediction of human clinical pharmacokinetics of modern and physicochemically diverse drugs.

Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems., (© 2022. The Author(s).)