A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

Progress in toxicogenomics to protect human health

Toxicogenomics measures molecular features, such as transcripts, proteins, metabolites and epigenomic modifications, to understand and predict the toxicological effects of environmental and pharmaceutical exposures. Transcriptomics has become an integral tool in contemporary toxicology research owing to innovations in gene expression profiling that can provide mechanistic and quantitative information at scale. These data can be used to predict toxicological hazards through the use of transcriptomic biomarkers, network inference analyses, pattern-matching approaches and artificial intelligence. Furthermore, emerging approaches, such as high-throughput dose-response modelling, can leverage toxicogenomic data for human health protection even in the absence of predicting specific hazards. Finally, single-cell transcriptomics and multi-omics provide detailed insights into toxicological mechanisms. Here, we review the progress since the inception of toxicogenomics in applying transcriptomics towards toxicology testing and highlight advances that are transforming risk assessment.

Multi-omics and chemical profiling approaches to understand the material foundation and pharmacological mechanism of sophorae tonkinensis radix et rhizome-induced liver injury in mice

ETHNOPHARMACOLOGICAL RELEVANCE

Sophorae tonkinensis Radix et Rhizoma (STR) is an extensively applied traditional Chinese medicine (TCM) in southwest China. However, its clinical application is relatively limited due to its hepatotoxicity effects.

AIM OF THE STUDY

To understand the material foundation and liver injury mechanism of STR.

MATERIALS AND METHODS

Chemical compositions in STR and its prototypes in mice were profiled by ultra-performance liquid chromatography coupled quadrupole-time of flight mass spectrometry (UPLC-Q/TOF MS). STR-induced liver injury (SILI) was comprehensively evaluated by STR-treated mice mode. The histopathologic and biochemical analyses were performed to evaluate liver injury levels. Subsequently, network pharmacology and multi-omics were used to analyze the potential mechanism of SILI in vivo. And the target genes were further verified by Western blot.

RESULTS

A total of 152 compounds were identified or tentatively characterized in STR, including 29 alkaloids, 21 organic acids, 75 flavonoids, 1 quinone, and 26 other types. Among them, 19 components were presented in STR-medicated serum. The histopathologic and biochemical analysis revealed that hepatic injury occurred after 4 weeks of intragastric administration of STR. Network pharmacology analysis revealed that IL6, TNF, STAT3, etc. were the main core targets, and the bile secretion might play a key role in SILI. The metabolic pathways such as taurine and hypotaurine metabolism, purine metabolism, and vitamin B6 metabolism were identified in the STR exposed groups. Among them, taurine, hypotaurine, hypoxanthine, pyridoxal, and 4-pyridoxate were selected based on their high impact value and potential biological function in the process of liver injury post STR treatment.

CONCLUSIONS

The mechanism and material foundation of SILI were revealed and profiled by a multi-omics strategy combined with network pharmacology and chemical profiling. Meanwhile, new insights were taken into understand the pathological mechanism of SILI.

Feed Components and Timing to Improve the Feed Conversion Ratio for Sustainable Aquaculture Using Starch

Aquaculture contributes to the sustainable development of food security, marine resource conservation, and economy. Shifting aquaculture feed from fish meal and oil to terrestrial plant derivatives may result in cost savings. However, many carnivorous fish cannot be sustained on plant-derived materials, necessitating the need for the identification of important factors for farmed fish growth and the identification of whether components derived from terrestrial plants can be used in feed. Herein, we focused on the carnivorous fish leopard coral grouper (P. leopardus) to identify the essential growth factors and clarify their intake timing from feeds. Furthermore, we evaluated the functionality of starch, which are easily produced by terrestrial plants. Results reveal that carbohydrates, which are not considered essential for carnivorous fish, can be introduced as a major part of an artificial diet. The development of artificial feed using starch offers the possibility of increasing the growth of carnivorous fish in aquaculture.

Next Generation Risk Assessment approaches for advanced nanomaterials: Current status and future perspectives

This manuscript discusses the challenges of applying New Approach Methodologies (NAMs) for safe by design and regulatory risk assessment of advanced nanomaterials (AdNMs). The authors propose a framework for Next Generation Risk Assessment of AdNMs involving NAMs that is aligned to the conventional risk assessment paradigm. This framework is exposure-driven, endpoint-specific, makes best use of pre-existing information, and can be implemented in tiers of increasing specificity and complexity of the adopted NAMs. The tiered structure of the approach, which effectively combines the use of existing data with targeted testing will allow safety to be assessed cost-effectively and as far as possible with even more limited use of vertebrates. The regulatory readiness of state-of-the-art emerging NAMs is assessed in terms of Transparency, Reliability, Accessibility, Applicability, Relevance and Completeness, and their appropriateness for AdNMs is discussed in relation to each step of the risk assessment paradigm along with providing perspectives for future developments in the respective scientific and regulatory areas.

Bioinformatics and machine learning to support nanomaterial grouping

Nanomaterials (NMs) offer plenty of novel functionalities. Moreover, their physicochemical properties can be fine-tuned to meet the needs of specific applications, leading to virtually unlimited numbers of NM variants. Hence, efficient hazard and risk assessment strategies building on New Approach Methodologies (NAMs) become indispensable. Indeed, the design, the development and implementation of NAMs has been a major topic in a substantial number of research projects. One of the promising strategies that can help to deal with the high number of NMs variants is grouping and read-across. Based on demonstrated structural and physicochemical similarity, NMs can be grouped and assessed together. Within an established NM group, read-across may be performed to fill in data gaps for data-poor variants using existing data for NMs within the group. Establishing a group requires a sound justification, usually based on a grouping hypothesis that links specific physicochemical properties to well-defined hazard endpoints. However, for NMs these interrelationships are only beginning to be understood. The aim of this review is to demonstrate the power of bioinformatics with a specific focus on Machine Learning (ML) approaches to unravel the NM Modes-of-Action (MoA) and identify the properties that are relevant to specific hazards, in support of grouping strategies. This review emphasizes the following messages: 1) ML supports identification of the most relevant properties contributing to specific hazards; 2) ML supports analysis of large omics datasets and identification of MoA patterns in support of hypothesis formulation in grouping approaches; 3) omics approaches are useful for shifting away from consideration of single endpoints towards a more mechanistic understanding across multiple endpoints gained from one experiment; and 4) approaches from other fields of Artificial Intelligence (AI) like Natural Language Processing or image analysis may support automated extraction and interlinkage of information related to NM toxicity. Here, existing ML models for predicting NM toxicity and for analyzing omics data in support of NM grouping are reviewed. Various challenges related to building robust models in the field of nanotoxicology exist and are also discussed.

A Data-Driven Computational Framework for Assessing the Risk of Placental Exposure to Environmental Chemicals

A computational framework based on placental gene networks was proposed in this work to improve the accuracy of the placental exposure risk assessment of environmental compounds. The framework quantitatively characterizes the ability of compounds to cross the placental barrier by systematically considering the interaction and pathway-level information on multiple placental transporters. As a result, probability scores were generated for 307 compounds crossing the placental barrier based on this framework. These scores were then used to categorize the compounds into different levels of transplacental transport range, creating a gradient partition. These probability scores not only facilitated a more intuitive understanding of a compound's ability to cross the placental barrier but also provided valuable information for predicting potential placental disruptors. Compounds with probability scores greater than 90% were considered to have significant transplacental transport potential, whereas those with probability scores less than 80% were classified as unlikely to cross the placental barrier. Furthermore, external validation set results showed that the probability score could accurately predict the compounds known to cross the placental barrier. In conclusion, the computational framework proposed in this study enhances the intuitive understanding of the ability of compounds to cross the placental barrier and opens up new avenues for assessing the placental exposure risk of compounds.

A network-based transcriptomic landscape of HepG2 cells uncovering causal gene-cytotoxicity interactions underlying drug-induced liver injury

Drug-induced liver injury (DILI) remains the main reason for drug development attritions largely due to poor mechanistic understanding. Toxicogenomic to interrogate the mechanism of DILI has been broadly performed. Gene coregulation network-based transcriptome analysis is a bioinformatics approach that potentially contributes to improve mechanistic interpretation of toxicogenomic data. Here we performed an extensive concentration time course response-toxicogenomic study in the HepG2 cell line exposed to 20 DILI compounds, 7 reference compounds for stress response pathways, and 10 agonists for cytokines and growth factor receptors. We performed whole transcriptome targeted RNA sequencing to more than 500 conditions and applied weighted gene coregulated network analysis to the transcriptomics data followed by the identification of gene coregulated networks (modules) that were strongly modulated upon the exposure of DILI compounds. Preservation analysis on the module responses of HepG2 and PHH demonstrated highly preserved adaptive stress response gene coregulated networks. We correlated gene coregulated networks with cell death onset and causal relationships of 67 critical target genes of these modules with the onset of cell death was evaluated using RNA interference screening. We identified GTPBP2, HSPA1B, IRF1, SIRT1, and TSC22D3 as essential modulators of DILI compound-induced cell death. These genes were also induced by DILI compounds in PHH. Altogether, we demonstrate the application of large transcriptome datasets combined with network-based analysis and biological validation to uncover the candidate determinants of DILI.

ELIXIR and Toxicology: a community in development

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.

In silico modeling-based new alternative methods to predict drug and herb-induced liver injury: A review

New approach methods (NAMs) have been developed to predict a wide range of toxicities through innovative technologies. Liver injury is one of the most extensively studied endpoints due to its severity and frequency, occurring among populations that consume drugs or dietary supplements. In this review, we focus on recent developments of in silico modeling for liver injury prediction using deep learning and in vitro data based on adverse outcome pathways (AOPs). Despite these models being mainly developed using datasets generated from drug-like molecules, they were also applied to the prediction of hepatotoxicity caused by herbal products. As deep learning has achieved great success in many different fields, advanced machine learning algorithms have been actively applied to improve the accuracy of in silico models. Additionally, the development of liver AOPs, combined with big data in toxicology, has been valuable in developing in silico models with enhanced predictive performance and interpretability. Specifically, one approach involves developing structure-based models for predicting molecular initiating events of liver AOPs, while others use in vitro data with structure information as model inputs for making predictions. Even though liver injury remains a difficult endpoint to predict, advancements in machine learning algorithms and the expansion of in vitro databases with relevant biological knowledge have made a huge impact on improving in silico modeling for drug-induced liver injury prediction.

Systems toxicology of complex wood combustion aerosol reveals gaseous carbonyl compounds as critical constituents

Epidemiological studies identified air pollution as one of the prime causes for human morbidity and mortality, due to harmful effects mainly on the cardiovascular and respiratory systems. Damage to the lung leads to several severe diseases such as fibrosis, chronic obstructive pulmonary disease and cancer. Noxious environmental aerosols are comprised of a gas and particulate phase representing highly complex chemical mixtures composed of myriads of compounds. Although some critical pollutants, foremost particulate matter (PM), could be linked to adverse health effects, a comprehensive understanding of relevant biological mechanisms and detrimental aerosol constituents is still lacking. Here, we employed a systems toxicology approach focusing on wood combustion, an important source for air pollution, and demonstrate a key role of the gas phase, specifically carbonyls, in driving adverse effects. Transcriptional profiling and biochemical analysis of human lung cells exposed at the air-liquid-interface determined DNA damage and stress response, as well as perturbation of cellular metabolism, as major key events. Connectivity mapping revealed a high similarity of gene expression signatures induced by wood smoke and agents prompting DNA-protein crosslinks (DPCs). Indeed, various gaseous aldehydes were detected in wood smoke, which promote DPCs, initiate similar genomic responses and are responsible for DNA damage provoked by wood smoke. Hence, systems toxicology enables the discovery of critical constituents of complex mixtures i.e. aerosols and highlights the role of carbonyls on top of particulate matter as an important health hazard.

New approach methodologies in human regulatory toxicology - Not if, but how and when!

The predominantly animal-centric approach of chemical safety assessment has increasingly come under pressure. Society is questioning overall performance, sustainability, continued relevance for human health risk assessment and ethics of this system, demanding a change of paradigm. At the same time, the scientific toolbox used for risk assessment is continuously enriched by the development of "New Approach Methodologies" (NAMs). While this term does not define the age or the state of readiness of the innovation, it covers a wide range of methods, including quantitative structure-activity relationship (QSAR) predictions, high-throughput screening (HTS) bioassays, omics applications, cell cultures, organoids, microphysiological systems (MPS), machine learning models and artificial intelligence (AI). In addition to promising faster and more efficient toxicity testing, NAMs have the potential to fundamentally transform today's regulatory work by allowing more human-relevant decision-making in terms of both hazard and exposure assessment. Yet, several obstacles hamper a broader application of NAMs in current regulatory risk assessment. Constraints in addressing repeated-dose toxicity, with particular reference to the chronic toxicity, and hesitance from relevant stakeholders, are major challenges for the implementation of NAMs in a broader context. Moreover, issues regarding predictivity, reproducibility and quantification need to be addressed and regulatory and legislative frameworks need to be adapted to NAMs. The conceptual perspective presented here has its focus on hazard assessment and is grounded on the main findings and conclusions from a symposium and workshop held in Berlin in November 2021. It intends to provide further insights into how NAMs can be gradually integrated into chemical risk assessment aimed at protection of human health, until eventually the current paradigm is replaced by an animal-free "Next Generation Risk Assessment" (NGRA).

PROTEOMAS: a workflow enabling harmonized proteomic meta-analysis and proteomic signature mapping

Toxicological evaluation of substances in regulation still often relies on animal experiments. Understanding the substances' mode-of-action is crucial to develop alternative test strategies. Omics methods are promising tools to achieve this goal. Until now, most attention was focused on transcriptomics, while proteomics is not yet routinely applied in toxicology despite the large number of datasets available in public repositories. Exploiting the full potential of these datasets is hampered by differences in measurement procedures and follow-up data processing. Here we present the tool PROTEOMAS, which allows meta-analysis of proteomic data from public origin. The workflow was designed for analyzing proteomic studies in a harmonized way and to ensure transparency in the analysis of proteomic data for regulatory purposes. It agrees with the Omics Reporting Framework guidelines of the OECD with the intention to integrate proteomics to other omic methods in regulatory toxicology. The overarching aim is to contribute to the development of AOPs and to understand the mode of action of substances. To demonstrate the robustness and reliability of our workflow we compared our results to those of the original studies. As a case study, we performed a meta-analysis of 25 proteomic datasets to investigate the toxicological effects of nanomaterials at the lung level. PROTEOMAS is an important contribution to the development of alternative test strategies enabling robust meta-analysis of proteomic data. This workflow commits to the FAIR principles (Findable, Accessible, Interoperable and Reusable) of computational protocols.

Mechanistic Insights into the Biological Effects of Engineered Nanomaterials: A Focus on Gold Nanoparticles

Nanotechnology has great potential to significantly advance the biomedical field for the benefit of human health. However, the limited understanding of nano-bio interactions leading to unknowns about the potential adverse health effects of engineered nanomaterials and to the poor efficacy of nanomedicines has hindered their use and commercialization. This is well evidenced considering gold nanoparticles, one of the most promising nanomaterials for biomedical applications. Thus, a fundamental understanding of nano-bio interactions is of interest to nanotoxicology and nanomedicine, enabling the development of safe-by-design nanomaterials and improving the efficacy of nanomedicines. In this review, we introduce the advanced approaches currently applied in nano-bio interaction studies-omics and systems toxicology-to provide insights into the biological effects of nanomaterials at the molecular level. We highlight the use of omics and systems toxicology studies focusing on the assessment of the mechanisms underlying the in vitro biological responses to gold nanoparticles. First, the great potential of gold-based nanoplatforms to improve healthcare along with the main challenges for their clinical translation are presented. We then discuss the current limitations in the translation of omics data to support risk assessment of engineered nanomaterials.

Toxicogenomics scoring system: TGSS, a novel integrated risk assessment model for chemical carcinogenicity prediction

BACKGROUND

Given the increasing exposure of humans to environmental chemicals and the limitations of conventional toxicity test, there is an urgent need to develop next-generation risk assessment methods.

OBJECTIVES

This study aims to establish a novel computational system named Toxicogenomics Scoring System (TGSS) to predict the carcinogenicity of chemicals coupling chemical-gene interactions with multiple cancer transcriptomic datasets.

METHODS

Chemical-related gene signatures were derived from chemical-gene interaction data from the Comparative Toxicogenomics Database (CTD). For each cancer type in TCGA, genes were ranked by their effects on tumorigenesis, which is based on the differential expression between tumor and normal samples. Next, we developed carcinogenicity scores (C-scores) using pre-ranked GSEA to quantify the correlation between chemical-related gene signatures and ranked gene lists. Then we established TGSS by systematically evaluating the C-scores in multiple chemical-tumor pairs. Furthermore, we examined the performance of our approach by ROC curves or prognostic analyses in TCGA and multiple independent cancer cohorts.

RESULTS

Forty-six environmental chemicals were finally included in the study. C-score was calculated for each chemical-tumor pair. The C-scores of IARC Group 3 chemicals were significantly lower than those of chemicals in Group 1 (P-value = 0.02) and Group 2 (P-values = 7.49 ×10^-5). ROC curves analysis indicated that C-score could distinguish "high-risk chemicals" from the other compounds (AUC = 0.67) with a specificity and sensitivity of 0.86 and 0.57. The results of survival analysis were also in line with the assessed carcinogenicity in TGSS for the chemicals in Group 1. Finally, consistent results were further validated in independent cancer cohorts.

CONCLUSION

TGSS highlighted the great potential of integrating chemical-gene interactions with gene-cancer relationships to predict the carcinogenic risk of chemicals, which would be valuable for systems toxicology.

Using chemical and biological data to predict drug toxicity

Various sources of information can be used to better understand and predict compound activity and safety-related endpoints, including biological data such as gene expression and cell morphology. In this review, we first introduce types of chemical, in vitro and in vivo information that can be used to describe compounds and adverse effects. We then explore how compound descriptors based on chemical structure or biological perturbation response can be used to predict safety-related endpoints, and how especially biological data can help us to better understand adverse effects mechanistically. Overall, the described applications demonstrate how large-scale biological information presents new opportunities to anticipate and understand the biological effects of compounds, and how this can support predictive toxicology and drug discovery projects.

Review article: clinical assessment of suspected drug-induced liver injury and its management

BACKGROUND

Idisyncratic drug-induced liver injury (DILI) is a rare instance of liver injury after exposure to an otherwise safe drug or herbal or dietary supplement. DILI can be associated with significant morbidity and mortality. Furthermore, it is an important consideration in drug development due to safety concerns.

AIMS AND METHODS

To highlight pearls and pitfalls to aid clinicians in diagnosing DILI and surmising the management options. We also share the best practices from personal insights developed from decades long participation in the causality assessment committee meetings of the DILI Network.

RESULTS

DILI lacks a diagnostic test and is currently diagnosed through a process of exclusion of competing aetiologies of liver injury. This requires a high degree of suspicion to consider the possibility of DILI, skill in ruling out the obvious and less obvious competing liver insults, and an understanding of the expected phenotypes of DILI. The facets of DILI cover multiple aspects, including the latency, liver injury pattern, course of injury, and associated autoimmune or immuno-allergic features. Care for patients with DILI is geared towards stopping the offending drug and symptom management that include the use of corticosteroids in select cases.

CONCLUSION

The diagnosis of DILI is challenging and is primarily made through a carefully crafted patient interview, temporal relationship with the implicated drug or supplement, and exclusion of competing aetiology. LiverTox is a useful resource for clinicians to review the literature and recognise the likelihood of the implicated agent in causing DILI.

Mechanism-driven modeling of chemical hepatotoxicity using structural alerts and an in vitro screening assay

Traditional experimental approaches to evaluate hepatotoxicity are expensive and time-consuming. As an advanced framework of risk assessment, adverse outcome pathways (AOPs) describe the sequence of molecular and cellular events underlying chemical toxicities. We aimed to develop an AOP that can be used to predict hepatotoxicity by leveraging computational modeling and in vitro assays. We curated 869 compounds with known hepatotoxicity classifications as a modeling set and extracted assay data from PubChem. The antioxidant response element (ARE) assay, which quantifies transcriptional responses to oxidative stress, showed a high correlation to hepatotoxicity (PPV=0.82). Next, we developed quantitative structure-activity relationship (QSAR) models to predict ARE activation for compounds lacking testing results. Potential toxicity alerts were identified and used to construct a mechanistic hepatotoxicity model. For experimental validation, 16 compounds in the modeling set and 12 new compounds were selected and tested using an in-house ARE-luciferase assay in HepG2-C8 cells. The mechanistic model showed good hepatotoxicity predictivity (accuracy = 0.82) for these compounds. Potential false positive hepatotoxicity predictions by only using ARE results can be corrected by incorporating structural alerts and vice versa. This mechanistic model illustrates a potential toxicity pathway for hepatotoxicity, and this strategy can be expanded to develop predictive models for other complex toxicities.

Use of transcriptomics in hazard identification and next generation risk assessment: A case study with clothianidin

Toxicological risk assessment is essential in the evaluation and authorization of different classes of chemical substances. Genotoxicity and mutagenicity testing are of highest priority and rely on established in vitro systems with bacterial and mammalian cells, sometimes followed by in vivo testing using rodent animal models. Transcriptomic approaches have recently also shown their value to determine transcript signatures specific for genotoxicity. Here, we studied how transcriptomic data, in combination with in vitro tests with human cells, can be used for the identification of genotoxic properties of test compounds. To this end, we used liver samples from a 28-day oral toxicity study in rats with the pesticidal active substances imazalil, thiacloprid, and clothianidin, a neonicotinoid-type insecticide with, amongst others, known hepatotoxic properties. Transcriptomic results were bioinformatically evaluated and pointed towards a genotoxic potential of clothianidin. In vitro Comet and γH2AX assays in human HepaRG hepatoma cells, complemented by in silico analyses of mutagenicity, were conducted as follow-up experiments to check if the genotoxicity alert from the transcriptomic study is in line with results from a battery of guideline genotoxicity studies. Our results illustrate the combined use of toxicogenomics, classic toxicological data and new approach methods in risk assessment. By means of a weight-of-evidence decision, we conclude that clothianidin does most likely not pose genotoxic risks to humans.

•

Analysis of clothianidin genotoxicity in silico, in vitro and in vivo.

•

Application of a toxicogenomics approach to analyze genotoxicity.

•

Weight-of-evidence decision supports classification as “non-genotoxic”.

Expanding RNAi therapeutics to extrahepatic tissues with lipophilic conjugates

Therapeutics based on short interfering RNAs (siRNAs) delivered to hepatocytes have been approved, but new delivery solutions are needed to target additional organs. Here we show that conjugation of 2'-O-hexadecyl (C16) to siRNAs enables safe, potent and durable silencing in the central nervous system (CNS), eye and lung in rodents and non-human primates with broad cell type specificity. We show that intrathecally or intracerebroventricularly delivered C16-siRNAs were active across CNS regions and cell types, with sustained RNA interference (RNAi) activity for at least 3 months. Similarly, intravitreal administration to the eye or intranasal administration to the lung resulted in a potent and durable knockdown. The preclinical efficacy of an siRNA targeting the amyloid precursor protein was evaluated through intracerebroventricular dosing in a mouse model of Alzheimer's disease, resulting in amelioration of physiological and behavioral deficits. Altogether, C16 conjugation of siRNAs has the potential for safe therapeutic silencing of target genes outside the liver with infrequent dosing.

Tox-GAN: An AI Approach Alternative to Animal Studies-a Case Study with Toxicogenomics

Animal studies are a critical component in biomedical research, pharmaceutical product development, and regulatory submissions. There is a worldwide effort in toxicology towards "reducing, refining and replacing" (3Rs) animal use. Here, we proposed a deep generative adversarial network (GAN)-based framework capable of deriving new animal results from existing animal studies without additional experiments. To prove the concept, we employed this Tox-GAN framework to generate both gene activities and expression profiles for multiple doses and treatment durations in toxicogenomics (TGx). Using the pre-existing rat liver TGx data from the Open TG-GATEs, we generated Tox-GAN transcriptomic profiles with high similarity (0.997 ± 0.002 in intensity and 0.740 ± 0.082 in fold change) to the corresponding real gene expression profiles. Consequently, Tox-GAN showed an outstanding performance in two critical TGx applications, gaining a molecular understanding of underlying toxicological mechanisms and gene expression-based biomarker development. For the former, over 87% agreement in Gene Ontology was found between Tox-GAN results and real gene expression data. For the latter, the concordance of biomarkers between real and generated data was high in both predictive performance and biomarker genes. We also demonstrated that the Tox-GAN models constructed with TG-GATEs data were capable of generating transcriptomic profiles reported in DrugMatrix. Finally, we demonstrated potential utility for Tox-GAN in aiding chemical-based read-across. To the best of our knowledge, the proposed Tox-GAN model is novel in its ability to generate in vivo transcriptomic profiles at different treatment conditions from chemical structures. Overall, Tox-GAN holds great promise for generating high-quality toxicogenomic profiles without animal experimentation.

Side effect prediction based on drug-induced gene expression profiles and random forest with iterative feature selection

One in every ten drug candidates fail in clinical trials mainly due to efficacy and safety related issues, despite in-depth preclinical testing. Even some of the approved drugs such as chemotherapeutics are notorious for their side effects that are burdensome on patients. In order to pave the way for new therapeutics with more tolerable side effects, the mechanisms underlying side effects need to be fully elucidated. In this work, we addressed the common side effects of chemotherapeutics, namely alopecia, diarrhea and edema. A strategy based on Random Forest algorithm unveiled an expression signature involving 40 genes that predicted these side effects with an accuracy of 89%. We further characterized the resulting signature and its association with the side effects using functional enrichment analysis and protein-protein interaction networks. This work contributes to the ongoing efforts in drug development for early identification of side effects to use the resources more effectively.

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases. Our optimal model SSL-GCN is hosted on an online server accessible through: https://app.cbbio.online/ssl-gcn/home .

A toxicogenomic data space for system-level understanding and prediction of EDC-induced toxicity

Endocrine disrupting compounds (EDCs) are a persistent threat to humans and wildlife due to their ability to interfere with endocrine signaling pathways. Inspired by previous work to improve chemical hazard identification through the use of toxicogenomics data, we developed a genomic-oriented data space for profiling the molecular activity of EDCs in an in silico manner, and for creating predictive models that identify and prioritize EDCs. Predictive models of EDCs, derived from gene expression data from rats (in vivo and in vitro primary hepatocytes) and humans (in vitro primary hepatocytes and HepG2), achieve testing accuracy greater than 90%. Negative test sets indicate that known safer chemicals are not predicted as EDCs. The rat in vivo-based classifiers achieve accuracy greater than 75% when tested for invitro to in vivoextrapolation. This study reveals key metabolic pathways and genes affected by EDCs together with a set of predictive models that utilize these pathways to prioritize EDCs in dose/time dependent manner and to predict EDCevokedmetabolic diseases.

Advanced preclinical models for evaluation of drug-induced liver injury - consensus statement by the European Drug-Induced Liver Injury Network [PRO-EURO-DILI-NET]

Drug-induced liver injury (DILI) is a major cause of acute liver failure (ALF) and one of the leading indications for liver transplantation in Western societies. Given the wide use of both prescribed and over the counter drugs, DILI has become a major health issue for which there is a pressing need to find novel and effective therapies. Although significant progress has been made in understanding the molecular mechanisms underlying DILI, our incomplete knowledge of its pathogenesis and inability to predict DILI is largely due to both discordance between human and animal DILI in preclinical drug development and a lack of models that faithfully recapitulate complex pathophysiological features of human DILI. This is exemplified by the hepatotoxicity of acetaminophen (APAP) overdose, a major cause of ALF because of its extensive worldwide use as an analgesic. Despite intensive efforts utilising current animal and in vitro models, the mechanisms involved in the hepatotoxicity of APAP are still not fully understood. In this expert Consensus Statement, which is endorsed by the European Drug-Induced Liver Injury Network, we aim to facilitate and outline clinically impactful discoveries by detailing the requirements for more realistic human-based systems to assess hepatotoxicity and guide future drug safety testing. We present novel insights and discuss major players in APAP pathophysiology, and describe emerging in vitro and in vivo pre-clinical models, as well as advanced imaging and in silico technologies, which may improve prediction of clinical outcomes of DILI.

Revealing the Angiopathy of Lacrimal Gland Lesion in Type 2 Diabetes

For a better understanding of diabetic angiopathy (DA), the potential biomarkers in lacrimal DA and its potential mechanism, we evaluated the morphological and hemodynamic alterations of lacrimal glands (LGs) in patients with type 2 diabetes and healthy counterparts by color Doppler flow imaging (CDFI). We further established a type 2 diabetic mice model and performed hematoxylin-eosin (HE) staining, immunofluorescence staining of CD31, RNA-sequencing analysis, and connectivity map (CMap) analysis. We found atrophy and ischemia in patients with type 2 diabetes and mice models. Furthermore, we identified 846 differentially expressed genes (DEGs) between type 2 diabetes mellitus (T2DM) and vehicle mice by RNA-seq. The gene ontology (GO) analysis indicated significant enrichment of immune system process, regulation of blood circulation, apoptotic, regulation of secretion, regulation of blood vessel diameter, and so on. The molecular complex detection (MCODE) showed 17 genes were involved in the most significant module, and 6/17 genes were involved in vascular disorders. CytoHubba revealed the top 10 hub genes of DEGs, and four hub genes (App, F5, Fgg, and Gas6) related to vascular regulation were identified repeatedly by MCODE and cytoHubba. GeneMANIA analysis demonstrated functions of the four hub genes above and their associated molecules were primarily related to the regulation of circulation and coagulation. CMap analysis found several small molecular compounds to reverse the altered DEGs, including disulfiram, bumetanide, genistein, and so on. Our outputs could empower the novel potential targets to treat lacrimal angiopathy, diabetes dry eye, and other diabetes-related diseases.

Predicting Drug-Induced Liver Injury Using Machine Learning on a Diverse Set of Predictors

A major challenge in drug development is safety and toxicity concerns due to drug side effects. One such side effect, drug-induced liver injury (DILI), is considered a primary factor in regulatory clearance. The Critical Assessment of Massive Data Analysis (CAMDA) 2020 CMap Drug Safety Challenge goal was to develop prediction models based on gene perturbation of six preselected cell-lines (CMap L1000), extended structural information (MOLD2), toxicity data (TOX21), and FDA reporting of adverse events (FAERS). Four types of DILI classes were targeted, including two clinically relevant scores and two control classifications, designed by the CAMDA organizers. The L1000 gene expression data had variable drug coverage across cell lines with only 247 out of 617 drugs in the study measured in all six cell types. We addressed this coverage issue by using Kru-Bor ranked merging to generate a singular drug expression signature across all six cell lines. These merged signatures were then narrowed down to the top and bottom 100, 250, 500, or 1,000 genes most perturbed by drug treatment. These signatures were subject to feature selection using Fisher's exact test to identify genes predictive of DILI status. Models based solely on expression signatures had varying results for clinical DILI subtypes with an accuracy ranging from 0.49 to 0.67 and Matthews Correlation Coefficient (MCC) values ranging from -0.03 to 0.1. Models built using FAERS, MOLD2, and TOX21 also had similar results in predicting clinical DILI scores with accuracy ranging from 0.56 to 0.67 with MCC scores ranging from 0.12 to 0.36. To incorporate these various data types with expression-based models, we utilized soft, hard, and weighted ensemble voting methods using the top three performing models for each DILI classification. These voting models achieved a balanced accuracy up to 0.54 and 0.60 for the clinically relevant DILI subtypes. Overall, from our experiment, traditional machine learning approaches may not be optimal as a classification method for the current data.

Analytical and Omics-Based Advances in the Study of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is a significant clinical issue, affecting 1-1.5 million patients annually, and remains a major challenge during drug development-toxicity and safety concerns are the second-highest reason for drug candidate failure. The future prevalence of DILI can be minimized by developing a greater understanding of the biological mechanisms behind DILI. Both qualitative and quantitative analytical techniques are vital to characterizing and investigating DILI. In vitro assays are capable of characterizing specific aspects of a drug's hepatotoxic nature and multiplexed assays are capable of characterizing and scoring a drug's association with DILI. However, an even deeper insight into the perturbations to biological pathways involved in the mechanisms of DILI can be gained through the use of omics-based analytical techniques: genomics, transcriptomics, proteomics, and metabolomics. These omics analytical techniques can offer qualitative and quantitative insight into genetic susceptibilities to DILI, the impact of drug treatment on gene expression, and the effect on protein and metabolite abundance. This review will discuss the analytical techniques that can be applied to characterize and investigate the biological mechanisms of DILI and potential predictive biomarkers.

Contextualization of causal regulatory networks from toxicogenomics data applied to drug-induced liver injury

In recent years, network-based methods have become an attractive analytical approach for toxicogenomics studies. They can capture not only the global changes of regulatory gene networks but also the relationships between their components. Among them, a causal reasoning approach depicts the mechanisms of regulation that connect upstream regulators in signaling networks to their downstream gene targets. In this work, we applied CARNIVAL, a causal network contextualisation tool, to infer upstream signaling networks deregulated in drug-induced liver injury (DILI) from gene expression microarray data from the TG-GATEs database. We focussed on six compounds that induce observable histopathologies linked to DILI from repeated dosing experiments in rats. We compared responses in vitro and in vivo to identify potential cross-platform concordances in rats as well as network preservations between rat and human. Our results showed similarities of enriched pathways and network motifs between compounds. These pathways and motifs induced the same pathology in rats but not in humans. In particular, the causal interactions "LCK activates SOCS3, which in turn inhibits TFDP1" was commonly identified as a regulatory path among the fibrosis-inducing compounds. This potential pathology-inducing regulation illustrates the value of our approach to generate hypotheses that can be further validated experimentally.

Systematic Organization of COVID-19 Data Supported by the Adverse Outcome Pathway Framework

Adverse Outcome Pathways (AOP) provide structured frameworks for the systematic organization of research data and knowledge. The AOP framework follows a set of key principles that allow for broad application across diverse disciplines related to human health, including toxicology, pharmacology, virology and medical research. The COVID-19 pandemic engages a great number of scientists world-wide and data is increasing with exponential speed. Diligent data management strategies are employed but approaches for systematically organizing the data-derived information and knowledge are lacking. We believe AOPs can play an important role in improving interpretation and efficient application of scientific understanding of COVID-19. Here, we outline a newly initiated effort, the CIAO project (https://www.ciao-covid.net/), to streamline collaboration between scientists across the world toward development of AOPs for COVID-19, and describe the overarching aims of the effort, as well as the expected outcomes and research support that they will provide.

The Promise of AI for DILI Prediction

Drug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intelligence (AI) approaches, particularly those building on machine learning, range from random forests to more recent techniques such as deep learning, and provide tools that can analyze chemical compounds and accurately predict some of their properties based purely on their structure. This article reviews existing AI approaches to predicting DILI and elaborates on the challenges that arise from the as yet limited availability of data. Future directions are discussed focusing on rich data modalities, such as 3D spheroids, and the slow but steady increase in drugs annotated with DILI risk labels.

Non-Animal Strategies for Toxicity Assessment of Nanoscale Materials: Role of Adverse Outcome Pathways in the Selection of Endpoints

Faster, cheaper, sensitive, and mechanisms-based animal alternatives are needed to address the safety assessment needs of the growing number of nanomaterials (NM) and their sophisticated property variants. Specifically, strategies that help identify and prioritize alternative schemes involving individual test models, toxicity endpoints, and assays for the assessment of adverse outcomes, as well as strategies that enable validation and refinement of these schemes for the regulatory acceptance are needed. In this review, two strategies 1) the current nanotoxicology literature review and 2) the adverse outcome pathways (AOPs) framework, a systematic process that allows the assembly of available mechanistic information concerning a toxicological response in a simple modular format, are presented. The review highlights 1) the most frequently assessed and reported ad hoc in vivo and in vitro toxicity measurements in the literature, 2) various AOPs of relevance to inhalation toxicity of NM that are presently under development, and 3) their applicability in identifying key events of toxicity for targeted in vitro assay development. Finally, using an existing AOP for lung fibrosis, the specific combinations of cell types, exposure and test systems, and assays that are experimentally supported and thus, can be used for assessing NM-induced lung fibrosis, are proposed.

High-throughput toxicogenomic screening of chemicals in the environment using metabolically competent hepatic cell cultures

The ToxCast in vitro screening program has provided concentration-response bioactivity data across more than a thousand assay endpoints for thousands of chemicals found in our environment and commerce. However, most ToxCast screening assays have evaluated individual biological targets in cancer cell lines lacking integrated physiological functionality (such as receptor signaling, metabolism). We evaluated differentiated HepaRGTM cells, a human liver-derived cell model understood to effectively model physiologically relevant hepatic signaling. Expression of 93 gene transcripts was measured by quantitative polymerase chain reaction using Fluidigm 96.96 dynamic arrays in response to 1060 chemicals tested in eight-point concentration-response. A Bayesian framework quantitatively modeled chemical-induced changes in gene expression via six transcription factors including: aryl hydrocarbon receptor, constitutive androstane receptor, pregnane X receptor, farnesoid X receptor, androgen receptor, and peroxisome proliferator-activated receptor alpha. For these chemicals the network model translates transcriptomic data into Bayesian inferences about molecular targets known to activate toxicological adverse outcome pathways. These data also provide new insights into the molecular signaling network of HepaRGTM cell cultures.

Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches

As expenditure on drug development increases exponentially, the overall drug discovery process requires a sustainable revolution. Since artificial intelligence (AI) is leading the fourth industrial revolution, AI can be considered as a viable solution for unstable drug research and development. Generally, AI is applied to fields with sufficient data such as computer vision and natural language processing, but there are many efforts to revolutionize the existing drug discovery process by applying AI. This review provides a comprehensive, organized summary of the recent research trends in AI-guided drug discovery process including target identification, hit identification, ADMET prediction, lead optimization, and drug repositioning. The main data sources in each field are also summarized in this review. In addition, an in-depth analysis of the remaining challenges and limitations will be provided, and proposals for promising future directions in each of the aforementioned areas.

DeepDILI: Deep Learning-Powered Drug-Induced Liver Injury Prediction Using Model-Level Representation

Drug-induced liver injury (DILI) is the most frequently reported single cause of safety-related withdrawal of marketed drugs. It is essential to identify drugs with DILI potential at the early stages of drug development. In this study, we describe a deep learning-powered DILI (DeepDILI) prediction model created by combining model-level representation generated by conventional machine learning (ML) algorithms with a deep learning framework based on Mold2 descriptors. We conducted a comprehensive evaluation of the proposed DeepDILI model performance by posing several critical questions: (1) Could the DILI potential of newly approved drugs be predicted by accumulated knowledge of early approved ones? (2) is model-level representation more informative than molecule-based representation for DILI prediction? and (3) could improved model explainability be established? For question 1, we developed the DeepDILI model using drugs approved before 1997 to predict the DILI potential of those approved thereafter. As a result, the DeepDILI model outperformed the five conventional ML algorithms and two state-of-the-art ensemble methods with a Matthews correlation coefficient (MCC) value of 0.331. For question 2, we demonstrated that the DeepDILI model's performance was significantly improved (i.e., a MCC improvement of 25.86% in test set) compared with deep neural networks based on molecule-based representation. For question 3, we found 21 chemical descriptors that were enriched, suggesting a strong association with DILI outcome. Furthermore, we found that the DeepDILI model has more discrimination power to identify the DILI potential of drugs belonging to the World Health Organization therapeutic category of 'alimentary tract and metabolism'. Moreover, the DeepDILI model based on Mold2 descriptors outperformed the ones with Mol2vec and MACCS descriptors. Finally, the DeepDILI model was applied to the recent real-world problem of predicting any DILI concern for potential COVID-19 treatments from repositioning drug candidates. Altogether, this developed DeepDILI model could serve as a promising tool for screening for DILI risk of compounds in the preclinical setting, and the DeepDILI model is publicly available through https://github.com/TingLi2016/DeepDILI.

Deep Learning on High-Throughput Transcriptomics to Predict Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is one of the most cited reasons for the high drug attrition rate and drug withdrawal from the market. The accumulated large amount of high throughput transcriptomic profiles and advances in deep learning provide an unprecedented opportunity to improve the suboptimal performance of DILI prediction. In this study, we developed an eight-layer Deep Neural Network (DNN) model for DILI prediction using transcriptomic profiles of human cell lines (LINCS L1000 dataset) with the current largest binary DILI annotation data [i.e., DILI severity and toxicity (DILIst)]. The developed models were evaluated by Monte Carlo cross-validation (MCCV), permutation test, and an independent validation (IV) set. The developed DNN model achieved the area under the receiver operating characteristic curve (AUC) of 0.802 and 0.798, and balanced accuracy of 0.741 and 0.721 for training and an IV set, respectively, outperforming the conventional machine learning algorithms, including K-nearest neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF). Moreover, the developed DNN model provided a more balanced sensitivity of 0.839 and specificity of 0.603. Besides, we found the developed DNN model had a superior predictive performance for oncology drugs. Also, the functional and network analysis of genes driving the predictions revealed their relevance to the underlying mechanisms of DILI. The proposed DNN model could be a promising tool for early detection of DILI potential in the pre-clinical setting.

Identification of early liver toxicity gene biomarkers using comparative supervised machine learning

Screening agrochemicals and pharmaceuticals for potential liver toxicity is required for regulatory approval and is an expensive and time-consuming process. The identification and utilization of early exposure gene signatures and robust predictive models in regulatory toxicity testing has the potential to reduce time and costs substantially. In this study, comparative supervised machine learning approaches were applied to the rat liver TG-GATEs dataset to develop feature selection and predictive testing. We identified ten gene biomarkers using three different feature selection methods that predicted liver necrosis with high specificity and selectivity in an independent validation dataset from the Microarray Quality Control (MAQC)-II study. Nine of the ten genes that were selected with the supervised methods are involved in metabolism and detoxification (Car3, Crat, Cyp39a1, Dcd, Lbp, Scly, Slc23a1, and Tkfc) and transcriptional regulation (Ablim3). Several of these genes are also implicated in liver carcinogenesis, including Crat, Car3 and Slc23a1. Our biomarker gene signature provides high statistical accuracy and a manageable number of genes to study as indicators to potentially accelerate toxicity testing based on their ability to induce liver necrosis and, eventually, liver cancer.

Network integration and modelling of dynamic drug responses at multi-omics levels

Uncovering cellular responses from heterogeneous genomic data is crucial for molecular medicine in particular for drug safety. This can be realized by integrating the molecular activities in networks of interacting proteins. As proof-of-concept we challenge network modeling with time-resolved proteome, transcriptome and methylome measurements in iPSC-derived human 3D cardiac microtissues to elucidate adverse mechanisms of anthracycline cardiotoxicity measured with four different drugs (doxorubicin, epirubicin, idarubicin and daunorubicin). Dynamic molecular analysis at in vivo drug exposure levels reveal a network of 175 disease-associated proteins and identify common modules of anthracycline cardiotoxicity in vitro, related to mitochondrial and sarcomere function as well as remodeling of extracellular matrix. These in vitro-identified modules are transferable and are evaluated with biopsies of cardiomyopathy patients. This to our knowledge most comprehensive study on anthracycline cardiotoxicity demonstrates a reproducible workflow for molecular medicine and serves as a template for detecting adverse drug responses from complex omics data.

Using a network propagation approach with integrated multi-omic data, Selevsek et al. develop a reproducible workflow for identifying drug toxicity effects in cellular systems. This is demonstrated with the analysis of anthracycline cardiotoxicity in cardiac microtissues under the effect of multiple drugs.

Using human in vitro transcriptome analysis to build trustworthy machine learning models for prediction of animal drug toxicity

During the development of new drugs or compounds there is a requirement for preclinical trials, commonly involving animal tests, to ascertain the safety of the compound prior to human trials. Machine learning techniques could provide an in-silico alternative to animal models for assessing drug toxicity, thus reducing expensive and invasive animal testing during clinical trials, for drugs that are most likely to fail safety tests. Here we present a machine learning model to predict kidney dysfunction, as a proxy for drug induced renal toxicity, in rats. To achieve this, we use inexpensive transcriptomic profiles derived from human cell lines after chemical compound treatment to train our models combined with compound chemical structure information. Genomics data due to its sparse, high-dimensional and noisy nature presents significant challenges in building trustworthy and transparent machine learning models. Here we address these issues by judiciously building feature sets from heterogenous sources and coupling them with measures of model uncertainty achieved through Gaussian Process based Bayesian models. We combine the use of insight into the feature-wise contributions to our predictions with the use of predictive uncertainties recovered from the Gaussian Process to improve the transparency and trustworthiness of the model.

Adverse outcome pathways as a tool for the design of testing strategies to support the safety assessment of emerging advanced materials at the nanoscale

Toxicity testing and regulation of advanced materials at the nanoscale, i.e. nanosafety, is challenged by the growing number of nanomaterials and their property variants requiring assessment for potential human health impacts. The existing animal-reliant toxicity testing tools are onerous in terms of time and resources and are less and less in line with the international effort to reduce animal experiments. Thus, there is a need for faster, cheaper, sensitive and effective animal alternatives that are supported by mechanistic evidence. More importantly, there is an urgency for developing alternative testing strategies that help justify the strategic prioritization of testing or targeting the most apparent adverse outcomes, selection of specific endpoints and assays and identifying nanomaterials of high concern. The Adverse Outcome Pathway (AOP) framework is a systematic process that uses the available mechanistic information concerning a toxicological response and describes causal or mechanistic linkages between a molecular initiating event, a series of intermediate key events and the adverse outcome. The AOP framework provides pragmatic insights to promote the development of alternative testing strategies. This review will detail a brief overview of the AOP framework and its application to nanotoxicology, tools for developing AOPs and the role of toxicogenomics, and summarize various AOPs of relevance to inhalation toxicity of nanomaterials that are currently under various stages of development. The review also presents a network of AOPs derived from connecting all AOPs, which shows that several adverse outcomes induced by nanomaterials originate from a molecular initiating event that describes the interaction of nanomaterials with lung cells and involve similar intermediate key events. Finally, using the example of an established AOP for lung fibrosis, the review will discuss various in vitro tests available for assessing lung fibrosis and how the information can be used to support a tiered testing strategy for lung fibrosis. The AOPs and AOP network enable deeper understanding of mechanisms involved in inhalation toxicity of nanomaterials and provide a strategy for the development of alternative test methods for hazard and risk assessment of nanomaterials.

De Novo Transcriptome Assembly and Annotation of Liver and Brain Tissues of Common Brushtail Possums (Trichosurus vulpecula) in New Zealand: Transcriptome Diversity after Decades of Population Control

The common brushtail possum (Trichosurus vulpecula), introduced from Australia in the mid-nineteenth century, is an invasive species in New Zealand where it is widespread and forms the largest self-sustained reservoir of bovine tuberculosis (Mycobacterium bovis) among wild populations. Conservation and agricultural authorities regularly apply a series of population control measures to suppress brushtail possum populations. The evolutionary consequence of more than half a century of intensive population control operations on the species’ genomic diversity and population structure is hindered by a paucity of available genomic resources. This study is the first to characterise the functional content and diversity of brushtail possum liver and brain cerebral cortex transcriptomes. Raw sequences from hepatic cells and cerebral cortex were assembled into 58,001 and 64,735 transcripts respectively. Functional annotation and polymorphism assignment of the assembled transcripts demonstrated a considerable level of variation in the core metabolic pathways that represent potential targets for selection pressure exerted by chemical toxicants. This study suggests that the brushtail possum population in New Zealand harbours considerable variation in metabolic pathways that could potentially promote the development of tolerance against chemical toxicants.

Transcriptomics in Toxicogenomics, Part III: Data Modelling for Risk Assessment

Transcriptomics data are relevant to address a number of challenges in Toxicogenomics (TGx). After careful planning of exposure conditions and data preprocessing, the TGx data can be used in predictive toxicology, where more advanced modelling techniques are applied. The large volume of molecular profiles produced by omics-based technologies allows the development and application of artificial intelligence (AI) methods in TGx. Indeed, the publicly available omics datasets are constantly increasing together with a plethora of different methods that are made available to facilitate their analysis, interpretation and the generation of accurate and stable predictive models. In this review, we present the state-of-the-art of data modelling applied to transcriptomics data in TGx. We show how the benchmark dose (BMD) analysis can be applied to TGx data. We review read across and adverse outcome pathways (AOP) modelling methodologies. We discuss how network-based approaches can be successfully employed to clarify the mechanism of action (MOA) or specific biomarkers of exposure. We also describe the main AI methodologies applied to TGx data to create predictive classification and regression models and we address current challenges. Finally, we present a short description of deep learning (DL) and data integration methodologies applied in these contexts. Modelling of TGx data represents a valuable tool for more accurate chemical safety assessment. This review is the third part of a three-article series on Transcriptomics in Toxicogenomics.

NanoSolveIT Project: Driving nanoinformatics research to develop innovative and integrated tools for in silico nanosafety assessment

Nanotechnology has enabled the discovery of a multitude of novel materials exhibiting unique physicochemical (PChem) properties compared to their bulk analogues. These properties have led to a rapidly increasing range of commercial applications; this, however, may come at a cost, if an association to long-term health and environmental risks is discovered or even just perceived. Many nanomaterials (NMs) have not yet had their potential adverse biological effects fully assessed, due to costs and time constraints associated with the experimental assessment, frequently involving animals. Here, the available NM libraries are analyzed for their suitability for integration with novel nanoinformatics approaches and for the development of NM specific Integrated Approaches to Testing and Assessment (IATA) for human and environmental risk assessment, all within the NanoSolveIT cloud-platform. These established and well-characterized NM libraries (e.g. NanoMILE, NanoSolutions, NANoREG, NanoFASE, caLIBRAte, NanoTEST and the Nanomaterial Registry (>2000 NMs)) contain physicochemical characterization data as well as data for several relevant biological endpoints, assessed in part using harmonized Organisation for Economic Co-operation and Development (OECD) methods and test guidelines. Integration of such extensive NM information sources with the latest nanoinformatics methods will allow NanoSolveIT to model the relationships between NM structure (morphology), properties and their adverse effects and to predict the effects of other NMs for which less data is available. The project specifically addresses the needs of regulatory agencies and industry to effectively and rapidly evaluate the exposure, NM hazard and risk from nanomaterials and nano-enabled products, enabling implementation of computational 'safe-by-design' approaches to facilitate NM commercialization.

Predictability of drug-induced liver injury by machine learning

Background

Drug-induced liver injury (DILI) is a major concern in drug development, as hepatotoxicity may not be apparent at early stages but can lead to life threatening consequences. The ability to predict DILI from in vitro data would be a crucial advantage. In 2018, the Critical Assessment Massive Data Analysis group proposed the CMap Drug Safety challenge focusing on DILI prediction.

Methods and results

The challenge data included Affymetrix GeneChip expression profiles for the two cancer cell lines MCF7 and PC3 treated with 276 drug compounds and empty vehicles. Binary DILI labeling and a recommended train/test split for the development of predictive classification approaches were also provided. We devised three deep learning architectures for DILI prediction on the challenge data and compared them to random forest and multi-layer perceptron classifiers. On a subset of the data and for some of the models we additionally tested several strategies for balancing the two DILI classes and to identify alternative informative train/test splits. All the models were trained with the MAQC data analysis protocol (DAP), i.e., 10x5 cross-validation over the training set. In all the experiments, the classification performance in both cross-validation and external validation gave Matthews correlation coefficient (MCC) values below 0.2. We observed minimal differences between the two cell lines. Notably, deep learning approaches did not give an advantage on the classification performance.

Discussion

We extensively tested multiple machine learning approaches for the DILI classification task obtaining poor to mediocre performance. The results suggest that the CMap expression data on the two cell lines MCF7 and PC3 are not sufficient for accurate DILI label prediction.

Reviewers

This article was reviewed by Maciej Kandula and Paweł P. Labaj.

Toward Rigorous Materials Production: New Approach Methodologies Have Extensive Potential to Improve Current Safety Assessment Practices

Advanced material development, including at the nanoscale, comprises costly and complex challenges coupled to ensuring human and environmental safety. Governmental agencies regulating safety have announced interest toward acceptance of safety data generated under the collective term New Approach Methodologies (NAMs), as such technologies/approaches offer marked potential to progress the integration of safety testing measures during innovation from idea to product launch of nanomaterials. Divided in overall eight main categories, searchable databases for grouping and read across purposes, exposure assessment and modeling, in silico modeling of physicochemical structure and hazard data, in vitro high-throughput and high-content screening assays, dose-response assessments and modeling, analyses of biological processes and toxicity pathways, kinetics and dose extrapolation, consideration of relevant exposure levels and biomarker endpoints typify such useful NAMs. Their application generally agrees with articulated stakeholder needs for improvement of safety testing procedures. They further fit for inclusion and add value in nanomaterials risk assessment tools. Overall 37 of 50 evaluated NAMs and tiered workflows applying NAMs are recommended for considering safer-by-design innovation, including guidance to the selection of specific NAMs in the eight categories. An innovation funnel enriched with safety methods is ultimately proposed under the central aim of promoting rigorous nanomaterials innovation.

De novo generation of hit-like molecules from gene expression signatures using artificial intelligence

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.

Immune Biomarkers for Diagnosis and Treatment Monitoring of Tuberculosis: Current Developments and Future Prospects

Tuberculosis (TB) treatment monitoring is paramount to clinical decision-making and the host biomarkers appears to play a significant role. The currently available diagnostic technology for TB detection is inadequate. Although GeneXpert detects total DNA present in the sample regardless live or dead bacilli present in clinical samples, all the commercial tests available thus far have low sensitivity. Humoral responses against Mycobacterium tuberculosis (Mtb) antigens are generally low, which precludes the use of serological tests for TB diagnosis, prognosis, and treatment monitoring. Mtb-specific CD4⁺ T cells correlate with Mtb antigen/bacilli burden and hence might serve as good biomarkers for monitoring treatment progress. Omics-based techniques are capable of providing a more holistic picture for disease mechanisms and are more accurate in predicting TB disease outcomes. The current review aims to discuss some of the recent advances on TB biomarkers, particularly host biomarkers that have the potential to diagnose and differentiate active TB and LTBI as well as their use in disease prognosis and treatment monitoring.