Deep Neural Network Models for Predicting Chemically Induced Liver Toxicity Endpoints From Transcriptomic Responses

Assessment of estrogenic potential from exudates of microcystin-producing and non-microcystin-producing Microcystis by metabolomics, machine learning and E-screen assay

Cyanobacterial blooms, often dominated by Microcystis aeruginosa, are capable of producing estrogenic effects. It is important to identify specific estrogenic compounds produced by cyanobacteria, though this can prove challenging owing to the complexity of exudate mixtures. In this study, we used untargeted metabolomics to compare components of exudates from microcystin-producing and non-microcystin-producing M. aeruginosa strains that differed with respect to their ability to produce microcystins, and across two growth phases. We identified 416 chemicals and found that the two strains produced similar components, mainly organoheterocyclic compounds (20.2%), organic acids and derivatives (17.3%), phenylpropanoids and polyketides (12.7%), benzenoids (12.0%), lipids and lipid-like molecules (11.5%), and organic oxygen compounds (10.1%). We then predicted estrogenic compounds from this group using random forest machine learning. Six compounds (daidzin, biochanin A, phenylethylamine, rhein, o-Cresol, and arbutin) belonging to phenylpropanoids and polyketides (3), benzenoids (2), and organic oxygen compound (1) were tested and exhibited estrogenic potency based upon the E-screen assay. This study confirmed that both Microcystis strains produce exudates that contain compounds with estrogenic properties, a growing concern in cyanobacteria management.

Computational models for predicting liver toxicity in the deep learning era

Drug-induced liver injury (DILI) is a severe adverse reaction caused by drugs and may result in acute liver failure and even death. Many efforts have centered on mitigating risks associated with potential DILI in humans. Among these, quantitative structure-activity relationship (QSAR) was proven to be a valuable tool for early-stage hepatotoxicity screening. Its advantages include no requirement for physical substances and rapid delivery of results. Deep learning (DL) made rapid advancements recently and has been used for developing QSAR models. This review discusses the use of DL in predicting DILI, focusing on the development of QSAR models employing extensive chemical structure datasets alongside their corresponding DILI outcomes. We undertake a comprehensive evaluation of various DL methods, comparing with those of traditional machine learning (ML) approaches, and explore the strengths and limitations of DL techniques regarding their interpretability, scalability, and generalization. Overall, our review underscores the potential of DL methodologies to enhance DILI prediction and provides insights into future avenues for developing predictive models to mitigate DILI risk in humans.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

Artificial neural networks in contemporary toxicology research

Artificial neural networks (ANNs) have a huge potential in toxicology research. They may be used to predict toxicity of various chemical compounds or classify the compounds based on their toxic effects. Today, numerous ANN models have been developed, some of which may be used to detect and possibly explain complex chemico-biological interactions. Fully connected multilayer perceptrons may in some circumstances have high classification accuracy and discriminatory power in separating damaged from intact cells after exposure to a toxic substance. Regularized and not fully connected convolutional neural networks can detect and identify discrete changes in patterns of two-dimensional data associated with toxicity. Bayesian neural networks with weight marginalization sometimes may have better prediction performance when compared to traditional approaches. With the further development of artificial intelligence, it is expected that ANNs will in the future become important parts of various accurate and affordable biosensors for detection of various toxic substances and evaluation of their biochemical properties. In this concise review article, we discuss the recent research focused on the scientific value of ANNs in evaluation and prediction of toxicity of chemical compounds.

Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Recently, research on the development of artificial intelligence (AI)-based computational toxicology models that predict toxicity without the use of animal testing has emerged because of the rapid development of computer technology. Various computational toxicology techniques that predict toxicity based on the structure of chemical substances are gaining attention, including the quantitative structure-activity relationship. To understand the recent development of these models, we analyzed the databases, molecular descriptors, fingerprints, and algorithms considered in recent studies. Based on a selection of 96 papers published since 2014, we found that AI models have been developed to predict approximately 30 different toxicity end points using more than 20 toxicity databases. For model development, molecular access system and extended-connectivity fingerprints are the most commonly used molecular descriptors. The most used algorithm among the machine learning techniques is the random forest, while the most used algorithm among the deep learning techniques is a deep neural network. The use of AI technology in the development of toxicity prediction models is a new concept that will aid in achieving a scientific accord and meet regulatory applications. The comprehensive overview provided in this study will provide a useful guide for the further development and application of toxicity prediction models.

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

Although drug-induced liver injury (DILI) is a major target of the pharmaceutical industry, we currently lack an efficient model for evaluating liver toxicity in the early stage of its development. Recent progress in artificial intelligence-based deep learning technology promises to improve the accuracy and robustness of current toxicity prediction models. Mask region-based CNN (Mask R-CNN) is a detection-based segmentation model that has been used for developing algorithms. In the present study, we applied a Mask R-CNN algorithm to detect and predict acute hepatic injury lesions induced by acetaminophen (APAP) in Sprague-Dawley rats. To accomplish this, we trained, validated, and tested the model for various hepatic lesions, including necrosis, inflammation, infiltration, and portal triad. We confirmed the model performance at the whole-slide image (WSI) level. The training, validating, and testing processes, which were performed using tile images, yielded an overall model accuracy of 96.44%. For confirmation, we compared the model’s predictions for 25 WSIs at 20× magnification with annotated lesion areas determined by an accredited toxicologic pathologist. In individual WSIs, the expert-annotated lesion areas of necrosis, inflammation, and infiltration tended to be comparable with the values predicted by the algorithm. The overall predictions showed a high correlation with the annotated area. The R square values were 0.9953, 0.9610, and 0.9445 for necrosis, inflammation plus infiltration, and portal triad, respectively. The present study shows that the Mask R-CNN algorithm is a useful tool for detecting and predicting hepatic lesions in non-clinical studies. This new algorithm might be widely useful for predicting liver lesions in non-clinical and clinical settings.

Developing an artificial intelligence method for screening hepatotoxic compounds in traditional Chinese medicine and Western medicine combination

BACKGROUNDS

Traditional Chinese medicine and Western medicine combination (TCM-WMC) increased the complexity of compounds ingested.

OBJECTIVE

To develop a method for screening hepatotoxic compounds in TCM-WMC based on chemical structures using artificial intelligence (AI) methods.

METHODS

Drug-induced liver injury (DILI) data was collected from the public databases and published literatures. The total dataset formed by DILI data was randomly divided into training set and test set at a ratio of 3:1 approximately. Machine learning models of SGD (Stochastic Gradient Descent), kNN (k-Nearest Neighbor), SVM (Support Vector Machine), NB (Naive Bayes), DT (Decision Tree), RF (Random Forest), ANN (Artificial Neural Network), AdaBoost, LR (Logistic Regression) and one deep learning model (deep belief network, DBN) were adopted to construct models for screening hepatotoxic compounds.

RESULT

Dataset of 2035 hepatotoxic compounds was collected in this research, in which 1505 compounds were as training set and 530 compounds were as test set. Results showed that RF obtained 0.838 of classification accuracy (CA), 0.827 of F1-score, 0.832 of Precision, 0.838 of Recall, 0.814 of area under the curve (AUC) on the training set and 0.767 of CA, 0.731 of F1, 0.739 of Precision, 0.767 of Recall, 0.739 of AUC on the test set, which was better than other eight machine learning methods. The DBN obtained 82.2% accuracy on the test set, which was higher than any other machine learning models on the test set.

CONCLUSION

The DILI AI models were expected to effectively screen hepatotoxic compounds in TCM-WMC.

Supervised Methods for Biomarker Detection from Microarray Experiments

Biomarkers are valuable indicators of the state of a biological system. Microarray technology has been extensively used to identify biomarkers and build computational predictive models for disease prognosis, drug sensitivity and toxicity evaluations. Activation biomarkers can be used to understand the underlying signaling cascades, mechanisms of action and biological cross talk. Biomarker detection from microarray data requires several considerations both from the biological and computational points of view. In this chapter, we describe the main methodology used in biomarkers discovery and predictive modeling and we address some of the related challenges. Moreover, we discuss biomarker validation and give some insights into multiomics strategies for biomarker detection.

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

The discovery and development of drugs is a long and expensive process with a high attrition rate. Computational drug discovery contributes to ligand discovery and optimization, by using models that describe the properties of ligands and their interactions with biological targets. In recent years, artificial intelligence (AI) has made remarkable modeling progress, driven by new algorithms and by the increase in computing power and storage capacities, which allow the processing of large amounts of data in a short time. This review provides the current state of the art of AI methods applied to drug discovery, with a focus on structure- and ligand-based virtual screening, library design and high-throughput analysis, drug repurposing and drug sensitivity, de novo design, chemical reactions and synthetic accessibility, ADMET, and quantum mechanics.

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Over 100 drugs and chemicals are associated with permanent hearing loss, tinnitus, and vestibular deficits, collectively known as ototoxicity. The ototoxic potential of drugs is rarely assessed in pre-clinical drug development or during clinical trials, so this debilitating side-effect is often discovered as patients begin to report hearing loss. Furthermore, drug-induced ototoxicity in adults, and particularly in elderly patients, may go unrecognized due to hearing loss from a variety of etiologies because of a lack of baseline assessments immediately prior to novel therapeutic treatment. During the current pandemic, there is an intense effort to identify new drugs or repurpose FDA-approved drugs to treat COVID-19. Several potential COVID-19 therapeutics are known ototoxins, including chloroquine (CQ) and lopinavir-ritonavir, demonstrating the necessity to identify ototoxic potential in existing and novel medicines. Furthermore, several factors are emerging as potentiators of ototoxicity, such as inflammation (a hallmark of COVID-19), genetic polymorphisms, and ototoxic synergy with co-therapeutics, increasing the necessity to evaluate a drug's potential to induce ototoxicity under varying conditions. Here, we review the potential of COVID-19 therapies to induce ototoxicity and factors that may compound their ototoxic effects. We then discuss two models for rapidly detecting the potential for ototoxicity: mammalian auditory cell lines and the larval zebrafish lateral line. These models offer considerable value for pre-clinical drug development, including development of COVID-19 therapies. Finally, we show the validity of in silico screening for ototoxic potential using a computational model that compares structural similarity of compounds of interest with a database of known ototoxins and non-ototoxins. Preclinical screening at in silico, in vitro, and in vivo levels can provide an earlier indication of the potential for ototoxicity and identify the subset of candidate therapeutics for treating COVID-19 that need to be monitored for ototoxicity as for other widely-used clinical therapeutics, like aminoglycosides and cisplatin.

Deep fusion learning facilitates anatomical therapeutic chemical recognition in drug repurposing and discovery

The advent of large-scale biomedical data and computational algorithms provides new opportunities for drug repurposing and discovery. It is of great interest to find an appropriate data representation and modeling method to facilitate these studies. The anatomical therapeutic chemical (ATC) classification system, proposed by the World Health Organization (WHO), is an essential source of information for drug repurposing and discovery. Besides, computational methods are applied to predict drug ATC classification. We conducted a systematic review of ATC computational prediction studies and revealed the differences in data sets, data representation, algorithm approaches, and evaluation metrics. We then proposed a deep fusion learning (DFL) framework to optimize the ATC prediction model, namely DeepATC. The methods based on graph convolutional network, inferring biological network and multimodel attentive fusion network were applied in DeepATC to extract the molecular topological information and low-dimensional representation from the molecular graph and heterogeneous biological networks. The results indicated that DeepATC achieved superior model performance with area under the curve (AUC) value at 0.968. Furthermore, the DFL framework was performed for the transcriptome data-based ATC prediction, as well as another independent task that is significantly relevant to drug discovery, namely drug-target interaction. The DFL-based model achieved excellent performance in the above-extended validation task, suggesting that the idea of aggregating the heterogeneous biological network and node's (molecule or protein) self-topological features will bring inspiration for broader drug repurposing and discovery research.

Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology

There are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) and computational methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional generative adversarial network (cGAN) or deep neural networks (DNN), and leveraging this large set of toxicity data we could efficiently predict toxic outcomes of untested chemicals. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo toxicity and chemical data were used to train two neural network generators. The first was a DNN (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train generators to produce toxicity data. Our results showed that Go-ZT significantly outperformed the cGAN, support vector machine, random forest and multilayer perceptron models in cross-validation, and when tested against an external test dataset. By combining both Go-ZT and GAN-ZT, our consensus model improved the SE, SP, PPV, and Kappa, to 71.4%, 95.9%, 71.4% and 0.673, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.837. Considering their potential use as prescreening tools, these models could provide in vivo toxicity predictions and insight into the hundreds of thousands of untested chemicals to prioritize compounds for HT testing.

The toxicity of SiO2 NPs on cell proliferation and cellular uptake of human lung fibroblastic cell line during the variation of calcination temperature and its modeling by artificial neural network

Less attention had been paid to cell toxicity of the various synthesis methods of nanoparticles, this study investigated the effect of the calcination temperature(CT) on the crystallization of SiO2 nanoparticles(NPs), cell proliferation(CP), and cellular uptake(CU) in MRC-5. In this study, parameters were adjusted as CT(70-1000 °C), calcination time(2, 12, and 24 h), and catalyst feed rate(0.01, 0.05, and 0.1 mL.min1). CP was determined by the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide(MTT) test after a 24-h exposure. The CU was achieved using ICP-MS. Results were analyzed using MATLAB2018. Results revealed that the size of synthesized particles was lower than 50 nm and, the XRD peak varied from 21 to 30° during the increase in CT. FTIR spectra confirmed the existence of Si-O and Si-Cl bonds. The maximum level of crystallization was at 1000 °C. CP decreased with the rise in the concentration of NPs(p < 0.05), as well as an increase in feed rate. A positive relationship between increased crystallization and decreased CP(R = 0.78) was seen, while such a trend was not observed in calcination time. The suggested structure in this study was 4:10:1 with Rall = 0.97, Rtest = 0.97, RMSE = 0.25, and MSE = 0.003. Furthermore, the CU rate increased with the rise in CT and calcination time. The maximum and minimum CU levels were related to NPs calcinated in 1000 °C-24 h and 350 °C-2 h, respectively. As a consequence, the most toxicity of SiO2 NPs was related to the crystalline NP. Therefore, the increase in CT and the calcination time were significant factors affecting on crystallization of SiO2 NPs, CP of lung cell, as well as CU of SiO2.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s40201-021-00663-4.

TOXPANEL: A Gene-Set Analysis Tool to Assess Liver and Kidney Injuries

Gene-set analysis is commonly used to identify trends in gene expression when cells, tissues, organs, or organisms are subjected to conditions that differ from those within the normal physiological range. However, tools for gene-set analysis to assess liver and kidney injury responses are less common. Furthermore, most websites for gene-set analysis lack the option for users to customize their gene-set database. Here, we present the ToxPanel website, which allows users to perform gene-set analysis to assess liver and kidney injuries using activation scores based on gene-expression fold-change values. The results are graphically presented to assess constituent injury phenotypes (histopathology), with interactive result tables that identify the main contributing genes to a given signal. In addition, ToxPanel offers the flexibility to analyze any set of custom genes based on gene fold-change values. ToxPanel is publically available online at https://toxpanel.bhsai.org. ToxPanel allows users to access our previously developed liver and kidney injury gene sets, which we have shown in previous work to yield robust results that correlate with the degree of injury. Users can also test and validate their customized gene sets using the ToxPanel website.

An ensemble learning approach for modeling the systems biology of drug-induced injury

BACKGROUND

Drug-induced liver injury (DILI) is an adverse reaction caused by the intake of drugs of common use that produces liver damage. The impact of DILI is estimated to affect around 20 in 100,000 inhabitants worldwide each year. Despite being one of the main causes of liver failure, the pathophysiology and mechanisms of DILI are poorly understood. In the present study, we developed an ensemble learning approach based on different features (CMap gene expression, chemical structures, drug targets) to predict drugs that might cause DILI and gain a better understanding of the mechanisms linked to the adverse reaction.

RESULTS

We searched for gene signatures in CMap gene expression data by using two approaches: phenotype-gene associations data from DisGeNET, and a non-parametric test comparing gene expression of DILI-Concern and No-DILI-Concern drugs (as per DILIrank definitions). The average accuracy of the classifiers in both approaches was 69%. We used chemical structures as features, obtaining an accuracy of 65%. The combination of both types of features produced an accuracy around 63%, but improved the independent hold-out test up to 67%. The use of drug-target associations as feature obtained the best accuracy (70%) in the independent hold-out test.

CONCLUSIONS

When using CMap gene expression data, searching for a specific gene signature among the landmark genes improves the quality of the classifiers, but it is still limited by the intrinsic noise of the dataset. When using chemical structures as a feature, the structural diversity of the known DILI-causing drugs hampers the prediction, which is a similar problem as for the use of gene expression information. The combination of both features did not improve the quality of the classifiers but increased the robustness as shown on independent hold-out tests. The use of drug-target associations as feature improved the prediction, specially the specificity, and the results were comparable to previous research studies.

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.

Use of deep learning methods to translate drug-induced gene expression changes from rat to human primary hepatocytes

In clinical trials, animal and cell line models are often used to evaluate the potential toxic effects of a novel compound or candidate drug before progressing to human trials. However, relating the results of animal and in vitro model exposures to relevant clinical outcomes in the human in vivo system still proves challenging, relying on often putative orthologs. In recent years, multiple studies have demonstrated that the repeated dose rodent bioassay, the current gold standard in the field, lacks sufficient sensitivity and specificity in predicting toxic effects of pharmaceuticals in humans. In this study, we evaluate the potential of deep learning techniques to translate the pattern of gene expression measured following an exposure in rodents to humans, circumventing the current reliance on orthologs, and also from in vitro to in vivo experimental designs. Of the applied deep learning architectures applied in this study the convolutional neural network (CNN) and a deep artificial neural network with bottleneck architecture significantly outperform classical machine learning techniques in predicting the time series of gene expression in primary human hepatocytes given a measured time series of gene expression from primary rat hepatocytes following exposure in vitro to a previously unseen compound across multiple toxicologically relevant gene sets. With a reduction in average mean absolute error across 76 genes that have been shown to be predictive for identifying carcinogenicity from 0.0172 for a random regression forest to 0.0166 for the CNN model (p < 0.05). These deep learning architecture also perform well when applied to predict time series of in vivo gene expression given measured time series of in vitro gene expression for rats.

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.

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.

In silico toxicology: From structure–activity relationships towards deep learning and adverse outcome pathways

In silico toxicology is an emerging field. It gains increasing importance as research is aiming to decrease the use of animal experiments as suggested in the 3R principles by Russell and Burch. In silico toxicology is a means to identify hazards of compounds before synthesis, and thus in very early stages of drug development. For chemical industries, as well as regulatory agencies it can aid in gap‐filling and guide risk minimization strategies. Techniques such as structural alerts, read‐across, quantitative structure–activity relationship, machine learning, and deep learning allow to use in silico toxicology in many cases, some even when data is scarce. Especially the concept of adverse outcome pathways puts all techniques into a broader context and can elucidate predictions by mechanistic insights.

This article is categorized under:

Structure and Mechanism > Computational Biochemistry and Biophysics

Data Science > Chemoinformatics