An Overview of Machine Learning and Big Data for Drug Toxicity Evaluation

A nonneglectable stereochemical factor in drug development: Atropisomerism

Chirality is one of the key factors affecting the medicinal efficacy of compounds. In addition to central chirality, sterically hindered chiral axes commonly appear in drugs and the resulting chirality is known as atropisomerism. With developments in medicinal chemistry, atropisomerism has attracted increasing attention. This review discusses the classification, biological activity, pharmacokinetics, toxicity and side effects of atropisomers, and can serve as a reference in the research and development of potential chiral drugs.

Predicting chemical hazard across taxa through machine learning

We applied machine learning methods to predict chemical hazards focusing on fish acute toxicity across taxa. We analyzed the relevance of taxonomy and experimental setup, showing that taking them into account can lead to considerable improvements in the classification performance. We quantified the gain obtained throught the introduction of taxonomic and experimental information, compared to classification based on chemical information alone. We used our approach with standard machine learning models (K-nearest neighbors, random forests and deep neural networks), as well as the recently proposed Read-Across Structure Activity Relationship (RASAR) models, which were very successful in predicting chemical hazards to mammals based on chemical similarity. We were able to obtain accuracies of over 93% on datasets where, due to noise in the data, the maximum achievable accuracy was expected to be below 96%. The best performances were obtained by random forests and RASAR models. We analyzed metrics to compare our results with animal test reproducibility, and despite most of our models "outperform animal test reproducibility" as measured through recently proposed metrics, we showed that the comparison between machine learning performance and animal test reproducibility should be addressed with particular care. While we focused on fish mortality, our approach, provided that the right data is available, is valid for any combination of chemicals, effects and taxa.

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

Drug-induced immune thrombocytopenia (DITP) often occurs in patients receiving many drug treatments simultaneously. However, clinicians usually fail to accurately distinguish which drugs can be plausible culprits. Despite significant advances in laboratory-based DITP testing, in vitro experimental assays have been expensive and, in certain cases, cannot provide a timely diagnosis to patients. To address these shortcomings, this paper proposes an efficient machine learning-based method for DITP toxicity prediction. A small dataset consisting of 225 molecules was constructed. The molecules were represented by six fingerprints, three descriptors, and their combinations. Seven classical machine learning-based models were examined to determine an optimal model. The results show that the RDMD + PubChem-k-NN model provides the best prediction performance among all the models, achieving an area under the curve of 76.9% and overall accuracy of 75.6% on the external validation set. The application domain (AD) analysis demonstrates the prediction reliability of the RDMD + PubChem-k-NN model. Five structural fragments related to the DITP toxicity are identified through information gain (IG) method along with fragment frequency analysis. Overall, as far as known, it is the first machine learning-based classification model for recognizing chemicals with DITP toxicity and can be used as an efficient tool in drug design and clinical therapy.

An Explainable Supervised Machine Learning Model for Predicting Respiratory Toxicity of Chemicals Using Optimal Molecular Descriptors

Respiratory toxicity is a serious public health concern caused by the adverse effects of drugs or chemicals, so the pharmaceutical and chemical industries demand reliable and precise computational tools to assess the respiratory toxicity of compounds. The purpose of this study is to develop quantitative structure-activity relationship models for a large dataset of chemical compounds associated with respiratory system toxicity. First, several feature selection techniques are explored to find the optimal subset of molecular descriptors for efficient modeling. Then, eight different machine learning algorithms are utilized to construct respiratory toxicity prediction models. The support vector machine classifier outperforms all other optimized models in 10-fold cross-validation. Additionally, it outperforms the prior study by 2% in prediction accuracy and 4% in MCC. The best SVM model achieves a prediction accuracy of 86.2% and a MCC of 0.722 on the test set. The proposed SVM model predictions are explained using the SHapley Additive exPlanations approach, which prioritizes the relevance of key modeling descriptors influencing the prediction of respiratory toxicity. Thus, our proposed model would be incredibly beneficial in the early stages of drug development for predicting and understanding potential respiratory toxic compounds.

Evaluation of Toxicity and Oxidative Stress of 2-Acetylpyridine-N(4)-orthochlorophenyl Thiosemicarbazone

Thiosemicarbazones are well known for their broad spectrum of action, including antitumoral and antiparasitic activities. Thiosemicarbazones work as chelating binders, reacting with metal ions. The objective of this work was to investigate the in silico, in vitro, and in vivo toxicity and oxidative stress of 2-acetylpyridine-N(4)-orthochlorophenyl thiosemicarbazone (TSC01). The in silico prediction showed good absorption by biological membranes and no theoretical toxicity. Also, the compound did not show cytotoxicity against Hep-G2 and HT-29 cells. In the acute nonclinical toxicological test, the animals treated with TSC01 showed behavioral changes of stimulus of the central nervous system (CNS) at 300 mg/kg. One hour after administration, a dose of 2000 mg/kg caused depressive signs. All changes disappeared after 24 h, with no deaths, which suggest an estimated LD50 of 5000 mg/kg and GSH 5. The group treated with 2000 mg/kg had an increase of water consumption and weight gain in the second week. The biochemical parameters presented no toxicity relevance, and the analysis of oxidative stress in the liver found an increase of lipid peroxidation and nitric oxide. However, histopathological analysis showed organ integrity was maintained without any changes. In conclusion, the results show the low toxicological potential of thiosemicarbazone derivative, indicating future safe use.

Machine learning models on chemical inhibitors of mitochondrial electron transport chain

Chemicals can induce adverse effects in humans by inhibiting mitochondrial electron transport chain (ETC) such as disrupting mitochondrial membrane potential, enhancing oxidative stress and causing some diseases. Thus, identifying ETC inhibitors (ETCi) is important to chemical risk assessment and protecting the public health. However, it is not feasible to identify all ETCi with experimental methods. Quantitative structure-activity relationship (QSAR) modeling is a promising method to rapidly and effectively identify ETCi. In this study, QSAR models for predicting ETCi were developed using machine learning methods. A clustering-based under-sampling (CBUS) method was developed to handle the imbalance issue in training sets. Structure-activity landscapes were generated and analyzed for training sets generated by the CBUS method. The consensus QSAR models constructed with CBUS achieved satisfactory performances (balanced accuracy = 0.852) in 100 iterations of five-fold cross validations, indicating the models can effectively classify ETCi. The classification model was further employed to screen chemicals in the Inventory of Existing Chemical Substances of China and 13 chemicals were identified as ETCi. Fifteen structural alerts for ETCi were identified in this study. These results demonstrated that the model and structural alerts are useful to screen ETCi.

Explainable multimodal machine learning model for classifying pregnancy drug safety

MOTIVATION

Teratogenic drugs can cause severe fetal malformation and therefore have critical impact on the health of the fetus, yet the teratogenic risks are unknown for most approved drugs. This article proposes an explainable machine learning model for classifying pregnancy drug safety based on multimodal data and suggests an orthogonal ensemble for modeling multimodal data. To train the proposed model, we created a set of labeled drugs by processing over 100 000 textual responses collected by a large teratology information service. Structured textual information is incorporated into the model by applying clustering analysis to textual features.

RESULTS

We report an area under the receiver operating characteristic curve (AUC) of 0.891 using cross-validation and an AUC of 0.904 for cross-expert validation. Our findings suggest the safety of two drugs during pregnancy, Varenicline and Mebeverine, and suggest that Meloxicam, an NSAID, is of higher risk; according to existing data, the safety of these three drugs during pregnancy is unknown. We also present a web-based application that enables physicians to examine a specific drug and its risk factors.

AVAILABILITY AND IMPLEMENTATION

The code and data is available from https://github.com/goolig/drug_safety_pregnancy_prediction.git.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A new method for predicting the acute toxicity of carbamate pesticides based on the perspective of binding information with carrier protein

Toxicity is one of the most important factors limiting the success of new drug development. In this paper, we built a fast and convenient new method (Carrier protein binding information-toxicity relationship, CPBITR) for predicting drug acute toxicity based on the perspective of binding information with carrier protein. First, we studied the binding information between carbamate pesticides and human serum albumin (HSA) through various spectroscopic methods and molecular docking. Then a total of 16 models were established to clarify the relationship between binding information with HSA and drug toxicity. The results showed that the binding information was related to toxicity. Finally we obtained the effective toxicity prediction model for carbamate pesticides. And the "Platform for Predicting Drug Toxicity Based on the Information of Binding with Carrier Protein" was established with the Back-propagation neural network model. We proposed and proved that it was feasible to predict drug toxicity from this new perspective: binding with carrier protein. According to this new perspective, toxicity prediction model of other drugs can also be established. This new method has the advantages of convenience and fast, and can be used to screen out low-toxic drugs quickly in the early stage. It is helpful for drug research and development.

Application of Artificial Intelligence and Machine Learning in Drug Discovery

Machine Learning (ML) and Deep Learning (DL) are two subclasses of Artificial Intelligence (AI), that, in this day and age of big data provides significant opportunities to pharmaceutical discovery research and development by translating data to information and ultimately to knowledge. Machine Learning or AI is not really new but over last few years, application of better methods have emerged and they have been successfully applied for drug discovery and development. This chapter would provide an overview of these methods and how they have been applied across various work streams, e.g., generative chemistry, ADMET prediction, retrosynthetic analysis, etc. within drug discovery process. This chapter would also attempt to provide caution and pit falls in utilizing these methods blindly while summarizing challenges and limitations.

Deep Learning Approaches and Applications in Toxicologic Histopathology: Current Status and Future Perspectives

Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research.

Chemical characterization of anemia-inducing aniline-related substances and their application to the construction of a decision tree-based anemia prediction model

Anemia is a well-observed toxicity of chemical substances, and aniline is a typical anemia-inducing substance. However, it remains unclear whether all aniline-like substances with various substituents could induce anemia. We thus investigated the physicochemical characteristics of anemia-inducing substances by decision tree analyses. Training and validation substances were selected from a publicly available database of rat repeated-dose toxicity studies, and discrimination models were constructed by decision tree and bootstrapping methods with molecular descriptors as explanatory variables. To improve the accuracy of discrimination, we individually evaluated the explanatory variables to modify them, established "prerules" that were applied before subjecting a substance to a decision tree by considering metabolism, such as azo reduction and N-dealkylation, and introduced the idea of "partly negative" evaluation for substances having multiple aniline-like substructures. The final model obtained showed 79.2% and 77.5% accuracy for the training and validation dataset, respectively. In addition, we identified some chemical properties that reduce the anemia inducibility of aniline-like substances, including the addition of a sulfonate or carboxy functional group and/or a bulky multiring structure to anilines. In conclusion, the present findings will provide a novel insight into the mechanistic understanding of chemically induced anemia and help to develop a prediction system.

AI in drug development: a multidisciplinary perspective

The introduction of a new drug to the commercial market follows a complex and long process that typically spans over several years and entails large monetary costs due to a high attrition rate. Because of this, there is an urgent need to improve this process using innovative technologies such as artificial intelligence (AI). Different AI tools are being applied to support all four steps of the drug development process (basic research for drug discovery; pre-clinical phase; clinical phase; and postmarketing). Some of the main tasks where AI has proven useful include identifying molecular targets, searching for hit and lead compounds, synthesising drug-like compounds and predicting ADME-Tox. This review, on the one hand, brings in a mathematical vision of some of the key AI methods used in drug development closer to medicinal chemists and, on the other hand, brings the drug development process and the use of different models closer to mathematicians. Emphasis is placed on two aspects not mentioned in similar surveys, namely, Bayesian approaches and their applications to molecular modelling and the eventual final use of the methods to actually support decisions. Promoting a perfect synergy.

Ethical Artificial Intelligence in Chemical Research and Development: A Dual Advantage for Sustainability

Artificial intelligence can be a game changer to address the global challenge of humanity-threatening climate change by fostering sustainable development. Since chemical research and development lay the foundation for innovative products and solutions, this study presents a novel chemical research and development process backed with artificial intelligence and guiding ethical principles to account for both process- and outcome-related sustainability. Particularly in ethically salient contexts, ethical principles have to accompany research and development powered by artificial intelligence to promote social and environmental good and sustainability (beneficence) while preventing any harm (non-maleficence) for all stakeholders (i.e., companies, individuals, society at large) affected.

In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Chemical-induced hematotoxicity is an important concern in the drug discovery, since it can often be fatal when it happens. It is quite useful for us to give special attention to chemicals which can cause hematotoxicity. In the present study, we focused on in silico prediction of chemical-induced hematotoxicity with machine learning (ML) and deep learning (DL) methods. We collected a large data set contained 632 hematotoxic chemicals and 1525 approved drugs without hematotoxicity. Computational models were built using several different machine learning and deep learning algorithms integrated on the Online Chemical Modeling Environment (OCHEM). Based on the three best individual models, a consensus model was developed. It yielded the prediction accuracy of 0.83 and balanced accuracy of 0.77 on external validation. The consensus model and the best individual model developed with random forest regression and classification algorithm (RFR) and QNPR descriptors were made available at https://ochem.eu/article/135149 , respectively. The relevance of 8 commonly used molecular properties and chemical-induced hematotoxicity was also investigated. Several molecular properties have an obvious differentiating effect on chemical-induced hematotoxicity. Besides, 12 structural alerts responsible for chemical hematotoxicity were identified using frequency analysis of substructures from Klekota-Roth fingerprint. These results should provide meaningful knowledge and useful tools for hematotoxicity evaluation in drug discovery and environmental risk assessment.

Modeling approaches for reducing safety-related attrition in drug discovery and development: a review on myelotoxicity, immunotoxicity, cardiovascular toxicity, and liver toxicity

Introduction:Safety and tolerability is a critical area where improvements are needed to decrease the attrition rates during development of new drug candidates. Modeling approaches, when smartly implemented, can contribute to this aim.Areas covered:The focus of this review was on modeling approaches applied to four kinds of drug-induced toxicities: hematological, immunological, cardiovascular (CV) and liver toxicity. Papers, mainly published in the last 10 years, reporting models in three main methodological categories - computational models (e.g., quantitative structure-property relationships, machine learning approaches, neural networks, etc.), pharmacokinetic-pharmacodynamic (PK-PD) models, and quantitative system pharmacology (QSP) models - have been considered.Expert opinion:The picture observed in the four examined toxicity areas appears heterogeneous. Computational models are typically used in all areas as screening tools in the early stages of development for hematological, cardiovascular and liver toxicity, with accuracies in the range of 70-90%. A limited number of computational models, based on the analysis of drug protein sequence, was instead proposed for immunotoxicity. In the later stages of development, toxicities are quantitatively predicted with reasonably good accuracy using either semi-mechanistic PK-PD models (hematological and cardiovascular toxicity), or fully exploited QSP models (immuno-toxicity and liver toxicity).

Assessing the calibration in toxicological in vitro models with conformal prediction

Machine learning methods are widely used in drug discovery and toxicity prediction. While showing overall good performance in cross-validation studies, their predictive power (often) drops in cases where the query samples have drifted from the training data’s descriptor space. Thus, the assumption for applying machine learning algorithms, that training and test data stem from the same distribution, might not always be fulfilled. In this work, conformal prediction is used to assess the calibration of the models. Deviations from the expected error may indicate that training and test data originate from different distributions. Exemplified on the Tox21 datasets, composed of chronologically released Tox21Train, Tox21Test and Tox21Score subsets, we observed that while internally valid models could be trained using cross-validation on Tox21Train, predictions on the external Tox21Score data resulted in higher error rates than expected. To improve the prediction on the external sets, a strategy exchanging the calibration set with more recent data, such as Tox21Test, has successfully been introduced. We conclude that conformal prediction can be used to diagnose data drifts and other issues related to model calibration. The proposed improvement strategy—exchanging the calibration data only—is convenient as it does not require retraining of the underlying model.

Human Induced Pluripotent Stem Cells as a Screening Platform for Drug-Induced Vascular Toxicity

Evaluation of potential vascular injury is an essential part of the safety study during pharmaceutical development. Vascular liability issues are important causes of drug termination during preclinical investigations. Currently, preclinical assessment of vascular toxicity primarily relies on the use of animal models. However, accumulating evidence indicates a significant discrepancy between animal toxicity and human toxicity, casting doubt on the clinical relevance of animal models for such safety studies. While the causes of this discrepancy are expected to be multifactorial, species differences are likely a key factor. Consequently, a human-based model is a desirable solution to this problem, which has been made possible by the advent of human induced pluripotent stem cells (iPSCs). In particular, recent advances in the field now allow the efficient generation of a variety of vascular cells (e.g., endothelial cells, smooth muscle cells, and pericytes) from iPSCs. Using these cells, different vascular models have been established, ranging from simple 2D cultures to highly sophisticated vascular organoids and microfluidic devices. Toxicity testing using these models can recapitulate key aspects of vascular pathology on molecular (e.g., secretion of proinflammatory cytokines), cellular (e.g., cell apoptosis), and in some cases, tissue (e.g., endothelium barrier dysfunction) levels. These encouraging data provide the rationale for continuing efforts in the exploration, optimization, and validation of the iPSC technology in vascular toxicology.

Drug Safety Data Curation and Modeling in ChEMBL: Boxed Warnings and Withdrawn Drugs

The safety of marketed drugs is an ongoing concern, with some of the more frequently prescribed medicines resulting in serious or life-threatening adverse effects in some patients. Safety-related information for approved drugs has been curated to include the assignment of toxicity class(es) based on their withdrawn status and/or black box warning information described on medicinal product labels. The ChEMBL resource contains a wide range of bioactivity data types, from early "Discovery" stage preclinical data for individual compounds through to postclinical data on marketed drugs; the inclusion of the curated drug safety data set within this framework can support a wide range of safety-related drug discovery questions. The curated drug safety data set will be made freely available through ChEMBL and updated in future database releases.

Predicting the reproductive toxicity of chemicals using ensemble learning methods and molecular fingerprints

Reproductive toxicity endpoints are a significant safety concern in the assessment of the adverse effects of chemicals in drug discovery. Computational models that can accurately predict a chemical's toxic potential are increasingly pursued to replace traditional animal experiments. Thus, ensemble learning models were built to predict the reproductive toxicity of compounds. Our ensemble models were developed using support vector machine, random forest, and extreme gradient boosting methods and 9 molecular fingerprints calculated for a dataset containing 1823 chemicals. The best prediction performance was achieved by the Ensemble-Top12 model, with an accuracy (ACC) of 86.33 %, a sensitivity (SEN) of 82.02 %, a specificity (SPE) of 90.19 %, and an area under the receiver operating characteristic curve (AUC) of 0.937 in 5-fold cross-validation and ACC, SEN, SPE, and AUC values of 84.38 %, 86.90 %, 90.67 %, and 0.920, respectively, in external validation. We also defined the applicability domain (AD) of the ensemble model by calculating the Tanimoto distance of the training set. Compared with models in existing literature, our ensemble model achieves relatively high ACC, SPE and AUC values. We also identified several fingerprint features related to chemical reproductive toxicity. Considering the performance of model, we recommend using the Ensemble-Top12 model to predict reproductive toxicity in early drug development.

Quantitative Structure-Activity Relationship (QSAR) Model for the Severity Prediction of Drug-Induced Rhabdomyolysis by Using Random Forest

Drug-induced rhabdomyolysis (DIR) is a rare and potentially life-threatening muscle injury that is characterized by low incidence and high risk. To our best knowledge, the performance of the current predictive models for the early detection of DIR is suboptimal because of the scarcity and dispersion of DIR cases. Therefore, on the basis of the curated drug information from the Drug-Induced Rhabdomyolysis Atlas (DIRA) database, we proposed a random forest (RF) model to predict the DIR severity of the marketed drugs. Compared with the state-of-art methods, our proposed model outperformed extreme gradient boosting, support vector machine, and logistic regression in distinguishing the Most-DIR concern drugs from the No-DIR concern drugs (Matthews correlation coefficient (MCC) and recall rate of our model were 0.46 and 0.81, respectively). Our model was subsequently applied to predicting the potentially serious DIR for 1402 drugs, which were reported to cause DIR by the postmarketing DIR surveillance data in the FDA Spontaneous Adverse Events Reporting System (FAERS). As a result, 62.7% (94) of drugs ranked in the top 150 drugs with the Most-DIR concerns in FAERS can be identified by our model. The top four drugs (odds ratio >30) including acepromazine, rapacuronium, oxyphenbutazone, and naringenin were correctly predicted by our model. In conclusion, the RF model can well predict the Most-DIR concern drug only based on the chemical structure information and can be a facilitated tool for early DIR detection.

Big data and machine learning for materials science

Herein, we review aspects of leading-edge research and innovation in materials science that exploit big data and machine learning (ML), two computer science concepts that combine to yield computational intelligence. ML can accelerate the solution of intricate chemical problems and even solve problems that otherwise would not be tractable. However, the potential benefits of ML come at the cost of big data production; that is, the algorithms demand large volumes of data of various natures and from different sources, from material properties to sensor data. In the survey, we propose a roadmap for future developments with emphasis on computer-aided discovery of new materials and analysis of chemical sensing compounds, both prominent research fields for ML in the context of materials science. In addition to providing an overview of recent advances, we elaborate upon the conceptual and practical limitations of big data and ML applied to materials science, outlining processes, discussing pitfalls, and reviewing cases of success and failure.

Cheminformatics to Characterize Pharmacologically Active Natural Products

Natural products have a significant role in drug discovery. Natural products have distinctive chemical structures that have contributed to identifying and developing drugs for different therapeutic areas. Moreover, natural products are significant sources of inspiration or starting points to develop new therapeutic agents. Natural products such as peptides and macrocycles, and other compounds with unique features represent attractive sources to address complex diseases. Computational approaches that use chemoinformatics and molecular modeling methods contribute to speed up natural product-based drug discovery. Several research groups have recently used computational methodologies to organize data, interpret results, generate and test hypotheses, filter large chemical databases before the experimental screening, and design experiments. This review discusses a broad range of chemoinformatics applications to support natural product-based drug discovery. We emphasize profiling natural product data sets in terms of diversity; complexity; acid/base; absorption, distribution, metabolism, excretion, and toxicity (ADME/Tox) properties; and fragment analysis. Novel techniques for the visual representation of the chemical space are also discussed.

In Silico ADME/Tox Profiling of Natural Products: A Focus on BIOFACQUIM

Natural products continue to be major sources of bioactive compounds and drug candidates not only because of their unique chemical structures but also because of their overall favorable metabolism and pharmacokinetic properties. The number of publicly accessible natural product databases has increased significantly in the past few years. However, the systematic ADME/Tox profile has been reported on a limited basis. For instance, BIOFACQUIM was recently published as a public database of natural products from Mexico, a country with a rich source of biomolecules. However, its ADME/Tox profile has not been reported. Herein, we discuss the results of an in-depth in silico ADME/Tox profile of natural products in BIOFACQUIM and other large public collections of natural products. It was concluded that the absorption and distribution profiles of compounds in BIOFACQUIM are similar to those of approved drugs, while the metabolism profile is comparable to that in the other natural product databases. The excretion profile of compounds in BIOFACQUIM is different from that of the approved drugs, but their predicted toxicity profile is comparable. This work further contributes to the deeper characterization of natural product collections as major sources of bioactive compounds with therapeutic potential.

Predicting coated-nanoparticle drug release systems with perturbation-theory machine learning (PTML) models

Nanoparticles (NPs) decorated with coating agents (polymers, gels, proteins, etc.) form Nanoparticle Drug Delivery Systems (DDNS), which are of high interest in nanotechnology and biomaterials science. There have been increasing reports of experimental data sets of biological activity, toxicity, and delivery properties of DDNS. However, these data sets are still dispersed and not as large as the datasets of DDNS components (NP and drugs). This has prompted researchers to train Machine Learning (ML) algorithms that are able to design new DDNS based on the properties of their components. However, most ML models reported up to date predictions of the specific activities of NP or drugs over a determined target or cell line. In this paper, we combine Perturbation Theory and Machine Learning (PTML algorithm) to train a model that is able to predict the best components (NP, coating agent, and drug) for DDNS design. In so doing, we downloaded a dataset of >30 000 preclinical assays of drugs from ChEMBL. We also downloaded an NP data set formed by preclinical assays of coated Metal Oxide Nanoparticles (MONPs) from public sources. Both the drugs and NP datasets of preclinical assays cover multiple conditions of assays that can be listed as two arrays, namely, cjdrug and cjNP. The cjdrug array includes >504 biological activity parameters (c0drug), >340 target proteins (c1drug), >650 types of cells (c2drug), >120 assay organisms (c3drug), and >60 assay strains (c4drug). On the other hand, the cjNP array includes 3 biological activity parameters (c0NP), 40 types of proteins (c1NP), 10 shapes of nanoparticles (c2NP), 6 assay media (c3NP), and 12 coating agents (c4NP). After downloading, we pre-processed both the data sets by separate calculation PT operators that are able to account for changes (perturbations) in the drug, coating agents, and NP chemical structure and/or physicochemical properties as well as for the assay conditions. Next, we carry out an information fusion process to form a final dataset of above 500 000 DDNS (drug + MONP pairs). We also trained other linear and non-linear PTML models using R studio scripts for comparative purposes. To the best of our knowledge, this is the first multi-label PTML model that is useful for the selection of drugs, coating agents, and metal or metal-oxide nanoparticles to be assembled in order to design new DDNS with optimal activity/toxicity profiles.

Transcriptomics in Toxicogenomics, Part I: Experimental Design, Technologies, Publicly Available Data, and Regulatory Aspects

The starting point of successful hazard assessment is the generation of unbiased and trustworthy data. Conventional toxicity testing deals with extensive observations of phenotypic endpoints in vivo and complementing in vitro models. The increasing development of novel materials and chemical compounds dictates the need for a better understanding of the molecular changes occurring in exposed biological systems. Transcriptomics enables the exploration of organisms' responses to environmental, chemical, and physical agents by observing the molecular alterations in more detail. Toxicogenomics integrates classical toxicology with omics assays, thus allowing the characterization of the mechanism of action (MOA) of chemical compounds, novel small molecules, and engineered nanomaterials (ENMs). Lack of standardization in data generation and analysis currently hampers the full exploitation of toxicogenomics-based evidence in risk assessment. To fill this gap, TGx methods need to take into account appropriate experimental design and possible pitfalls in the transcriptomic analyses as well as data generation and sharing that adhere to the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. In this review, we summarize the recent advancements in the design and analysis of DNA microarray, RNA sequencing (RNA-Seq), and single-cell RNA-Seq (scRNA-Seq) data. We provide guidelines on exposure time, dose and complex endpoint selection, sample quality considerations and sample randomization. Furthermore, we summarize publicly available data resources and highlight applications of TGx data to understand and predict chemical toxicity potential. Additionally, we discuss the efforts to implement TGx into regulatory decision making to promote alternative methods for risk assessment and to support the 3R (reduction, refinement, and replacement) concept. This review is the first part of a three-article series on Transcriptomics in Toxicogenomics. These initial considerations on Experimental Design, Technologies, Publicly Available Data, Regulatory Aspects, are the starting point for further rigorous and reliable data preprocessing and modeling, described in the second and third part of the review series.

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.