Predicting Cytotoxicity of Metal Oxide Nanoparticles using Isalos Analytics Platform

TISBE: A Public Web Platform for the Consensus-Based Explainable Prediction of Developmental Toxicity

Despite being extremely relevant for the protection of prenatal and neonatal health, the developmental toxicity (Dev Tox) is a highly complex endpoint whose molecular rationale is still largely unknown. The lack of availability of high-quality data as well as robust nontesting methods makes its understanding even more difficult. Thus, the application of new explainable alternative methods is of utmost importance, with Dev Tox being one of the most animal-intensive research themes of regulatory toxicology. Descending from TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), the present work describes TISBE (TIRESIA Improved on Structure-Based Explainability), a new public web platform implementing four fundamental advancements for in silico analyses: a three times larger dataset, a transparent XAI (explainable artificial intelligence) framework employing a fragment-based fingerprint coding, a novel consensus classifier based on five independent machine learning models, and a new applicability domain (AD) method based on a double top-down approach for better estimating the prediction reliability. The training set (TS) includes as many as 1008 chemicals annotated with experimental toxicity values. Based on a 5-fold cross-validation, a median value of 0.410 for the Matthews correlation coefficient was calculated; TISBE was very effective, with a median value of sensitivity and specificity equal to 0.984 and 0.274, respectively. TISBE was applied on two external pools made of 1484 bioactive compounds and 85 pediatric drugs taken from ChEMBL (Chemical European Molecular Biology Laboratory) and TEDDY (Task-Force in Europe for Drug Development in the Young) repositories, respectively. Notably, TISBE gives users the option to clearly spot the molecular fragments responsible for the toxicity or the safety of a given chemical query and is available for free at https://prometheus.farmacia.uniba.it/tisbe.

An ancestral molecular response to nanomaterial particulates

The varied transcriptomic response to nanoparticles has hampered the understanding of the mechanism of action. Here, by performing a meta-analysis of a large collection of transcriptomics data from various engineered nanoparticle exposure studies, we identify common patterns of gene regulation that impact the transcriptomic response. Analysis identifies deregulation of immune functions as a prominent response across different exposure studies. Looking at the promoter regions of these genes, a set of binding sites for zinc finger transcription factors C2H2, involved in cell stress responses, protein misfolding and chromatin remodelling and immunomodulation, is identified. The model can be used to explain the outcomes of mechanism of action and is observed across a range of species indicating this is a conserved part of the innate immune system.

A data reusability assessment in the nanosafety domain based on the NSDRA framework followed by an exploratory quantitative structure activity relationships (QSAR) modeling targeting cellular viability

INTRODUCTION

The current effort towards the digital transformation across multiple scientific domains requires data that is Findable, Accessible, Interoperable and Reusable (FAIR). In addition to the FAIR data, what is required for the application of computational tools, such as Quantitative Structure Activity Relationships (QSARs), is a sufficient data volume and the ability to merge sources into homogeneous digital assets. In the nanosafety domain there is a lack of FAIR available metadata.

METHODOLOGY

To address this challenge, we utilized 34 datasets from the nanosafety domain by exploiting the NanoSafety Data Reusability Assessment (NSDRA) framework, which allowed the annotation and assessment of dataset's reusability. From the framework's application results, eight datasets targeting the same endpoint (i.e. numerical cellular viability) were selected, processed and merged to test several hypothesis including universal versus nanogroup-specific QSAR models (metal oxide and nanotubes), and regression versus classification Machine Learning (ML) algorithms.

RESULTS

Universal regression and classification QSARs reached an 0.86 R2 and 0.92 accuracy, respectively, for the test set. Nanogroup-specific regression models reached 0.88 R2 for nanotubes test set followed by metal oxide (0.78). Nanogroup-specific classification models reached 0.99 accuracy for nanotubes test set, followed by metal oxide (0.91). Feature importance revealed different patterns depending on the dataset with common influential features including core size, exposure conditions and toxicological assay. Even in the case where the available experimental knowledge was merged, the models still failed to correctly predict the outputs of an unseen dataset, revealing the cumbersome conundrum of scientific reproducibility in realistic applications of QSAR for nanosafety. To harness the full potential of computational tools and ensure their long-term applications, embracing FAIR data practices is imperative in driving the development of responsible QSAR models.

CONCLUSIONS

This study reveals that the digitalization of nanosafety knowledge in a reproducible manner has a long way towards its successful pragmatic implementation. The workflow carried out in the study shows a promising approach to increase the FAIRness across all the elements of computational studies, from dataset's annotation, selection, merging to FAIR modeling reporting. This has significant implications for future research as it provides an example of how to utilize and report different tools available in the nanosafety knowledge system, while increasing the transparency of the results. One of the main benefits of this workflow is that it promotes data sharing and reuse, which is essential for advancing scientific knowledge by making data and metadata FAIR compliant. In addition, the increased transparency and reproducibility of the results can enhance the trustworthiness of the computational findings.

TiO2 nanoparticles' library toxicity (UV and non-UV exposure) - High-throughput in vivo transcriptomics reveals mechanisms

The hazards of nanomaterials/nanoparticles (NMs/NPs) are mostly assessed using individual NMs, and a more systematic approach, using many NMs, is needed to evaluate its risks in the environment. Libraries of NMs, with a range of identified different but related characters/descriptors allow the comparison of effects across many NMs. The effects of a custom designed Fe-doped TiO₂ NMs library containing 11 NMs was assessed on the soil model Enchytraeus crypticus (Oligochaeta), both with and without UV (standard fluorescent) radiation. Effects were analyzed at organism (phenotypic, survival and reproduction) and gene expression level (transcriptomics, high-throughput 4x44K microarray) to understand the underlying mechanisms. A total of 48 microarrays (20 test conditions) were done plus controls (UV and non-UV). Unique mechanisms induced by TiO₂ NPs exposure included the impairment in RNA processing for TiO₂_10nm, or deregulated apoptosis for 2%FeTiO₂_10nm. Strikingly apparent was the size dependent effects such as induction of reproductive effects via smaller TiO₂ NPs (≤12 nm) - embryo interaction, while larger particles (27 nm) caused reproductive effects through different mechanisms. Also, phagocytosis was affected by 12 and 27 nm NPs, but not by ≤11 nm. The organism level study shows the integrated response, i.e. the result after a cascade of events. While uni-cell models offer key mechanistic information, we here deliver a combined biological system level (phenotype and genotype), seldom available, especially for environmental models.

Predicting the toxicity of nanoparticles using artificial intelligence tools: a systematic review

Nanoparticles have been used extensively in different scientific fields. Due to the possible destructive effects of nanoparticles on the environment or the biological systems, their toxicity evaluation is a crucial phase for studying nanomaterial safety. In the meantime, experimental approaches for toxicity assessment of various nanoparticles are expensive and time-consuming. Thus, an alternative technique, such as artificial intelligence (AI), could be valuable for predicting nanoparticle toxicity. Therefore, in this review, the AI tools were investigated for the toxicity assessment of nanomaterials. To this end, a systematic search was performed on PubMed, Web of Science, and Scopus databases. Articles were included or excluded based on pre-defined inclusion and exclusion criteria, and duplicate studies were excluded. Finally, twenty-six studies were included. The majority of the studies were conducted on metal oxide and metallic nanoparticles. In addition, Random Forest (RF) and Support Vector Machine (SVM) had the most frequency in the included studies. Most of the models demonstrated acceptable performance. Overall, AI could provide a robust, fast, and low-cost tool for the evaluation of nanoparticle toxicity.

Predicting the cytotoxicity of nanomaterials through explainable, extreme gradient boosting

Nanoparticles (NPs) are a wide class of materials currently used in several industrial and biomedical applications. Due to their small size (1-100 nm), NPs can easily enter the human body, inducing tissue damage. NP toxicity depends on physical and chemical NP properties (e.g., size, charge and surface area) in ways and magnitudes that are still unknown. We assess the average as well as the individual importance of NP atomic descriptors, along with chemical properties and experimental conditions, in determining cytotoxicity endpoints for several nanomaterials. We employ a multicenter cytotoxicity nanomaterial database (12 different materials with first and second dimensions ranging between 2.70 and 81.2 nm and between 4.10 and 4048 nm, respectively). We develop a regressor model based on extreme gradient boosting with hyperparameter optimization. We employ Shapley additive explanations to obtain good cytotoxicity prediction performance. Model performances are quantified as statistically significant Spearman correlations between the true and predicted values, ranging from 0.5 to 0.7. Our results show that i) size in situ and surface areas larger than 200 nm and 50 m2/g, respectively, ii) primary particles smaller than 20 nm; iii) irregular (i.e., not spherical) shapes and iv) positive Z-potentials contribute the most to the prediction of NP cytotoxicity, especially if lactate dehydrogenase (LDH) assays are employed for short experimental times. These results were moderately stable across toxicity endpoints, although some degree of variability emerged across dose quantification methods, confirming the complexity of nano-bio interactions and the need for large, systematic experimental characterization to reach a safer-by-design approach.

Representing and describing nanomaterials in predictive nanoinformatics

Engineered nanomaterials (ENMs) enable new and enhanced products and devices in which matter can be controlled at a near-atomic scale (in the range of 1 to 100 nm). However, the unique nanoscale properties that make ENMs attractive may result in as yet poorly known risks to human health and the environment. Thus, new ENMs should be designed in line with the idea of safe-and-sustainable-by-design (SSbD). The biological activity of ENMs is closely related to their physicochemical characteristics, changes in these characteristics may therefore cause changes in the ENMs activity. In this sense, a set of physicochemical characteristics (for example, chemical composition, crystal structure, size, shape, surface structure) creates a unique 'representation' of a given ENM. The usability of these characteristics or nanomaterial descriptors (nanodescriptors) in nanoinformatics methods such as quantitative structure-activity/property relationship (QSAR/QSPR) models, provides exciting opportunities to optimize ENMs at the design stage by improving their functionality and minimizing unforeseen health/environmental hazards. A computational screening of possible versions of novel ENMs would return optimal nanostructures and manage ('design out') hazardous features at the earliest possible manufacturing step. Safe adoption of ENMs on a vast scale will depend on the successful integration of the entire bulk of nanodescriptors extracted experimentally with data from theoretical and computational models. This Review discusses directions for developing appropriate nanomaterial representations and related nanodescriptors to enhance the reliability of computational modelling utilized in designing safer and more sustainable ENMs.

European Registry of Materials: global, unique identifiers for (undisclosed) nanomaterials

Management of nanomaterials and nanosafety data needs to operate under the FAIR (findability, accessibility, interoperability, and reusability) principles and this requires a unique, global identifier for each nanomaterial. Existing identifiers may not always be applicable or sufficient to definitively identify the specific nanomaterial used in a particular study, resulting in the use of textual descriptions in research project communications and reporting. To ensure that internal project documentation can later be linked to publicly released data and knowledge for the specific nanomaterials, or even to specific batches and variants of nanomaterials utilised in that project, a new identifier is proposed: the European Registry of Materials Identifier. We here describe the background to this new identifier, including FAIR interoperability as defined by FAIRSharing, identifiers.org, Bioregistry, and the CHEMINF ontology, and show how it complements other identifiers such as CAS numbers and the ongoing efforts to extend the InChI identifier to cover nanomaterials. We provide examples of its use in various H2020-funded nanosafety projects.

Where Is Nano Today and Where Is It Headed? A Review of Nanomedicine and the Dilemma of Nanotoxicology

Worldwide nanotechnology development and application have fueled many scientific advances, but technophilic expectations and technophobic demands must be counterbalanced in parallel. Some of the burning issues today are the following: (1) Where is nano today? (2) How good are the communication and investment networks between academia/research and governments? (3) Is there any spotlight application for nanotechnology? Nanomedicine is a particular arm of nanotechnology within the healthcare landscape, focused on diagnosis, treatment, and monitoring of emerging (such as coronavirus disease 2019, COVID-19) and contemporary (including diabetes, cardiovascular diseases, neurodegenerative disorders, and cancer) diseases. However, it may only represent the bright side of the coin. In fact, in the recent past, the concept of nanotoxicology has emerged to address the dark shadows of nanomedicine. The nanomedicine field requires more nanotoxicological studies to identify undesirable effects and guarantee safety. Here, we provide an overall perspective on nanomedicine and nanotoxicology as central pieces of the giant puzzle of nanotechnology. First, the impact of nanotechnology on education and research is highlighted, followed by market trends and scientific output tendencies. In the next section, the nanomedicine and nanotoxicology dilemma is addressed through the interplay of in silico, in vitro, and in vivo models with the support of omics and microfluidic approaches. Lastly, a reflection on the regulatory issues and clinical trials is provided. Finally, some conclusions and future perspectives are proposed for a clearer and safer translation of nanomedicines from the bench to the bedside.

Machine Learning Study of Metabolic Networks vs ChEMBL Data of Antibacterial Compounds

Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.

Characterization of ENM Dynamic Dose-Dependent MOA in Lung with Respect to Immune Cells Infiltration

The molecular effects of exposures to engineered nanomaterials (ENMs) are still largely unknown. In classical inhalation toxicology, cell composition of bronchoalveolar lavage (BAL) is a toxicity indicator at the lung tissue level that can aid in interpreting pulmonary histological changes. Toxicogenomic approaches help characterize the mechanism of action (MOA) of ENMs by investigating the differentially expressed genes (DEG). However, dissecting which molecular mechanisms and events are directly induced by the exposure is not straightforward. It is now generally accepted that direct effects follow a monotonic dose-dependent pattern. Here, we applied an integrated modeling approach to study the MOA of four ENMs by retrieving the DEGs that also show a dynamic dose-dependent profile (dddtMOA). We further combined the information of the dddtMOA with the dose dependency of four immune cell populations derived from BAL counts. The dddtMOA analysis highlighted the specific adaptation pattern to each ENM. Furthermore, it revealed the distinct effect of the ENM physicochemical properties on the induced immune response. Finally, we report three genes dose-dependent in all the exposures and correlated with immune deregulation in the lung. The characterization of dddtMOA for ENM exposures, both for apical endpoints and molecular responses, can further promote toxicogenomic approaches in a regulatory context.

AOP173 key event associated pathway predictor - online application for the prediction of benchmark dose lower bound (BMDLs) of a transcriptomic pathway involved in MWCNTs-induced lung fibrosis

Nano-QSAR model allows for prediction of the toxicity of materials that have not been experimentally tested before by linking the nano-related structural properties with the biological responses induced by nanomaterials. Prediction of adverse effects caused by substances without having to perform time- and cost-consuming experiments makes QSAR models promising tools for supporting risk assessment. However, very often, newly developed nano-QSAR models are not used in practice due to the complexity of their algorithms, the necessity to have experience in chemoinformatics, and their poor accessibility. In this perspective, the aim of this paper is to encourage developers of the QSAR models to take the effort to prepare user-friendly applications based on predictive models. This would make the developed models accessible to a wider community, and, in effect, promote their further application by regulators and decision-makers. Here, we describe a web-based application that enables to predict the transcriptomic pathway-level response perturbated in the lungs of mice exposed to multiwalled carbon nanotubes. The developed application is freely available at http://aop173-event1.nanoqsar-aop.com/apps/aop_app. It requires only two types of input information related to analyzed nanotubes (their length and diameter) to assess the doses that initiate the inflammation process that may lead to lung fibrosis.

Machine Learning Models for Predicting Cytotoxicity of Nanomaterials

The wide application of nanomaterials in consumer and medical products has raised concerns about their potential adverse effects on human health. Thus, more and more biological assessments regarding the toxicity of nanomaterials have been performed. However, the different ways the evaluations were performed, such as the utilized assays, cell lines, and the differences of the produced nanoparticles, make it difficult for scientists to analyze and effectively compare toxicities of nanomaterials. Fortunately, machine learning has emerged as a powerful tool for the prediction of nanotoxicity based on the available data. Among different types of toxicity assessments, nanomaterial cytotoxicity was the focus here because of the high sensitivity of cytotoxicity assessment to different treatments without the need for complicated and time-consuming procedures. In this review, we summarized recent studies that focused on the development of machine learning models for prediction of cytotoxicity of nanomaterials. The goal was to provide insight into predicting potential nanomaterial toxicity and promoting the development of safe nanomaterials.

Health and environmental safety of nanomaterials: O Data, Where Art Thou?

Nanotechnology keeps drawing attention due to the great tunable properties of nanomaterials in comparison to their bulk conventional materials. The growth of nanotechnology in combination with the digitization era has led to an increased need of safety related data. In addition to safety, new data-driven paradigms on safe and sustainable by design materials are stressing the necessity of data even more. Data is a fundamental asset to the scientific community in studying and analysing the entire life-cycle of nanomaterials. Unfortunately, data exist in a scattered fashion, in different sources and formats. To our knowledge, there is no study focusing on aspects of actual data-structure knowledge that exists in literature and databases. The purpose of this review research is to transparently and comprehensively, display to the nanoscience community the datasets readily available for machine learning purposes making it convenient and more efficient for the next users such as modellers or data curators to retrieve information. We systematically recorded the features and descriptors available in the datasets and provide synopsised information on their ranges, forms and metrics in the supplementary material.

Using the Isalos platform to develop a (Q)SAR model that predicts metal oxide toxicity utilizing facet-based electronic, image analysis-based, and periodic table derived properties as descriptors

Engineered nanoparticles (NPs) are being studied for their potential to harm humans and the environment. Biological activity, toxicity, physicochemical properties, fate, and transport of NPs must all be evaluated and/or predicted. In this work, we explored the influence of metal oxide nanoparticle facets on their toxicity towards bronchial epithelial (BEAS-2B), Murine myeloid (RAW 264.7), and E. coli cell lines. To estimate the toxicity of metal oxide nanoparticles grown to a low facet index, a quantitative structure–activity relationship ((Q)SAR) approach was used. The novel model employs theoretical (density functional theory calculations) and experimental studies (transmission electron microscopy images from which several particle descriptors are extracted and toxicity data extracted from the literature) to investigate the properties of faceted metal oxides, which are then utilized to construct a toxicity model. The classification mode of the k-nearest neighbour algorithm (EnaloskNN, Enalos Chem/Nanoinformatics) was used to create the presented model for metal oxide cytotoxicity. Four descriptors were identified as significant: core size, chemical potential, enthalpy of formation, and electronegativity count of metal oxides. The relationship between these descriptors and metal oxide facets is discussed to provide insights into the relative toxicities of the nanoparticle. The model and the underpinning dataset are freely available on the NanoSolveIT project cloud platform and the NanoPharos database, respectively.

Methods, models, mechanisms and metadata: Introducing the Nanotoxicology collection at F1000Research

Nanotoxicology is a relatively new field of research concerning the study and application of nanomaterials to evaluate the potential for harmful effects in parallel with the development of applications. Nanotoxicology as a field spans materials synthesis and characterisation, assessment of fate and behaviour, exposure science, toxicology / ecotoxicology, molecular biology and toxicogenomics, epidemiology, safe and sustainable by design approaches, and chemoinformatics and nanoinformatics, thus requiring scientists to work collaboratively, often outside their core expertise area. This interdisciplinarity can lead to challenges in terms of interpretation and reporting, and calls for a platform for sharing of best-practice in nanotoxicology research. The F1000Research Nanotoxicology collection, introduced via this editorial, will provide a place to share accumulated best practice, via original research reports including no-effects studies, protocols and methods papers, software reports and living systematic reviews, which can be updated as new knowledge emerges or as the domain of applicability of the method, model or software is expanded. This editorial introduces the Nanotoxicology Collection in F1000Research. The aim of the collection is to provide an open access platform for nanotoxicology researchers, to support an improved culture of data sharing and documentation of evolving protocols, biological and computational models, software tools and datasets, that can be applied and built upon to develop predictive models and move towards in silico nanotoxicology and nanoinformatics. Submissions will be assessed for fit to the collection and subjected to the F1000Research open peer review process.

Ecotoxicological read-across models for predicting acute toxicity of freshly dispersed versus medium-aged NMs to Daphnia magna

Nanoinformatics models to predict the toxicity/ecotoxicity of nanomaterials (NMs) are urgently needed to support commercialization of nanotechnologies and allow grouping of NMs based on their physico-chemical and/or (eco)toxicological properties, to facilitate read-across of knowledge from data-rich NMs to data-poor ones. Here we present the first ecotoxicological read-across models for predicting NMs ecotoxicity, which were developed in accordance with ECHA's recommended strategy for grouping of NMs as a means to explore in silico the effects of a panel of freshly dispersed versus environmentally aged (in various media) Ag and TiO₂ NMs on the freshwater zooplankton Daphnia magna, a keystone species used in regulatory testing. The dataset used to develop the models consisted of dose-response data from 11 NMs (5 TiO₂ NMs of identical cores with different coatings, and 6 Ag NMs with different capping agents/coatings) each dispersed in three different media (a high hardness medium (HH Combo) and two representative river waters containing different amounts of natural organic matter (NOM) and having different ionic strengths), generated in accordance with the OECD 202 immobilization test. The experimental hypotheses being tested were (1) that the presence of NOM in the medium would reduce the toxicity of the NMs by forming an ecological corona, and (2) that environmental ageing of NMs reduces their toxicity compared to the freshly dispersed NMs irrespective of the medium composition (salt only or NOM-containing). As per the ECHA guidance, the NMs were grouped into two categories - freshly dispersed and 2-year-aged and explored in silico to identify the most important features driving the toxicity in each group. The final predictive models have been validated according to the OECD criteria and a QSAR model report form (QMRF) report included in the supplementary information to support adoption of the models for regulatory purposes.

Identifying diverse metal oxide nanomaterials with lethal effects on embryonic zebrafish using machine learning

Manufacturers of nanomaterial-enabled products need models of endpoints that are relevant to human safety to support the "safe by design" paradigm and avoid late-stage attrition. Increasingly, embryonic zebrafish (Danio Rerio) are recognised as a key human safety relevant in vivo test system. Hence, machine learning models were developed for identifying metal oxide nanomaterials causing lethality to embryonic zebrafish up to 24 hours post-fertilisation, or excess lethality in the period of 24-120 hours post-fertilisation, at concentrations of 250 ppm or less. Models were developed using data from the Nanomaterial Biological-Interactions Knowledgebase for a dataset of 44 diverse, coated and uncoated metal or, in one case, metalloid oxide nanomaterials. Different modelling approaches were evaluated using nested cross-validation on this dataset. Models were initially developed for both lethality endpoints using multiple descriptors representing the composition of the core, shell and surface functional groups, as well as particle characteristics. However, interestingly, the 24 hours post-fertilisation data were found to be harder to predict, which could reflect different exposure routes. Hence, subsequent analysis focused on the prediction of excess lethality at 120 hours-post fertilisation. The use of two data augmentation approaches, applied for the first time in nano-QSAR research, was explored, yet both failed to boost predictive performance. Interestingly, it was found that comparable results to those originally obtained using multiple descriptors could be obtained using a model based upon a single, simple descriptor: the Pauling electronegativity of the metal atom. Since it is widely recognised that a variety of intrinsic and extrinsic nanomaterial characteristics contribute to their toxicological effects, this is a surprising finding. This may partly reflect the need to investigate more sophisticated descriptors in future studies. Future studies are also required to examine how robust these modelling results are on truly external data, which were not used to select the single descriptor model. This will require further laboratory work to generate comparable data to those studied herein.

Machine learning and materials modelling interpretation of in vivo toxicological response to TiO2 nanoparticles library (UV and non-UV exposure)

Assessing the risks of nanomaterials/nanoparticles (NMs/NPs) under various environmental conditions requires a more systematic approach, including the comparison of effects across many NMs with identified different but related characters/descriptors. Hence, there is an urgent need to provide coherent (eco)toxicological datasets containing comprehensive toxicity information relating to a diverse spectra of NPs characters. These datasets are test benches for developing holistic methodologies with broader applicability. In the present study we assessed the effects of a custom design Fe-doped TiO₂ NPs library, using the soil invertebrate Enchytraeus crypticus (Oligochaeta), via a 5-day pulse via aqueous exposure followed by a 21-days recovery period in soil (survival, reproduction assessment). Obviously, when testing TiO₂, realistic conditions should include UV exposure. The 11 Fe-TiO₂ library contains NPs of size range between 5-27 nm with varying %Fe (enabling the photoactivation of TiO₂ at energy wavelengths in the visible-light range). The NPs were each described by 122 descriptors, being a mixture of measured and atomistic model descriptors. The data were explored using single and univariate statistical methods, combined with machine learning and multiscale modelling techniques. An iterative pruning process was adopted for identifying automatically the most significant descriptors. TiO₂ NPs toxicity decreased when combined with UV. Notably, the short-term water exposure induced lasting biological responses even after longer-term recovery in clean exposure. The correspondence with Fe-content correlated with the band-gap hence the reduction of UV oxidative stress. The inclusion of both measured and modelled materials data benefitted the explanation of the results, when combined with machine learning.

Predicting and investigating cytotoxicity of nanoparticles by translucent machine learning

Safety concerns of engineered nanoparticles (ENPs) hamper their applications and commercialization in many potential fields. Machine learning has been proved as a great tool to understand the complex ENP-organism-environment relationship. However, good-performance machine learning models usually exist as black boxes, which may be difficult to build trust and whose ways of expressing knowledge rarely directly map to forms familiar to scientists. Here, we present an approach for uncovering causal structure in nanotoxicity datasets by mutual-validated and model-agnostic interpretation methods. Model predictions can be explained from feature importance, feature effects, and feature interactions. The utility of this approach is demonstrated through two case studies, the cytotoxicity of cadmium-containing quantum dots and metal oxide nanoparticles. Further, these case studies indicate the efficacy and impacts at two scales: (i) model interpretation, where the most relevant features for correlating cytotoxicity are identified and their influence on model predictions and interactions with other features are then explained, and (ii) model validation, where the difference among interpretation results of different methods (or the difference between interpretation results and well-known toxicity mechanisms) may reflect some inherent problems in the used dataset (or the developed models). Our approach of integrating machine learning models and interpretation methods provides a roadmap for predicting the toxicity of ENPs in a translucent way.

Nanotechnology and artificial intelligence to enable sustainable and precision agriculture

Climate change, increasing populations, competing demands on land for production of biofuels and declining soil quality are challenging global food security. Finding sustainable solutions requires bold new approaches and integration of knowledge from diverse fields, such as materials science and informatics. The convergence of precision agriculture, in which farmers respond in real time to changes in crop growth with nanotechnology and artificial intelligence, offers exciting opportunities for sustainable food production. Coupling existing models for nutrient cycling and crop productivity with nanoinformatics approaches to optimize targeting, uptake, delivery, nutrient capture and long-term impacts on soil microbial communities will enable design of nanoscale agrochemicals that combine optimal safety and functionality profiles.

Recent Advances in Immunosafety and Nanoinformatics of Two-Dimensional Materials Applied to Nano-imaging

Two-dimensional (2D) materials have emerged as an important class of nanomaterials for technological innovation due to their remarkable physicochemical properties, including sheet-like morphology and minimal thickness, high surface area, tuneable chemical composition, and surface functionalization. These materials are being proposed for new applications in energy, health, and the environment; these are all strategic society sectors toward sustainable development. Specifically, 2D materials for nano-imaging have shown exciting opportunities in in vitro and in vivo models, providing novel molecular imaging techniques such as computed tomography, magnetic resonance imaging, fluorescence and luminescence optical imaging and others. Therefore, given the growing interest in 2D materials, it is mandatory to evaluate their impact on the immune system in a broader sense, because it is responsible for detecting and eliminating foreign agents in living organisms. This mini-review presents an overview on the frontier of research involving 2D materials applications, nano-imaging and their immunosafety aspects. Finally, we highlight the importance of nanoinformatics approaches and computational modeling for a deeper understanding of the links between nanomaterial physicochemical properties and biological responses (immunotoxicity/biocompatibility) towards enabling immunosafety-by-design 2D materials.

Computational enrichment of physicochemical data for the development of a ζ-potential read-across predictive model with Isalos Analytics Platform

The physicochemical characterisation data from a library of 69 engineered nanomaterials (ENMs) has been exploited in silico following enrichment with a set of molecular descriptors that can be easily acquired or calculated using atomic periodicity and other fundamental atomic parameters. Based on the extended set of twenty descriptors, a robust and validated nanoinformatics model has been proposed to predict the ENM ζ-potential. The five critical parameters selected as the most significant for the model development included the ENM size and coating as well as three molecular descriptors, metal ionic radius (r_ion), the sum of metal electronegativity divided by the number of oxygen atoms present in a particular metal oxide (Σχ/n_O) and the absolute electronegativity (χ_abs), each of which is thoroughly discussed to interpret their influence on ζ-potential values. The model was developed using the Isalos Analytics Platform and is available to the community as a web service through the Horizon 2020 (H2020) NanoCommons Transnational Access services and the H2020 NanoSoveIT Integrated Approach to Testing and Assessment (IATA).

Can an InChI for Nano Address the Need for a Simplified Representation of Complex Nanomaterials across Experimental and Nanoinformatics Studies?

Chemoinformatics has developed efficient ways of representing chemical structures for small molecules as simple text strings, simplified molecular-input line-entry system (SMILES) and the IUPAC International Chemical Identifier (InChI), which are machine-readable. In particular, InChIs have been extended to encode formalized representations of mixtures and reactions, and work is ongoing to represent polymers and other macromolecules in this way. The next frontier is encoding the multi-component structures of nanomaterials (NMs) in a machine-readable format to enable linking of datasets for nanoinformatics and regulatory applications. A workshop organized by the H2020 research infrastructure NanoCommons and the nanoinformatics project NanoSolveIT analyzed issues involved in developing an InChI for NMs (NInChI). The layers needed to capture NM structures include but are not limited to: core composition (possibly multi-layered); surface topography; surface coatings or functionalization; doping with other chemicals; and representation of impurities. NM distributions (size, shape, composition, surface properties, etc.), types of chemical linkages connecting surface functionalization and coating molecules to the core, and various crystallographic forms exhibited by NMs also need to be considered. Six case studies were conducted to elucidate requirements for unambiguous description of NMs. The suggested NInChI layers are intended to stimulate further analysis that will lead to the first version of a "nano" extension to the InChI standard.

Metadata Stewardship in Nanosafety Research: Community-Driven Organisation of Metadata Schemas to Support FAIR Nanoscience Data

The emergence of nanoinformatics as a key component of nanotechnology and nanosafety assessment for the prediction of engineered nanomaterials (NMs) properties, interactions, and hazards, and for grouping and read-across to reduce reliance on animal testing, has put the spotlight firmly on the need for access to high-quality, curated datasets. To date, the focus has been around what constitutes data quality and completeness, on the development of minimum reporting standards, and on the FAIR (findable, accessible, interoperable, and reusable) data principles. However, moving from the theoretical realm to practical implementation requires human intervention, which will be facilitated by the definition of clear roles and responsibilities across the complete data lifecycle and a deeper appreciation of what metadata is, and how to capture and index it. Here, we demonstrate, using specific worked case studies, how to organise the nano-community efforts to define metadata schemas, by organising the data management cycle as a joint effort of all players (data creators, analysts, curators, managers, and customers) supervised by the newly defined role of data shepherd. We propose that once researchers understand their tasks and responsibilities, they will naturally apply the available tools. Two case studies are presented (modelling of particle agglomeration for dose metrics, and consensus for NM dissolution), along with a survey of the currently implemented metadata schema in existing nanosafety databases. We conclude by offering recommendations on the steps forward and the needed workflows for metadata capture to ensure FAIR nanosafety data.