Perspectives from the NanoSafety Modelling Cluster on the validation criteria for (Q)SAR models used in nanotechnology

Building species trait-specific nano-QSARs: Model stacking, navigating model uncertainties and limitations, and the effect of dataset size

A strong need exists for broadly applicable nano-QSARs, capable of predicting toxicological outcomes towards untested species and nanomaterials, under different environmental conditions. Existing nano-QSARs are generally limited to only a few species but the inclusion of species characteristics into models can aid in making them applicable to multiple species, even when toxicity data is not available for biological species. Species traits were used to create classification- and regression machine learning models to predict acute toxicity towards aquatic species for metallic nanomaterials. Afterwards, the individual classification- and regression models were stacked into a meta-model to improve performance. Additionally, the uncertainty and limitations of the models were assessed in detail (beyond the OECD principles) and it was investigated whether models would benefit from the addition of more data. Results showed a significant improvement in model performance following model stacking. Investigation of model uncertainties and limitations highlighted the discrepancy between the applicability domain and accuracy of predictions. Data points outside of the assessed chemical space did not have higher likelihoods of generating inadequate predictions or vice versa. It is therefore concluded that the applicability domain does not give complete insight into the uncertainty of predictions and instead the generation of prediction intervals can help in this regard. Furthermore, results indicated that an increase of the dataset size did not improve model performance. This implies that larger dataset sizes may not necessarily improve model performance while in turn also meaning that large datasets are not necessarily required for prediction of acute toxicity with nano-QSARs.

Data-Driven Quantitative Intrinsic Hazard Criteria for Nanoproduct Development in a Safe-by-Design Paradigm: A Case Study of Silver Nanoforms

The current European (EU) policies, that is, the Green Deal, envisage safe and sustainable practices for chemicals, which include nanoforms (NFs), at the earliest stages of innovation. A theoretically safe and sustainable by design (SSbD) framework has been established from EU collaborative efforts toward the definition of quantitative criteria in each SSbD dimension, namely, the human and environmental safety dimension and the environmental, social, and economic sustainability dimensions. In this study, we target the safety dimension, and we demonstrate the journey toward quantitative intrinsic hazard criteria derived from findable, accessible, interoperable, and reusable data. Data were curated and merged for the development of new approach methodologies, that is, quantitative structure-activity relationship models based on regression and classification machine learning algorithms, with the intent to predict a hazard class. The models utilize system (i.e., hydrodynamic size and polydispersity index) and non-system (i.e., elemental composition and core size)-dependent nanoscale features in combination with biological in vitro attributes and experimental conditions for various silver NFs, functional antimicrobial textiles, and cosmetics applications. In a second step, interpretable rules (criteria) followed by a certainty factor were obtained by exploiting a Bayesian network structure crafted by expert reasoning. The probabilistic model shows a predictive capability of ≈78% (average accuracy across all hazard classes). In this work, we show how we shifted from the conceptualization of the SSbD framework toward the realistic implementation with pragmatic instances. This study reveals (i) quantitative intrinsic hazard criteria to be considered in the safety aspects during synthesis stage, (ii) the challenges within, and (iii) the future directions for the generation and distillation of such criteria that can feed SSbD paradigms. Specifically, the criteria can guide material engineers to synthesize NFs that are inherently safer from alternative nanoformulations, at the earliest stages of innovation, while the models enable a fast and cost-efficient in silico toxicological screening of previously synthesized and hypothetical scenarios of yet-to-be synthesized NFs.

Core, Coating, or Corona? The Importance of Considering Protein Coronas in nano-QSPR Modeling of Zeta Potential

To control stability in a biological medium, several factors affecting the zeta potential (ζ) of nanoparticles (NPs) must be considered, including complex interactions between the nanostructure and the composition of the protein corona (PC). Effective in silico methods (based on machine learning and quantitative structure-property relationship (QSPR) models) could help predict and characterize the relationship between the physicochemical properties of NP and the formation of PC and biological outcomes in the medium at an early stage of the experiment. However, the models currently developed are limited to simple descriptors that do not represent the complex interactions between the core, the coating, and their PC fingerprints. To be useful, the models developed should be described as a function of both the structural properties determined by the core and coating of the NPs and the biological medium determined by the formation of the protein corona. We have developed a set of complex descriptors that describe the quantitative relationship between the value of the zeta potential (ζ), core, the coating of NPs, and their PC fingerprints (the so-called nano-QSPR model). The nano-QSPR model was developed based on a genetic algorithm using a partial least-squares regression method (GA-PLS), which is characterized by high external predictive power (Q²_EXT = 0.89). The GA-PLS model was developed using descriptors that describe (i) the core structure (determined by 7 different types of polymer-based NMs in the range of 20 different sizes), (ii) the coating structure with 7 different functional groups, and (iii) 80 different types of protein compositions adsorbed on the surface of the NPs. The presented study answers the question of how complex interactions between the corona and NP determine the zeta potential (ζ) of NP in a given medium. Moreover, our current study is a proof-of-concept that the zeta potential of NPs modeled on the original structure depends not only on the NPs themselves but also on the structure and properties determined by the NP core and coating, as well as the biological medium determined by the formation of the protein corona. On the basis of these results, our studies will be useful in determining the stability and mechanism of cell uptake, toxicity, and ability to predict the zeta potential of compounds not yet tested.

Exploring the potential of in silico machine learning tools for the prediction of acute Daphnia magna nanotoxicity

Engineered nanomaterials (ENMs) are ubiquitous nowadays, finding their application in different fields of technology and various consumer products. Virtually any chemical can be manipulated at the nano-scale to display unique characteristics which makes them appealing over larger sized materials. As the production and development of ENMs have increased considerably over time, so too have concerns regarding their adverse effects and environmental impacts. It is unfeasible to assess the risks associated with every single ENM through in vivo or in vitro experiments. As an alternative, in silico methods can be employed to evaluate ENMs. To perform such an evaluation, we collected data from databases and literature to create classification models based on machine learning algorithms in accordance with the principles laid out by the OECD for the creation of QSARs. The aim was to investigate the performance of various machine learning algorithms towards predicting a well-defined in vivo toxicity endpoint (Daphnia magna immobilization) and also to identify which features are important drivers of D. magna in vivo nanotoxicity. Results indicated highly comparable model performance between all algorithms and predictive performance exceeding ∼0.7 for all evaluated metrics (e.g. accuracy, sensitivity, specificity, balanced accuracy, Matthews correlation coefficient, area under the receiver operator characteristic curve). The random forest, artificial neural network, and k-nearest neighbor models displayed the best performance but this was only marginally better compared to the other models. Furthermore, the variable importance analysis indicated that molecular descriptors and physicochemical properties were generally important within most models, while features related to the exposure conditions produced slightly conflicting results. Lastly, results also indicate that reliable and robust machine learning models can be generated for in vivo endpoints with smaller datasets.

Nano-QSAR modeling for predicting the cytotoxicity of metallic and metal oxide nanoparticles: A review

Given the rapid development of nanotechnology, it is crucial to understand the effects of nanoparticles on living organisms. However, it is laborious to perform toxicological tests on a case-by-case basis. Quantitative structure-activity relationship (QSAR) is an effective computational technique because it saves time, costs, and animal sacrifice. Therefore, this review presents general procedures for the construction and application of nano-QSAR models of metal-based and metal-oxide nanoparticles (MBNPs and MONPs). We also provide an overview of available databases and common algorithms. The molecular descriptors and their roles in the toxicological interpretation of MBNPs and MONPs are systematically reviewed and the future of nano-QSAR is discussed. Finally, we address the growing demand for novel nano-specific descriptors, new computational strategies to address the data shortage, in situ data for regulatory concerns, a better understanding of the physicochemical properties of NPs with bioactivity, and, most importantly, the design of nano-QSAR for real-life environmental predictions rather than laboratory simulations.

RNA m6A Alterations Induced by Biomineralization Nanoparticles: A Proof-of-Concept Study of Epitranscriptomics for Nanotoxicity Evaluation

Although various strategies have been included in nanotoxicity evaluation, epitranscriptomics has rarely been integrated into this field. In this proof-of-concept study, N6-methyladenosine (m⁶A) changes of mRNA in HEK293T cells induced by three bovine serum albumin (BSA)-templated Au, CuS and Gd₂O₃ nanoparticles are systematically explored, and their possible biological mechanisms are preliminarily investigated. It has been found that all the three BSA-templated nanoparticles can reduce m⁶A levels, and the genes with reduced m⁶A are enriched for TGF-beta signaling, which is critical for cell proliferation, differentiation and apoptosis. Further results indicate that abnormal aggregation of m⁶A-related enzymes at least partly account for the nanoparticle-induced epitranscriptomic changes. These findings demonstrate that epitranscriptomics analysis can provide an unprecedented landscape of the biological effect induced by nanomaterials, which should be involved in the nanotoxicity evaluation to promote the potential clinical translation of nanomaterials.

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.

FAIRification of nanosafety data to improve applicability of (Q)SAR approaches: A case study on in vitro Comet assay genotoxicity data

(Quantitative) structure-activity relationship ([Q]SAR) methodologies are widely applied to predict the (eco)toxicological effects of chemicals, and their use is envisaged in different regulatory frameworks for filling data gaps of untested substances. However, their application to the risk assessment of nanomaterials is still limited, also due to the scarcity of large and curated experimental datasets. Despite a great amount of nanosafety data having been produced over the last decade in international collaborative initiatives, their interpretation, integration and reuse has been hampered by several obstacles, such as poorly described (meta)data, non-standard terminology, lack of harmonized reporting formats and criteria. Recently, the FAIR (Findable, Accessible, Interoperable, and Reusable) principles have been established to guide the scientific community in good data management and stewardship. The EU H2020 Gov4Nano project, together with other international projects and initiatives, is addressing the challenge of improving nanosafety data FAIRness, for maximizing their availability, understanding, exchange and ultimately their reuse. These efforts are largely supported by the creation of a common Nanosafety Data Interface, which connects a row of project-specific databases applying the eNanoMapper data model. A wide variety of experimental data relating to characterization and effects of nanomaterials are stored in the database; however, the methods, protocols and parameters driving their generation are not fully mature. This article reports the progress of an ongoing case study in the Gov4nano project on the reuse of in vitro Comet genotoxicity data, focusing on the issues and challenges encountered in their FAIRification through the eNanoMapper data model. The case study is part of an iterative process in which the FAIRification of data supports the understanding of the phenomena underlying their generation and, ultimately, improves their reusability.

Machine learning predictions of concentration-specific aggregate hazard scores of inorganic nanomaterials in embryonic zebrafish

The possibility of employing computational approaches like nano-QSAR or nano-read-across to predict nanomaterial hazard is attractive from both a financial, and most importantly, where in vivo tests are required, ethical perspective. In the present work, we have employed advanced Machine Learning techniques, including stacked model ensembles, to create nano-QSAR tools for modeling the toxicity of metallic and metal oxide nanomaterials, both coated and uncoated and with a variety of different core compositions, tested at different dosage concentrations on embryonic zebrafish. Using both computed and experimental descriptors, we have identified a set of properties most relevant for the assessment of nanomaterial toxicity and successfully correlated these properties with the associated biological responses observed in zebrafish. Our findings suggest that for the group of metal and metal oxide nanomaterials, the core chemical composition, concentration and properties dependent upon nanomaterial surface and medium composition (such as zeta potential and agglomerate size) are significant factors influencing toxicity, albeit the ranking of different variables is sensitive to the exact analysis method and data modeled. Our generalized nano-QSAR ensemble models provide a promising framework for anticipating the toxicity potential of new nanomaterials and may contribute to the transition out of the animal testing paradigm. However, future experimental studies are required to generate comparable, similarly high quality data, using consistent protocols, for well characterized nanomaterials, as per the dataset modeled herein. This would enable the predictive power of our promising ensemble modeling approaches to be robustly assessed on large, diverse and truly external datasets.

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).

Understanding Nanoparticle Toxicity to Direct a Safe-by-Design Approach in Cancer Nanomedicine

Nanomedicine is a rapidly growing field that uses nanomaterials for the diagnosis, treatment and prevention of various diseases, including cancer. Various biocompatible nanoplatforms with diversified capabilities for tumor targeting, imaging, and therapy have materialized to yield individualized therapy. However, due to their unique properties brought about by their small size, safety concerns have emerged as their physicochemical properties can lead to altered pharmacokinetics, with the potential to cross biological barriers. In addition, the intrinsic toxicity of some of the inorganic materials (i.e., heavy metals) and their ability to accumulate and persist in the human body has been a challenge to their translation. Successful clinical translation of these nanoparticles is heavily dependent on their stability, circulation time, access and bioavailability to disease sites, and their safety profile. This review covers preclinical and clinical inorganic-nanoparticle based nanomaterial utilized for cancer imaging and therapeutics. A special emphasis is put on the rational design to develop non-toxic/safe inorganic nanoparticle constructs to increase their viability as translatable nanomedicine for cancer therapies.

Predicting Cytotoxicity of Metal Oxide Nanoparticles using Isalos Analytics Platform

A literature curated dataset containing 24 distinct metal oxide (MexOy) nanoparticles (NPs), including 15 physicochemical, structural and assay-related descriptors, was enriched with 62 atomistic computational descriptors and exploited to produce a robust and validated in silico model for prediction of NP cytotoxicity. The model can be used to predict the cytotoxicity (cell viability) of MexOy NPs based on the colorimetric lactate dehydrogenase (LDH) assay and the luminometric adenosine triphosphate (ATP) assay, both of which quantify irreversible cell membrane damage. Out of the 77 total descriptors used, 7 were identified as being significant for induction of cytotoxicity by MexOy NPs. These were NP core size, hydrodynamic size, assay type, exposure dose, the energy of the MexOy conduction band (EC), the coordination number of the metal atoms on the NP surface (Avg. C.N. Me atoms surface) and the average force vector surface normal component of all metal atoms (v⟂ Me atoms surface). The significance and effect of these descriptors is discussed to demonstrate their direct correlation with cytotoxicity. The produced model has been made publicly available by the Horizon 2020 (H2020) NanoSolveIT project and will be added to the project's Integrated Approach to Testing and Assessment (IATA).

Molecular Mechanisms, Characterization Methods, and Utilities of Nanoparticle Biotransformation in Nanosafety Assessments

It is a big challenge to reveal the intrinsic cause of a nanotoxic effect due to diverse branches of signaling pathways induced by engineered nanomaterials (ENMs). Biotransformation of toxic ENMs involving biochemical reactions between nanoparticles (NPs) and biological systems has recently attracted substantial attention as it is regarded as the upstream signal in nanotoxicology pathways, the molecular initiating event (MIE). Considering that different exposure routes of ENMs may lead to different interfaces for the arising of biotransformation, this work summarizes the nano-bio interfaces and dose calculation in inhalation, dermal, ingestion, and injection exposures to humans. Then, five types of biotransformation are shown, including aggregation and agglomeration, corona formation, decomposition, recrystallization, and redox reactions. Besides, the characterization methods for investigation of biotransformation as well as the safe design of ENMs to improve the sustainable development of nanotechnology are also discussed. Finally, future perspectives on the implications of biotransformation in clinical translation of nanomedicine and commercialization of nanoproducts are provided.

Nanotoxicology data for in silico tools: a literature review

The exercise of non-testing approaches in nanoparticles (NPs) hazard assessment is necessary for the risk assessment, considering cost and time efficiency, to identify, assess, and classify potential risks. One strategy for investigating the toxicological properties of a variety of NPs is by means of computational tools that decode how nano-specific features relate to toxicity and enable its prediction. This literature review records systematically the data used in published studies that predict nano (eco)-toxicological endpoints using machine learning models. Instead of seeking mechanistic interpretations this review maps the pathways followed, involving biological features in relation to NPs exposure, their physico-chemical characteristics and the most commonly predicted outcomes. The results, derived from published research of the last decade, are summarized visually, providing prior-based data mining paradigms to be readily used by the nanotoxicology community in computational studies.

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

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

Practices and Trends of Machine Learning Application in Nanotoxicology

Machine Learning (ML) techniques have been applied in the field of nanotoxicology with very encouraging results. Adverse effects of nanoforms are affected by multiple features described by theoretical descriptors, nano-specific measured properties, and experimental conditions. ML has been proven very helpful in this field in order to gain an insight into features effecting toxicity, predicting possible adverse effects as part of proactive risk analysis, and informing safe design. At this juncture, it is important to document and categorize the work that has been carried out. This study investigates and bookmarks ML methodologies used to predict nano (eco)-toxicological outcomes in nanotoxicology during the last decade. It provides a review of the sequenced steps involved in implementing an ML model, from data pre-processing, to model implementation, model validation, and applicability domain. The review gathers and presents the step-wise information on techniques and procedures of existing models that can be used readily to assemble new nanotoxicological in silico studies and accelerates the regulation of in silico tools in nanotoxicology. ML applications in nanotoxicology comprise an active and diverse collection of ongoing efforts, although it is still in their early steps toward a scientific accord, subsequent guidelines, and regulation adoption. This study is an important bookend to a decade of ML applications to nanotoxicology and serves as a useful guide to further in silico applications.

Machine learning prediction of nanoparticle in vitro toxicity: A comparative study of classifiers and ensemble-classifiers using the Copeland Index

Nano-Particles (NPs) are well established as important components across a broad range of products from cosmetics to electronics. Their utilization is increasing with their significant economic and societal potential yet to be fully realized. Inroads have been made in our understanding of the risks posed to human health and the environment by NPs but this area will require continuous research and monitoring. In recent years Machine Learning (ML) techniques have exploited large datasets and computation power to create breakthroughs in diverse fields from facial recognition to genomics. More recently, ML techniques have been applied to nanotoxicology with very encouraging results. In this study, categories of ML classifiers (rules, trees, lazy, functions and bayes) were compared using datasets from the Safe and Sustainable Nanotechnology (S2NANO) database to investigate their performance in predicting NPs in vitro toxicity. Physicochemical properties, toxicological and quantum-mechanical attributes and in vitro experimental conditions were used as input variables to predict the toxicity of NPs based on cell viability. Voting, an ensemble meta-classifier, was used to combine base models to optimize the classification prediction of toxicity. To facilitate inter-comparison, a Copeland Index was applied that ranks the classifiers according to their performance and suggested the optimal classifier. Neural Network (NN) and Random forest (RF) showed the best performance in the majority of the datasets used in this study. However, the combination of classifiers demonstrated an improved prediction resulting meta-classifier to have higher indices. This proposed Copeland Index can now be used by researchers to identify and clearly prioritize classifiers in order to achieve more accurate classification predictions for NP toxicity for a given dataset.

Multivariate modeling of engineered nanomaterial features associated with developmental toxicity

Despite the increasing prevalence of engineered nanomaterials (ENMs) in consumer products, their toxicity profiles remain to be elucidated. ENM physicochemical characteristics (PCC) are known to influence ENM behavior, however the mechanisms of these effects have not been quantified. Further confounding the question of how the PCC influence behavior is the inclusion of structural and molecular descriptors in modeling schema that minimize the effects of PCC on the toxicological endpoints. In this work, we analyze ENM physico-chemical measurements that have not previously been studied within a developmental toxicity framework using an embryonic zebrafish model. In testing a panel of diverse ENMs to build a consensus model, we found nonlinear relationships between any singular PCC and bioactivity. By using a machine learning (ML) method to characterize the information content of combinatorial PCC sets, we found that concentration, surface area, shape, and polydispersity can accurately capture the developmental toxicity profile of ENMs with consideration to whole-organism effects.

Computational models for the assessment of manufactured nanomaterials: Development of model reporting standards and mapping of the model landscape

Different types of computational models have been developed for predicting the biokinetics, environmental fate, exposure levels and toxicological effects of chemicals and manufactured nanomaterials (MNs). However, these models are not described in a consistent manner in the scientific literature, which is one of the barriers to their broader use and acceptance, especially for regulatory purposes. Quantitative structure-activity relationships (QSARs) are in silico models based on the assumption that the activity of a substance is related to its chemical structure. These models can be used to provide information on (eco)toxicological effects in hazard assessment. In an environmental risk assessment, environmental exposure models can be used to estimate the predicted environmental concentration (PEC). In addition, physiologically based kinetic (PBK) models can be used in various ways to support a human health risk assessment. In this paper, we first propose model reporting templates for systematically and transparently describing models that could potentially be used to support regulatory risk assessments of MNs, for example under the REACH regulation. The model reporting templates include (a) the adaptation of the QSAR Model Reporting Format (QMRF) to report models for MNs, and (b) the development of a model reporting template for PBK and environmental exposure models applicable to MNs. Second, we show the usefulness of these templates to report different models, resulting in an overview of the landscape of available computational models for MNs.

A nanoinformatics decision support tool for the virtual screening of gold nanoparticle cellular association using protein corona fingerprints

The increasing use of nanoparticles (NPs) in a wide range of consumer and industrial applications has necessitated significant effort to address the challenge of characterizing and quantifying the underlying nanostructure - biological response relationships to ensure that these novel materials can be exploited responsibly and safely. Such efforts demand reliable experimental data not only in terms of the biological dose-response, but also regarding the physicochemical properties of the NPs and their interaction with the biological environment. The latter has not been extensively studied, as a large surface to bind biological macromolecules is a unique feature of NPs that is not relevant for chemicals or pharmaceuticals, and thus only limited data have been reported in the literature quantifying the protein corona formed when NPs interact with a biological medium and linking this with NP cellular association/uptake. In this work we report the development of a predictive model for the assessment of the biological response (cellular association, which can include both internalized NPs and those attached to the cell surface) of surface-modified gold NPs, based on their physicochemical properties and protein corona fingerprints, utilizing a dataset of 105 unique NPs. Cellular association was chosen as the end-point for the original experimental study due to its relevance to inflammatory responses, biodistribution, and toxicity in vivo. The validated predictive model is freely available online through the Enalos Cloud Platform ( http://enalos.insilicotox.com/NanoProteinCorona/ ) to be used as part of a regulatory or NP safe-by-design decision support system. This online tool will allow the virtual screening of NPs, based on a list of the significant NP descriptors, identifying those NPs that would warrant further toxicity testing on the basis of predicted NP cellular association.