Developing Integrated Approaches for Testing and Assessment (IATAs) in order to support nanomaterial safety

Due to the unique characteristics of nanomaterials (NM) there has been an increase in their use in nanomedicines and innovative medical devices (MD). Although large numbers of NMs have now been developed, comprehensive safety investigations are still lacking. Current gaps in understanding the potential mechanisms of NM-induced toxicity can make it challenging to determine the safety testing necessary to support inclusion of NMs in MD applications. This article provides guidance for implementation of pre-clinical tailored safety assessment strategies with the aim to increase the translation of NMs from bench development to clinical use. Integrated Approaches to Testing and Assessment (IATAs) are a key tool in developing these strategies. IATAs follow an iterative approach to answer a defined question in a specific regulatory context to guide the gathering of relevant information for safety assessment, including existing experimental data, integrated with in silico model predictions where available and appropriate, and/or experimental procedures and protocols for generating new data to fill gaps. This allows NM developers to work toward current guidelines and regulations, while taking NM specific considerations into account. Here, an example IATA for NMs with potential for direct blood contact was developed for the assessment of haemocompatibility. This example IATA brings together the current guidelines for NM safety assessment within a framework that can be used to guide information and data gathering for the safety assessment of intravenously injected NMs. Additionally, the decision framework underpinning this IATA has the potential to be adapted to other testing needs and regulatory contexts.

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.

Radial basis function network training using a nonsymmetric partition of the input space and particle swarm optimization

This paper presents a novel algorithm for training radial basis function (RBF) networks, in order to produce models with increased accuracy and parsimony. The proposed methodology is based on a nonsymmetric variant of the fuzzy means (FM) algorithm, which has the ability to determine the number and locations of the hidden-node RBF centers, whereas the synaptic weights are calculated using linear regression. Taking advantage of the short computational times required by the FM algorithm, we wrap a particle swarm optimization (PSO) based engine around it, designed to optimize the fuzzy partition. The result is an integrated framework for fully determining all the parameters of an RBF network. The proposed approach is evaluated through its application on 12 real-world and synthetic benchmark datasets and is also compared with other neural network training techniques. The results show that the RBF network models produced by the PSO-based nonsymmetric FM algorithm outperform the models produced by the other techniques, exhibiting higher prediction accuracies in shorter computational times, accompanied by simpler network structures.