Role of Artificial Intelligence and Machine Learning in Nanosafety

Abstract

Robotics and automation provide potentially paradigm shifting improvements in the way materials are synthesized and characterized, generating large, complex data sets that are ideal for modeling and analysis by modern machine learning (ML) methods. Nanomaterials have not yet fully captured the benefits of automation, so lag behind in the application of ML methods of data analysis. Here, some key developments in, and roadblocks to the application of ML methods are reviewed to model and predict potentially adverse biological and environmental effects of nanomaterials. This work focuses on the diverse ways a range of ML algorithms are applied to understand and predict nanomaterials properties, provides examples of the application of traditional ML and deep learning methods to nanosafety, and provides context and future perspectives on developments that are likely to occur, or need to occur in the near future that allow artificial intelligence to make a deeper contribution to nanosafety.

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

“…In the past decade, a variety of data driven computational approaches, such as Quantitative Structure-Activity Relationship (QSAR) models and read-across approaches that use diverse machine learning methods, have been used to predict NM-related toxicity [ 10 , 148 ]. The goal of these methods is to map the material description and intrinsic/extrinsic physicochemical properties to the biological outcomes to identify NM properties of concern, and facilitate design of NM that avoid, reduce or modulate these properties [ 150 , 151 ].…”

“…This is particularly important for virtual NM not yet synthesized, where prediction of their properties is important. An overview of various computational models for NMs is given in recent reviews [ 10 , 150 , 151 ].…”

“…When combined with development of physicochemical characterization methods, exposure models, and life cycle assessment, this evolution provides a solid foundation for SbD strategies and nanomaterials (NM) risk management that supports sustainable innovation [ 8 , 9 ]. However, a commonly cited roadblock is lack of curated, organized and harmonized datasets for NMs toxicity [ 10 ], like those available for small molecules on UniChem, ChEMBL and other platforms.…”

RNA m6A Modification Alteration by Black Phosphorus Quantum Dots Regulates Cell Ferroptosis: Implications for Nanotoxicological Assessment

“…[ 7 ] Although numerous studies have been conducted for nanosafety evaluation using in silico, in vitro, and in vivo methods, a widely accepted assessment framework for ENMs remains to be built. [ 8–10 ]…”

Predicting Cytotoxicity of Metal Oxide Nanoparticles Using Isalos Analytics Platform

“…According to a study by Törnqvist et al (2014), data from 36 relevant projects demonstrated major (i.e., 53%) reductions in the use of animals in pharmaceutical development [ 27 ]. Taking into account the cost and working hours associated with in vivo and in vitro experiments and that traditional “wet-lab” toxicology cannot keep up with diversity and increasing abundance of engineered NPs, computational modelling has the potential to act as a high-throughput alternative [ 28 , 29 ] and is becoming increasingly accepted in regulatory testing as model validation and documentation improves.…”