The trial on non-testing approaches for nanostructured materials and the
prediction of toxicity that may cause cell disruption is needed for the risk assessment,
to recognize, evaluate, and categorize possible risks. Another tactic for examining the
toxicologic characteristics of a nanostructure is using in silico methods that interpret
how nano-specific structures correlate to noxiousness and permit its prediction.
Nanotoxicology is the study of the toxicity of nanostructures and has been broadly
functional in medical research to predict the toxicity in numerous biotic systems.
Exploring biotic systems through in vivo and in vitro approaches is affluent and time-consuming. However, computational toxicology is a multi-discipline ground that
operates In silico strategies and algorithms to inspect the toxicology of biotic systems
and also has gained attention for many years. Molecular dynamics (MD) simulations of
biomolecules such as proteins and deoxyribonucleic acid (DNA) are prevalent for
considering connections between biotic systems and chemicals in computational
toxicology. This chapter summarizes the works predicting nanotoxicological endpoints
using (ML) machine learning models. Instead of looking for mechanistic clarifications,
the chapter plots the ways that are followed, linking biotic features concerning
exposure to nanostructure materials, their physicochemical features, and the commonly
predicted conclusions. The outcomes and conclusions obtained from the research, and
review papers from indexing databases like SCOPUS, Web of Science, and PubMed
were studied and included in the chapter. The chapter maps current models developed
precisely for nanostructures to recognize the threat potential upon precise exposure
circumstances. The authors have provided computational nano-toxicological effects
with the collective vision of applied machine learning tools.
Keywords: Biomedical, Computational nanotoxicology, In silico approaches, Molecular dynamics, Machine learning, Nanostructures.
