Meta-analysis of cellular toxicity for graphene via data-mining the literature and machine learning

Abstract

Background: Due to graphene is currently incorporated into various consumer product and numerous new applications, determining the relationships between physicochemical properties of graphene and their toxicity is a prominent concern for environmental and health risk analysis. Data from the literatures suggested that graphene exposure may resulted in cytotoxicity, however, the toxicity data of graphene is still insu cient to point out its side because of the complexity and heterogeneity of available data on potential risks of graphene.Methods and Results: Here, we developed a meta-analysis approach for assembling published evidence on cytotoxicity based on 792 related publications, 986 cell survival rate samples, 762 IC 50 samples, and 100 LDH release samples. In this study, among corresponding attributes, we proved that the cytotoxicity of graphene assessed in the form of cell viability, IC 50 and LDH can be primarily predicted from exposure dose and detection method, diameter and surface modi cation, detection method and organ source, respectively. Furthermore, this paper provides guidance regarding three optional data sets for above-mentioned three endpoints that are chie y related to cellular toxicity for future studies and cross-validation studies based on machine learning tools including Random Forests (RFs), Support Vector Machine (SVM), LASSO regression, and Elastic Net were conducted for result veri cation.Conclusions: In summary, our study indicates that following rigorous methodological experimental and extract approaches accompanied with suitable machine learning tools, in parallel to continuous addition to reliable data set developed using our meta-analysis approach, will offer higher predictive power and accuracy, and also help to provide effective information on designing safe graphene.

Structure–Activity Relationship of Graphene-Based Materials: Impact of the Surface Chemistry, Surface Specific Area and Lateral Size on Their In Vitro Toxicity

“…Our conclusion stating that lateral size impacts cytotoxicity is in agreement with a machine learning work [48] where SARs were investigated for GBMs. Lateral size was also found to have a major impact on cytotoxicity.…”

Impact of Graphene Derivatives as Artificial Extracellular Matrices on Mesenchymal Stem Cells

“…In a recent study, different strategies towards the improvement and acceleration of data mining to analyse the cytotoxic potential of graphene and its physiochemical properties has been attempted. For example, machine learning has been employed to study the cell model using experimental parameters which induce cytotoxicity [120]. Furthermore, an increasing number of research groups devoted their attention to develop alternative MSCs mediated therapies.…”

Digital Innovation Enabled Nanomaterial Manufacturing; Machine Learning Strategies and Green Perspectives

“…In the case of liver cancer, it was shown that cells are damaged at the DNA level. In this direction, Bayesian networks and random forest models were considered promising to manage data mined from literature and databases in order to develop a predictive modelling framework about the factors affecting cellular toxicity of graphene and deliver a holistic hazard ranking assessment of graphene, as well as support rational nanomaterials design, environmental, and health policies [ 122 ].…”

“…For instance, in the mining of 17 publications about CNTs and their effect on pulmonary toxicity, 136 types of structures indicated that aggregate size, diameter, length, and metallic impurities are the most important descriptors. In another case regarding quantum dots, it was shown that toxicity was connected beyond the structural factors also to exposure indicators and cell lines such as exposure time, assay type, diameter, surface modification, shell and ligand [ 122 ].…”