Machine learning provides predictive analysis into silver nanoparticle protein corona formation from physicochemical properties

Abstract

Proteins encountered in biological and environmental systems bind to engineered nanomaterials (ENMs) to form a protein corona (PC) that alters the surface chemistry, reactivity, and fate of the ENMs. Complexities such as the diversity of the PC and variation with ENM properties and reaction conditions make the PC population difficult to predict. Here, we support the development of predictive models for PC populations by relating biophysicochemical characteristics of proteins, ENMs, and solution conditions to PC formation using random forest classification. The resulting model offers a predictive analysis into the population of PC proteins in Ag ENM systems of various ENM size and surface coatings. With an area under the receiver operating characteristic curve of 0.83 and F1-score of 0.81, a model with strong performance has been constructed based upon experimental data. The weighted contribution of each variable provides recommendations for mechanistic models based upon protein enrichment classification results. Protein biophysical properties such as pI and weight are weighted heavily. Yet, ENM size, surface charge, and solution ionic strength also proved essential to an accurate model. The model can be readily modified and applied to other ENM PC populations. The model presented here represents the first step toward robust predictions of PC fingerprints.

Machine learning predicts the functional composition of the protein corona and the cellular recognition of nanoparticles

“…(15,23) with robust tolerance of heterogeneity. However, the quantitative prediction of the functional compositions of the protein corona by a comprehensive understanding of complex NP-protein binding patterns remains unavailable using machine learning (24). To address these problems, the present work attempts to use a powerful RF model to identify the rules for protein corona formation by associating numerous NP physicochemical properties and distinct experimental conditions with quantitative protein corona compositions (e.g., hydrophily and function).…”

Protein Corona Composition of Silica Nanoparticles in Complex Media: Nanoparticle Size does not Matter

“…ρ To identify potential links between the LFC and the physicochemical features, we fitted linear regression models using the LFC as a response variable and the physicochemical properties as covariates, for each NP size (for predictive models see Findlay et al [70] for example). Using a Bayesian factor analysis against all possible models (see Section 2.4) we observed that the best fitted model was the same for each NP size:…”

Role of Artificial Intelligence and Machine Learning in Nanosafety

“…[44] Findlay et al tackled this important problem of predicting the protein corona around silver nanoparticles using an ML approach. [45] They training a random forest model using biophysicochemical characteristics of proteins, ENMs, and solution conditions. The area under the receiver operating characteristic curve was 0.83 indicating strong predictive performance.…”