Dataset Information

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.

SUBMITTER: Findlay MR

PROVIDER: S-EPMC5986185 | biostudies-literature | 2018 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Findlay Matthew R MR Freitas Daniel N DN Mobed-Miremadi Maryam M Wheeler Korin E KE

Environmental science. Nano 20171101 1

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 ...[more]

PMID: 29881624

Similar Datasets

Project description:The potential applications of nanomaterials as drug delivery systems and in other products continue to expand. Upon introduction into physiological environments and driven by energetics, nanomaterials readily associate proteins forming a protein corona (PC) on their surface. This PC influences the nanomaterial's surface characteristics and may impact their interaction with cells. To determine the biological impact of nanomaterial exposure as well as nanotherapeutic applications, it is necessary to understand PC formation. Utilizing a label-free mass spectrometry-based proteomics approach, we examined the composition of the PC for a set of four silver nanoparticles (AgNPs) including citrate-stabilized and polyvinlypyrrolidone-stabilized (PVP) colloidal silver (20 or 110 nm diameter). To simulate cell culture conditions, AgNPs were incubated for 1 h in Dulbecco's Modified Eagle Medium supplemented with 10% fetal bovine serum, washed, coronal proteins solubilized, and proteins identified and quantified by label-free LC-MS/MS. To determine which attributes influence PC formation, the AgNPs were characterized in both water and cell culture media with 10% FBS. All AgNPs associated a common subset of 11 proteins including albumin, apolipoproteins, keratins, and other serum proteins. 110 nm citrate- and PVP-stabilized AgNPs were found to bind the greatest number of proteins (79 and 85 respectively) compared to 20 nm citrate- and PVP-stabilized AgNPs (45 and 48 respectively), suggesting a difference in PC formation based on surface curvature. While no relationships were found for other protein parameters (isoelectric point or aliphatic index), the PC on 20 nm AgNPs (PVP and citrate) consisted of more hydrophobic proteins compared to 110 nm AgNPs implying that this class of proteins are more receptive to curvature-induced folding and crowding in exchange for an increased hydration in the aqueous environment. These observations demonstrate the significance of electrostatic and hydrophobic interactions in the formation of the PC which may have broad biological and toxicological implications.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets