Dataset Information

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

ABSTRACT: Protein corona formation is critical for the design of ideal and safe nanoparticles (NPs) for nanomedicine, biosensing, organ targeting, and other applications, but methods to quantitatively predict the formation of the protein corona, especially for functional compositions, remain unavailable. The traditional linear regression model performs poorly for the protein corona, as measured by R² (less than 0.40). Here, the performance with R² over 0.75 in the prediction of the protein corona was achieved by integrating a machine learning model and meta-analysis. NPs without modification and surface modification were identified as the two most important factors determining protein corona formation. According to experimental verification, the functional protein compositions (e.g., immune proteins, complement proteins, and apolipoproteins) in complex coronas were precisely predicted with good R² (most over 0.80). Moreover, the method successfully predicted the cellular recognition (e.g., cellular uptake by macrophages and cytokine release) mediated by functional corona proteins. This workflow provides a method to accurately and quantitatively predict the functional composition of the protein corona that determines cellular recognition and nanotoxicity to guide the synthesis and applications of a wide range of NPs by overcoming limitations and uncertainty.

SUBMITTER: Ban Z

PROVIDER: S-EPMC7229677 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Ban Zhan Z Yuan Peng P Yu Fubo F Peng Ting T Zhou Qixing Q Zhou Qixing Q Hu Xiangang X

Proceedings of the National Academy of Sciences of the United States of America 20200424 19

Protein corona formation is critical for the design of ideal and safe nanoparticles (NPs) for nanomedicine, biosensing, organ targeting, and other applications, but methods to quantitatively predict the formation of the protein corona, especially for functional compositions, remain unavailable. The traditional linear regression model performs poorly for the protein corona, as measured by R2 (less than 0.40). Here, the performance with R2 over 0.75 in the predi ...[more]

PMID: 32332167

Similar Datasets

Project description:Background: When nanoparticles (NPs) are applied into a biological fluid, such as blood, proteins bind rapidly to their surface forming a so-called "protein corona". These proteins are strongly attached to the NP surface and confers them a new biological identity that is crucial for the biological response in terms of body biodistribution, cellular uptake, and toxicity. The corona is dynamic in nature and it is well known that the composition varies in dependence of the physicochemical properties of the NPs. In the present study we investigated the protein corona that forms around poly(lactide-co-glycolide) (PLGA) NPs at different serum concentrations using two substantially different serum types, namely fetal bovine serum (FBS) and human serum. The corona was characterized by means of sodium dodecylsulfate polyacrylamide gel electrophoresis (SDS-PAGE), Bradford protein assay, zeta potential measurements, and liquid chromatography-mass spectrometry/mass spectrometry (LC-MS/MS). Additionally, the time-dependent cell interaction of PLGA NPs in the absence or presence of a preformed protein corona was assessed by in vitro incubation experiments with the human liver cancer cell line HepG2. Results: Our data revealed that the physiological environment critically affects the protein adsorption on PLGA NPs with significant impact on the NP-cell interaction. Under comparable conditions the protein amount forming the protein corona depends on the serum type used and the serum concentration. On PLGA NPs incubated with either FBS or human serum a clear difference in qualitative corona protein composition was identified by SDS-PAGE and LC-MS/MS in combination with bioinformatic protein classification. In the case of human serum a considerable change in corona composition was observed leading to a concentration-dependent desorption of abundant proteins in conjunction with an adsorption of high-affinity proteins with lower abundance. Cell incubation experiments revealed that the respective corona composition showed significant influence on the resulting nanoparticle-cell interaction. Conclusion: Controlling protein corona formation is still a challenging task and our data highlight the need for a rational future experimental design in order to enable a prediction of the corona formation on nanoparticle surfaces and, therefore, the resulting biodistribution in the body.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets