Machine learning predicts the functional composition of the protein corona and the cellular recognition of nanoparticles (2020)
Original Study 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.
Data Sample
| Title |
NP without modification |
Surface modification |
SizeTEM (nm) |
Zeta potential |
Incubation protein source |
Incubation plasma concentration (v/v%) |
Incubation NP concentration (mg/L) |
Centrifugation speed (g) |
Centrifugation time ?min? |
Certrifugation temperature (?) |
NP type |
NP shape |
Dispersion medium |
Dispersion medium pH |
SizeDLS (nm) |
PDI |
Incubation culture |
Incubation time (h) |
Incubation temperature (?) |
Centrifugation repetitions |
Modification type |
| Protein adsorption is required for stealth effect of poly(ethylene glycol)- and poly(phosphoester)-coated nanocarriers |
PS |
PEG |
119 |
8 |
HP |
80 |
822,2696 |
20000 |
60 |
25 |
other |
sphere |
water |
7 |
119 |
2,5 |
water |
1 |
37 |
1 |
Neutral |
| Protein adsorption is required for stealth effect of poly(ethylene glycol)- and poly(phosphoester)-coated nanocarriers |
PS |
PEG |
117 |
14 |
HP |
80 |
836,3325 |
20000 |
60 |
25 |
other |
sphere |
water |
7 |
117 |
2,5 |
water |
1 |
37 |
1 |
Neutral |
| Protein adsorption is required for stealth effect of poly(ethylene glycol)- and poly(phosphoester)-coated nanocarriers |
PS |
NH2 |
106 |
46 |
HP |
80 |
923,114 |
20000 |
60 |
25 |
other |
sphere |
water |
7 |
106 |
2,5 |
water |
1 |
37 |
1 |
Anionic |
| Protein adsorption is required for stealth effect of poly(ethylene glycol)- and poly(phosphoester)-coated nanocarriers |
PS |
PEEP |
122 |
-10 |
HP |
80 |
802,0499 |
20000 |
60 |
25 |
other |
sphere |
water |
7 |
122 |
2,5 |
water |
1 |
37 |
1 |
Neutral |
| Protein adsorption is required for stealth effect of poly(ethylene glycol)- and poly(phosphoester)-coated nanocarriers |
PS |
PEEP |
117 |
-9 |
HP |
80 |
836,3255 |
20000 |
60 |
25 |
other |
sphere |
water |
7 |
117 |
2,5 |
water |
1 |
37 |
1 |
Neutral |
Data Summary
| Variable |
Count (unique values) |
| NP without modification |
40 |
| Surface modification |
50 |
| SizeTEM (nm) |
155 |
| Zeta potential |
293 |
| Incubation protein source |
5 |
| Incubation plasma concentration (v/v%) |
18 |
| Incubation NP concentration (mg/L) |
39 |
| Centrifugation speed (g) |
24 |
| Centrifugation time (min) |
10 |
| Certrifugation temperature (?) |
7 |
| NP type |
4 |
| NP shape |
6 |
| Dispersion medium |
5 |
| Dispersion medium pH |
3 |
| SizeDLS (nm) |
301 |
| PDI |
181 |
| Incubation culture |
3 |
| Incubation time (h) |
22 |
| Incubation temperature |
8 |
| Centrifugation repetitions |
9 |
| Modification type |
3 |