Human Angiotensin I-Converting Enzyme Produced by Different Cells: Classification of the SERS Spectra with Linear Discriminant Analysis

Abstract

Angiotensin I-converting enzyme (ACE) is a peptidase widely presented in human tissues and biological fluids. ACE is a glycoprotein containing 17 potential N-glycosylation sites which can be glycosylated in different ways due to post-translational modification of the protein in different cells. For the first time, surface-enhanced Raman scattering (SERS) spectra of human ACE from lungs, mainly produced by endothelial cells, ACE from heart, produced by endothelial heart cells and miofibroblasts, and ACE from seminal fluid, produced by epithelial cells, have been compared with full assignment. The ability to separate ACEs' SERS spectra was demonstrated using the linear discriminant analysis (LDA) method with high accuracy. The intervals in the spectra with maximum contributions of the spectral features were determined and their contribution to the spectrum of each separate ACE was evaluated. Near 25 spectral features forming three intervals were enough for successful separation of the spectra of different ACEs. However, more spectral information could be obtained from analysis of 50 spectral features. Band assignment showed that several features did not correlate with band assignments to amino acids or peptides, which indicated the carbohydrate contribution to the final spectra. Analysis of SERS spectra could be beneficial for the detection of tissue-specific ACEs.

Keywords: SERS; angiotensin I-converting enzyme; full spectra assignment; glycosylation; linear discriminant analysis; nanostructured surface; tissue-specificity.

Figure 1

SERS spectra of ACEs. Red traces indicate those vibrational bands which contain the differences in ACE spectra.

Figure 2

The averages of the collected spectra for each type of ACE from the selected range after baseline correction, normalization and smoothing.

Figure 3

LDA subspace from test set defined by discriminant functions (matrix Z). The corresponding protein groups from the test part are indicated by color: blue—lung ACE; red—seminal fluid ACE; green—heart ACE.

Figure 4

Feature importance analysis of trained LDA model. Bar plots indicate the most significant model weights for each ACE group after filtering described above. The average spectra of the corresponding ACE are also shown in the figure.

Figure 5

Feature contribution to the mean ACE spectra: (a) for first 25 selected features; (b) for first 50 selected features; (c) achieved accuracy with its confidence (2σ) interval vs number of selected features for the classification.

Figure 6

Selected intervals from Figure 5, assigned for each type of ACE, respectively. Bar plots correspond to the feature importance. Lines correspond to spectra averages for each ACE type.