Method for estimating marker protein levels

Abstract

To provide an estimation method for estimating the amount of marker proteins in the stratum corneum. [Solution] Identify one or more cell regions, stratified exfoliation regions, and single-cell regions in the stratum corneum image. A marker protein quantity estimation method that estimates the amount of marker proteins in the stratum corneum from stratum corneum images based on the correlation between the obtained stratum corneum parameters as explanatory variables and one of the following as the dependent variable: Enolase-1 quantity, FABP5 quantity, or Polyamine quantity.

Description

Technical Field

[0001] The present invention relates to a method for estimating the amount of marker protein in the stratum corneum.

Background Art

[0002] Methods for evaluating skin conditions based on the amount of specific proteins or the expression level of specific genes in stratum corneum cells are known. For example, Patent Document 1 discloses a method for evaluating skin viscoelasticity from the expression level of Enolase-1 in the stratum corneum, Patent Document 2 discloses a method for evaluating acne worsening from the increased expression level of FABP-5 in a skin sample compared to the normal state, and Patent Document 3 discloses a method for evaluating skin conditions such as chime from the amount of polyamine in the stratum corneum. The expression levels of these marker proteins are generally determined by the fluorescent antibody method. However, it is very laborious to create a calibration curve for determining the relationship between fluorescence intensity and protein concentration, prepare a measurement sample, and measure the fluorescence intensity. Therefore, a simple method for estimating the amount of marker protein is required.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide a method for estimating the amount of marker protein in the stratum corneum.

Means for Solving the Problems

[0005] This invention was developed as a result of diligent research to solve the above problems, and it was discovered that the amount of marker proteins in the stratum corneum can be estimated using the stratum corneum structure obtained from observation images of the stratum corneum as an indicator.

[0006] Specifically, the means for solving the problems of the present invention are as follows: 1. Identify one or more cellular regions, stratified exfoliation regions, and single-cell regions in the stratum corneum image. A method for estimating the amount of marker proteins in the stratum corneum, characterized by estimating the amount of marker proteins in the stratum corneum from a stratum corneum image based on one or more of the correlations selected from (1) to (3) below. (1) Correlation between one or more stratum corneum parameters selected from the group consisting of cell region area, roundness, and approximate 4-6 sides, with Enolase-1 amount as the dependent variable. (2) Correlation between one or more stratum corneum parameters selected from a group consisting of the mean single-cell brightness, median single-cell brightness, and minimum single-cell brightness, with FABP5 amount as the explanatory variable and the dependent variable. (3) Correlation between one or more stratum corneum parameters selected from the group consisting of multilayer exfoliation area, multilayer exfoliation rate, average single-cell brightness, median single-cell brightness, maximum single-cell brightness, and minimum single-cell brightness, with polyamine amount as the explanatory variable and the dependent variable. 2. The method for estimating the amount of marker proteins according to 1, characterized in that the amounts of two or more marker proteins are estimated based on two or more selected from the correlations in (1) to (3) above. 3. The method for estimating marker protein amounts according to 1. or 2., characterized in that one or more of the cell regions, stratified exfoliation regions, and single-cell regions are identified using a machine learning model that has been trained in advance on multiple training stratum corneum images and one or more cell regions, stratified exfoliation regions, and single-cell regions obtained by visual evaluation in each training stratum corneum image. [Effects of the Invention]

[0007] The present invention's method for estimating marker protein levels uses numerical values ​​obtained from the stratum corneum structure as indicators, allowing for very easy and accurate estimation of marker protein levels in the stratum corneum. The marker protein levels estimated by this method can be used to evaluate skin condition and other factors. [Modes for carrying out the invention]

[0008] This invention identifies one or more cellular regions, stratified exfoliation regions, and single-cell regions in stratum corneum images. This invention relates to a method for estimating the amount of marker proteins in the stratum corneum from stratum corneum images, based on one or more of the correlations selected from (1) to (3) below. (1) Correlation between one or more stratum corneum parameters selected from the group consisting of cell region area, roundness, and approximate 4-6 sides, with Enolase-1 amount as the dependent variable. (2) Correlation between one or more stratum corneum parameters selected from a group consisting of the mean single-cell brightness, median single-cell brightness, and minimum single-cell brightness, with FABP5 amount as the explanatory variable and the dependent variable. (3) Correlation between one or more stratum corneum parameters selected from the group consisting of multilayer exfoliation area, multilayer exfoliation rate, average single-cell brightness, median single-cell brightness, maximum single-cell brightness, and minimum single-cell brightness, with polyamine amount as the explanatory variable and the dependent variable.

[0009] Enolase-1 is an intracellular protein with a molecular weight of 47,038 Da. Enolase, formally known as phosphopyruvate hydratase, is an important enzyme involved in glycolysis. Humans have five isozymes of phosphopyruvate hydratase, and Enolase-1 is one of them (α-enolase). FABP5 (Fatty acid binding protein-5) is an intracellular protein with a molecular weight of 15,033 Da. FABP5 is primarily found in the epidermis and was identified due to its increased expression in the tissues of psoriasis patients (characterized by regular thickening and parakeratinization of the epidermis). FABP5 is an intracellular protein that binds to fatty acids (oleic acid) and hydrophobic ligands, and is involved in fatty acid uptake, transport, metabolism, and cell proliferation and differentiation. Polyamines are substances containing two or more amino groups that are synthesized in the body from amino acids. Polyamines are actively synthesized in the cells of all animals and humans during the growth phase. During nucleic acid synthesis in cell proliferation, they strongly bind to RNA, altering the RNA structure and promoting protein synthesis at various stages of growth. In addition, polyamines have various functions such as anti-inflammatory effects, antioxidant effects, inhibition of glycation, and life extension.

[0010] The method for collecting the stratum corneum to obtain images can be either biopsy or tape stripping, but tape stripping is preferred because it is less burdensome for the subject. Tape stripping is a method in which an adhesive tape is applied to the skin and then peeled off to collect the surface layer of the skin.

[0011] Stratum corneum cells collected by tape stripping are imaged using transmitted light observation (including differential interference contrast, phase contrast, and dark-field observation) or reflected light observation to observe the morphology of the cells. Stratum corneum cells are preferably observed in an unstained state, but they can be stained if necessary. Cell observation can be performed using a microscope capable of cell observation, such as the VHX-5000 digital microscope from Keyence Corporation or the Dino-Lite digital microscope from AnMo Electronics Corporation. Observation conditions are not limited as long as they allow for detailed observation of cells, but examples include conditions with a resolution of 1.0 μm / pixel or higher and approximately 200,000 pixels or more.

[0012] The captured stratum corneum image is processed using an image processing system to identify one or more of the cell region, the stratified exfoliation region, and the single-cell region in the stratum corneum image. Then, based on one or more of the identified cell region, stratified exfoliation region, and single-cell region, according to the type of marker protein to be estimated, etc., one or more selected from the group consisting of the cell region area, stratified exfoliation area, stratified exfoliation rate, circularity, approximated 4-6 polygon, single-cell luminance average value, single-cell luminance median value, single-cell luminance maximum value, and single-cell luminance minimum value are quantified. The stratum corneum image may use a color image, an image converted to grayscale by image processing, or both can be used.

[0013] The cell region area is the sum of the areas of the stratum corneum cell regions in the stratum corneum image. The stratified exfoliation area is the area of the region where two or more layers of the stratum corneum overlap and exfoliate. The stratified exfoliation rate is the ratio of the "stratified exfoliation area" to the "cell region area" (stratified exfoliation area / cell region area). The circularity is the value obtained by averaging over all cells in one image of the degree of circularity of the region of each stratum corneum cell (calculated by 4π×(area) / (square of the perimeter)). The approximated 4-6 polygon means that with the centroid of the shape of each stratum corneum cell as the center, a regular 4-6 polygon is placed within the stratum corneum cell region, and the angle and size are adjusted so that the area of the region protruding from the regular 4-6 polygon is minimized. When the area of the protruding region is minimized, the area of the protruding region is divided by the stratum corneum cell area and then returned. The n for which this value is minimized among regular n-gons (n is 4 to 6) is taken as the approximated n-gon, and it is the value obtained by averaging n for each stratum corneum cell in the stratum corneum image over all cells.

[0014] The single-cell luminance average value is the value obtained by averaging the average luminance values within the cell regions of each stratum corneum cell in the stratum corneum image over all cells. The single-cell luminance median value is the value obtained by averaging the median luminance values within the cell regions of each stratum corneum cell in the stratum corneum image over all cells. The single-cell luminance maximum value is the value obtained by averaging the maximum luminance values within the cell regions of each stratum corneum cell in the stratum corneum image over all cells. The minimum cell brightness value is the average value of the minimum brightness within the cell regions of individual stratum corneum cells in the stratum corneum image across all cells. Hereinafter, one or more selected from the group consisting of cell region area, multilamellar exfoliation area, multilamellar exfoliation rate, circularity, approximated 4 - 6 polygon, average 1 - cell brightness value, median 1 - cell brightness value, maximum 1 - cell brightness value, and minimum 1 - cell brightness value, when quantified, are also referred to as stratum corneum parameter values.

[0015] Quantification by the image processing system can be performed using a known image processing system. For example, the image processing software attached to the above - mentioned digital microscope, commercially available image processing software, etc. can be used. Also, an image processing system equipped with a machine learning model that has previously machine - learned one or more of a plurality of learning stratum corneum images and, in each learning stratum corneum image, the cell region (region where cells are present) by visual evaluation, the multilamellar exfoliation region (region where two or more layers of the stratum corneum overlap and exfoliate) by visual evaluation, and the 1 - cell region (region of each individual cell) by visual evaluation can be used. By inputting the stratum corneum image to be quantified into this machine learning model, outputting one or more of the cell region, multilamellar exfoliation region, and 1 - cell region of this stratum corneum image, and calculating the stratum corneum parameter values (cell region area, multilamellar exfoliation area, multilamellar exfoliation rate, circularity, approximated 4 - 6 polygon, average 1 - cell brightness value, median 1 - cell brightness value, maximum 1 - cell brightness value, minimum 1 - cell brightness value) based on the cell region, multilamellar exfoliation region, and 1 - cell region output by the machine learning model, a stratum corneum parameter value equivalent to the stratum corneum parameter value based on visual evaluation can be calculated quickly. Furthermore, one or more of the stratum corneum region, multilamellar exfoliation region, and 1 - cell region output by the image processing system equipped with the machine learning model can be visually corrected by a person to obtain the stratum corneum parameter value.

[0016] The method for estimating the amount of marker proteins in the stratum corneum using these quantified stratum corneum parameter values ​​as indicators is not particularly limited, and known methods can be used. For example, the stratum corneum parameter values ​​may be analyzed using simple linear regression or multiple linear regression. The multiple linear regression may be linear or nonlinear. In addition, other parameters other than cell region area, layered exfoliation area, layered exfoliation rate, roundness, approximating 4-6 polygon, average single-cell brightness, median single-cell brightness, maximum single-cell brightness, and minimum single-cell brightness may be included as explanatory variables in the multiple linear regression. [Examples]

[0017] <Sample for machine learning> Stratum corneum cells were collected from the faces of 412 women (aged 18-87, average age 46.8) using the tape stripping method. The collected stratum corneum cells were photographed unstained using a digital microscope (Keyence Corporation, VHX-5000) at 8-bit (RGB color), a resolution of 0.41 μm / pixel, and a pixel count of 1600 x 1200 pixels. Two to three fields of view were captured for each sample and used for machine learning.

[0018] Using the image annotation software Labelme, cell regions, stratified exfoliation regions, and single-cell regions were visually identified to obtain stratum corneum images for training. We used machine learning on each training stratum corneum image, along with cell regions, stratified exfoliation regions, and single-cell regions evaluated visually, to obtain a machine learning model capable of outputting cell regions, stratified exfoliation regions, and single-cell regions.

[0019] <Sample> Stratum corneum cells were collected from the faces of 227 women (aged 28-87, average age 47.2 years) using the tape stripping method. 3-5 samples were collected from each woman, resulting in a total of 966 samples. The sample preparation method is the same as that used for machine learning samples. Sample images were analyzed using an image processing device equipped with a machine learning model. The cell region area, layer exfoliation area, layer exfoliation rate, roundness, approximate 4-6 polygon, average single-cell brightness, median single-cell brightness, maximum single-cell brightness, and minimum single-cell brightness of each stratum corneum image were quantified to determine the stratum corneum parameter values. Furthermore, the cell area, cell perimeter, area and ratio of the long and short sides of the rectangle circumscribing the cell, and the maximum standard deviation of cell brightness were also quantified to determine the stratum corneum parameter values.

[0020] The single-cell area is the average area of ​​all individual stratum corneum cells in a stratum corneum image. Single-cell circumference is the average circumference of all individual stratum corneum cells within a stratum corneum image. The area of ​​the rectangle circumscribing a single cell is the average area of ​​the smallest rectangle that covers the entire area of ​​each individual stratum corneum cell in a stratum corneum image, across all cells. The ratio of the long side to the short side of a rectangle circumscribing a single cell is the average ratio (long side / short side) of the smallest rectangle covering the entire area of ​​each individual stratum corneum cell in a stratum corneum image, across all cells. The single-cell brightness standard deviation is the value obtained by calculating the standard deviation of brightness within the cell region of individual stratum corneum cells in a stratum corneum image.

[0021] Furthermore, comparing the cell regions and layered delamination regions analyzed by an image processing device equipped with a machine learning model, respectively, for 966 samples, the results showed that the ratio of the cell region area by visual evaluation to the cell region area analyzed by the image processing device equipped with a machine learning model was 95%, and the ratio of the layered delamination region area by visual evaluation to the layered delamination region area analyzed by the image processing device equipped with a machine learning model was 86%. Thus, the cell regions and layered delamination regions by visual evaluation were equivalent to those analyzed by the image processing device equipped with a machine learning model.

[0022] <Measurement of marker protein levels (Enolase-1, FABP5)> • Extraction from the stratum corneum of the skin A stratum corneum sample was collected using a stratum corneum checker and placed in a tube containing glass beads and 500 μl of RIPA buffer (#89900 / Thermo SCIETIFIC). The tube was shaken for 3 minutes using the bead disruption method to extract stratum corneum proteins.

[0023] • Measurement of marker protein levels 100 μl / well of immobilized antibody (Table 1), diluted in PBS(-) (WAKO / #16219321), was dispensed into a 96-well plate (COSTAR / #3590) and incubated overnight at 20°C for fixation. After washing three times with 300 μl of wash buffer (PBS containing 0.05% Tween2), 200 μl / well of Reagent Diluent (R&D systems / #890803) was added, and blocking was performed at 25°C for 1 hour. After washing again, 100 μl / well of stratum corneum extract sample was added and reacted at 37°C for approximately 2 hours. Purified protein antigens of each biomarker (Table 1) were also added in a concentration gradient and reacted to create a calibration curve.

[0024] Next, after washing, 100 μl / well of a solution prepared by diluting the detection antibody (Table 1) in Wash Buffer to a concentration of 0.5 μg / ml was added, and the mixture was reacted at 37°C for 1 hour. After the reaction was complete, the wells were washed, and then Streptavidin-HRP (R&D Systems / #890803) was diluted 200-fold with wash buffer, added at a rate of 100 μl / well, and reacted at 25°C for 30 minutes.

[0025] After the reaction was complete, the wells were washed, and the mixture was colored with 100 μl / well of TMB reagent (Promega / #G7431) (25°C, 15 minutes). The reaction was then stopped with 1N sulfuric acid, and the absorbance at 450 nm was measured using a SPECTRA MAX 190 (Molecular Device). The amount of marker protein in each sample was calculated from the aforementioned calibration curve. Each marker protein amount was corrected for the total protein content in the stratum corneum extract and expressed as an amount per unit protein. The total protein content was measured using the BCA Protein Assay kit (Thermo Fisher Scientific).

[0026] [Table 1]

[0027] <Measurement of marker protein levels (Polyamine)> Stratum corneum cells collected by tape stripping were attached to a transparent plate with the stripped surface facing upwards. A reagent that specifically binds to polyamines and emits red fluorescence (Funakoshi Co., Ltd., Polyamine RED) was dropped onto the plate and allowed to stand for a certain period of time. After washing with water and drying, fluorescence imaging was performed using a fluorescence microscope under observation conditions of excitation light 560 nm and fluorescence light 580 nm. From the acquired fluorescence images, the average brightness value per image was quantified as the amount of polyamine.

[0028] "Simple linear regression analysis" Simple linear regression analysis was performed on each stratum corneum parameter value and marker protein amount. For those where a correlation was found, the correlation coefficient r, p value, and the equation of the simple linear regression line (Y=aX+b, where X is each stratum corneum parameter value and Y is the marker protein amount) are shown in Table 2. [Table 2]

[0029] As shown in Table 2, each stratum corneum parameter value described in (1) to (3) of the present invention was correlated (|r|≧0.2) with the amount of marker protein described in each of (1) to (3).

[0030] Multiple regression analysis For each marker protein, multiple regression analysis was performed using several stratum corneum parameter values ​​that showed correlation as explanatory variables. The equation of the multiple regression line is (Y=a1X1+a2X2+···+a n X n Table 3 shows the values ​​of each stratum corneum parameter (+b, Xn are the values, and Y is the amount of marker protein). [Table 3]

[0031] As shown in Table 3, a higher correlation was observed through multiple regression analysis.

[0032] Furthermore, multiple regression analysis was performed using 14 stratum corneum parameter values, including stratum corneum parameters that did not show a correlation with marker protein levels, as explanatory variables. The equation of the multiple regression line is (Y=a1X1+a2X2+···+a 14 X 14 Table 4 shows the values ​​of each stratum corneum parameter (+b, Xn are the values, and Y is the amount of marker protein).

[0033] [Table 4]

[0034] A higher correlation was observed when the layer parameter values ​​described in (1) to (3) of the present invention were combined with other parameter values.

Claims

1. Identify one or more cellular regions, stratified exfoliation regions, and single-cell regions in the stratum corneum image. A method for estimating the amount of marker proteins in the stratum corneum, characterized by estimating the amount of marker proteins in the stratum corneum from a stratum corneum image based on the correlation relationship described in (3) below. (3) Correlation between one or more stratum corneum parameters selected from the group consisting of multilayer exfoliation area, multilayer exfoliation rate, average single-cell brightness, median single-cell brightness, maximum single-cell brightness, and minimum single-cell brightness, with the amount of polyamine as the dependent variable.

2. The method for estimating marker protein amounts according to claim 1, characterized in that one or more of the cell regions, stratified exfoliation regions, and single-cell regions are identified using a machine learning model that has been trained in advance on multiple training stratum corneum images and one or more cell regions, stratified exfoliation regions, and single-cell regions obtained by visual evaluation in each training stratum corneum image.

Images