Methods, systems, devices, media, or program products for computer-aided diagnosis or screening of drugs based on krtdap

Abstract

This invention provides a method, system, device, medium, or program product for computer-aided diagnosis or drug screening based on KRTDAP. This invention found that KRTDAP expression is significantly elevated in patients with oral submucosal fibrosis. Further research revealed that high KRTDAP expression promotes the progression of oral submucosal fibrosis, suggesting that KRTDAP may be associated with the diagnosis of oral submucosal fibrosis. Based on this, this invention provides an efficient and rapid method for the diagnosis of patients with oral submucosal fibrosis and for the screening of drugs based on KRTDAP targeting, which is of great significance for research on the prevention and treatment of oral submucosal fibrosis.

Description

Technical Field

[0001] This invention belongs to the field of next-generation information technology, specifically relating to a method, system, device, medium or program product for diagnosing oral submucosal fibrosis based on KRTDAP expression levels, and a method, system, device, medium or program product for computer-aided drug screening based on KRTDAP. Background Technology

[0002] Oral submucous fibrosis (OSF) is a chronic, progressive oral mucosal disease with a tendency to become cancerous and can affect any part of the oral mucosa. The main clinical manifestations of OSF include burning pain in the oral mucosa, progressive limitation of mouth opening, and difficulty swallowing. In the early stages of the disease, symptoms are not obvious, or patients may only experience mild stinging when consuming spicy foods. As the disease progresses, blisters begin to appear on the oral mucosa; once these blisters rupture, ulcers form. This process may be accompanied by symptoms such as decreased taste, dry mouth, and numbness of the lips and tongue. In later stages, patients experience stiffness of the oral mucosa, limited mouth opening, and tongue movement disorders, making it difficult to chew and swallow food, which may lead to malnutrition and weight loss.

[0003] Although studies have shown that areca nut chewing is a major risk factor for oral submucosal fibrosis, its pathogenic mechanism remains unclear, with current research suggesting it is the result of multiple biological processes. To date, treatment options and outcomes for oral submucosal fibrosis are very limited. Therefore, a deeper understanding of the pathogenesis of oral submucosal fibrosis will facilitate further research into treatment methods. Furthermore, exploring more precise and effective diagnostic methods based on the disease's pathogenesis will also contribute to its early prevention and treatment. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, system, device, medium or program product for diagnosing oral submucosal fibrosis based on KRTDAP expression levels, as well as a method, system, device, medium or program product for computer-aided drug screening based on KRTDAP.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] The first aspect of this invention provides a method for diagnosing fibrosis based on KRTDAP expression levels, the method being performed by a computer, and the method comprising the following steps:

[0007] Data Acquisition: Acquire data on the KRTDAP expression level in the sample of the subject to be tested. The KRTDAP expression level includes one or more of the following: nucleic acid expression level and protein expression level.

[0008] Data processing: The KRTDAP expression level data is input into the constructed fibrosis diagnostic model, which diagnoses whether the subject has fibrosis based on the KRTDAP expression data.

[0009] Output results.

[0010] Furthermore, the fibrosis is oral submucosal fibrosis.

[0011] Furthermore, the construction steps of the fibrosis diagnostic model are as follows:

[0012] Data on KRTDAP expression levels are obtained, including one or more of the following: nucleic acid expression level and protein expression level; the KRTDAP expression level data are obtained from healthy subjects and fibrosis patients; the KRTDAP expression level data are input into a machine learning algorithm to construct a fibrosis diagnostic model.

[0013] Furthermore, the nucleic acid expression level data includes, but is not limited to, data obtained by RT-PCR, qRT-PCR, in situ hybridization, RNA sequencing, and fluorescence-activated cell sorting.

[0014] Furthermore, the protein expression level data includes, but is not limited to, data obtained through mass spectrometry-based quantitative proteomics, immunoassays, protein immunoblotting, spectrophotometry, enzyme assays, ultraviolet assays, kinetic assays, electrochemical assays, colorimetric assays, turbidimetric assays, atomic absorption spectrometry, flow cytometry, mass spectrometry, or any combination thereof.

[0015] Furthermore, the construction step of the fibrosis diagnostic model also includes verifying the model's effectiveness, and the method for verifying the model's effectiveness includes ROC curves.

[0016] Furthermore, the fibrosis diagnostic model obtains results using the following criteria: when the KRTDAP expression level is higher than a threshold, the subject is classified as having fibrosis; if the KRTDAP expression level is lower than a threshold, the subject is classified as not having fibrosis.

[0017] In some embodiments of the present invention, the preset threshold is a representative value of a sample of healthy subjects, including but not limited to the maximum value, the third quartile, and the mean. In some preferred embodiments, the sample includes more than 20 samples, such as 30, 50, 80, 100, 150, 200, 300, 500, or more.

[0018] Furthermore, the machine learning algorithm includes algorithmic models developed using various development tools.

[0019] Furthermore, the development tools include, but are not limited to, TensorFlow, Scikit-Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell.

[0020] Furthermore, the algorithm models include, but are not limited to, linear regression models, logistic regression models, Lasso regression models, Ridge regression models, linear discriminant analysis models, nearest neighbor models, decision tree models, perceptron models, neural network models, support vector machine models, Naive Bayes models, AdaBoost models, GBDT models, XGBoost models, LightGBM models, CatBoost models, and random forest models.

[0021] Furthermore, the subjects / patients include humans and / or mammals.

[0022] A second aspect of the present invention provides a system for diagnosing fibrosis based on KRTDAP expression levels, the system comprising:

[0023] Data acquisition unit: used to acquire data on the expression level of KRTDAP in the sample of the subject to be tested, wherein the expression level of KRTDAP includes one or more of the following: nucleic acid expression level, protein expression level.

[0024] Data classification unit: used to classify and diagnose the fibrosis diagnostic model obtained by the data acquisition unit through the construction method provided in the first aspect of the present invention, and to obtain the classification result of whether the subject to be tested has fibrosis.

[0025] Result output unit: Used to output classification results.

[0026] Furthermore, the fibrosis is oral submucosal fibrosis.

[0027] A third aspect of the present invention provides a computer device, computer-readable storage medium, or computer program product for diagnosing fibrosis based on KRTDAP expression levels, including a computer program.

[0028] The device includes a memory and a processor, the memory being used to store program instructions; the processor being used to invoke the program instructions, which, when executed, implement the steps of the method for diagnosing fibrosis provided in the first aspect of the present invention.

[0029] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for diagnosing fibrosis provided in the first aspect of the present invention.

[0030] When the computer program is executed by a processor, it implements the steps of the method for diagnosing fibrosis provided in the first aspect of the present invention.

[0031] The fibrosis is oral submucosal fibrosis.

[0032] A fourth aspect of the present invention provides a method for screening drugs for the treatment of oral submucosal fibrosis based on KRTDAP computer-aided screening, the method comprising:

[0033] Data Acquisition: Acquire KRTDAP gene and / or protein data.

[0034] Drug screening: Candidate drugs that can inhibit KRTDAP were obtained through computer-aided screening.

[0035] Furthermore, the computer-aided screening process includes:

[0036] Obtain the KRTDAP gene sequence and / or protein structure.

[0037] Based on the KRTDAP gene sequence and / or protein structure, substances with the potential to inhibit KRTDAP are screened from the database, including RNA drugs, antibodies, and small molecule compounds.

[0038] The selected substances are subjected to molecular docking with KRTDAP to calculate their affinity / binding energy and obtain a score. The substances are then sorted according to the score, and the top n substances are selected as candidate drugs, where n is a natural number greater than or equal to 1.

[0039] Furthermore, the computer-aided screening process also includes:

[0040] Inhibitory activity experiments were conducted on candidate drugs. The inhibition rate was calculated after each candidate drug was mixed with KRTDAP protein solution, and drugs with inhibitory effects were screened.

[0041] A fifth aspect of the present invention provides a system for computer-aided screening of drugs for treating oral submucosal fibrosis based on KRTDAP, the system comprising:

[0042] Data acquisition unit: Acquire KRTDAP gene and / or protein data.

[0043] Drug screening unit: Candidate drugs that target and inhibit KRTDAP are obtained by using the computer-aided screening process provided in the fourth aspect of the present invention.

[0044] The sixth aspect of the present invention provides a computer device, computer-readable storage medium or computer program product for computer-aided screening of drugs for the treatment of oral submucosal fibrosis based on KRTDAP, including a computer program.

[0045] The device includes a memory and a processor, the memory being used to store program instructions; the processor being used to invoke the program instructions, and when the program instructions are executed, to implement the steps of the computer-aided method for screening drugs for treating oral submucosal fibrosis provided in the fourth aspect of the present invention.

[0046] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for computer-aided screening of drugs for treating oral submucosal fibrosis provided in the fourth aspect of the present invention.

[0047] When the computer program is executed by a processor, it implements the steps of the method for computer-aided screening of drugs for treating oral submucosal fibrosis provided in the fourth aspect of the present invention.

[0048] Advantages and beneficial effects of the present invention:

[0049] This invention is the first to discover significantly high expression of KRTDAP in oral submucosal fibrosis and confirm its role in promoting the fibrotic process. This invention provides an efficient and rapid method for diagnosing patients with oral submucosal fibrosis and predicting the efficacy of drug treatments, which is of great significance for research on the prevention and treatment of oral submucosal fibrosis. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the method for diagnosing fibrosis based on KRTDAP expression levels provided by the present invention.

[0051] Figure 2 This is a schematic diagram of the system structure for diagnosing fibrosis based on KRTDAP expression levels, as provided by the present invention.

[0052] Figure 3 This is a schematic diagram of the drug screening method based on KRTDAP provided by the present invention.

[0053] Figure 4 This is a schematic diagram of the system structure for drug screening based on KRTDAP provided by the present invention.

[0054] Figure 5 A schematic diagram of the structure of the computer device provided by the present invention.

[0055] Figure 6 The following figures illustrate the expression of KRTDAP in oral submucosal fibrosis: A shows the immunohistochemical results of KRTDAP expression in tissues of patients and healthy individuals with oral submucosal fibrosis; B is a bar chart of KRTDAP-positive regions in different tissues of patients and healthy individuals with oral submucosal fibrosis in Figure A; C shows the qRT-PCR results of KRTDAP expression in a arecoline-induced oral submucosal fibrosis cell model; D shows the enzyme-linked immunosorbent assay (ELISA) results of KRTDAP expression in a arecoline-induced oral submucosal fibrosis cell model; and E shows the qRT-PCR results of KRTDAP expression in a pressure-induced oral submucosal fibrosis cell model.

[0056] Figure 7 Figures show the experimental results of KRTDAP in promoting fibrosis: A shows the qRT-PCR results of vimentin after KRTDAP addition; B shows the qRT-PCR results of fibronectin (Fn1) after KRTDAP addition; C shows the qRT-PCR results of type III collagen (col3) after KRTDAP addition; D shows the qRT-PCR results of N-cadherin after KRTDAP addition; and E shows the protein immunoblotting results of N-cadherin (N-cadherin) and tight junction protein (Occludin) expression levels after KRTDAP addition.

[0057] Figure 8 Figures showing the results of epithelial cell migration ability experiments after the addition of KRTDAP: A is the result of the scratch assay; B is the result of the Transwell assay. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0059] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Figure 1 This is a schematic flowchart of the method for diagnosing fibrosis based on KRTDAP expression levels provided by the present invention. Specifically, the method includes:

[0062] 101: Data Acquisition: Acquire data on the KRTDAP expression level in the sample of the subject to be tested. The KRTDAP expression level includes one or more of the following: nucleic acid expression level and protein expression level.

[0063] In some embodiments, the subject / patient may be human or non-human and may include, for example, animal strains or species used as a "model system" for research purposes. Similarly, the subject / patient may include adults or adolescents (e.g., children). Furthermore, the subject / patient may refer to any living organism, preferably a mammal (e.g., human or non-human). Examples of mammals include, but are not limited to, any member of the mammalian class: humans, non-human primates (e.g., chimpanzees) and other apes and monkeys; livestock, such as cattle, horses, sheep, goats, pigs; domestic animals, such as rabbits, dogs, and cats; laboratory animals include rodents, such as rats, mice, and guinea pigs. Examples of non-mammals include, but are not limited to, birds, fish, etc.

[0064] In the context of this invention, the term "sample" as used refers to a composition obtained from or derived from a subject / patient that contains cells and / or other molecular entities to be characterized and / or identified based on, for example, physical, biochemical, chemical, and / or physiological characteristics. For example, a sample refers to any sample derived from a subject / patient that is expected or known to contain cells and / or molecular entities to be characterized. Samples include, but are not limited to, tissue samples, primary or cultured cells or cell lines, cell cultures, cell supernatants, cell lysates, platelets, serum, plasma, vitreous fluid, lymph, synovial fluid, follicular fluid, semen, pancreatic juice, amniotic fluid, milk, whole blood, blood-derived cells, urine, cerebrospinal fluid, saliva, sputum, tears, sweat, mucus, tissue culture fluid, tissue extracts, homogenized tissue, cell extracts, and combinations thereof.

[0065] In a specific embodiment of this invention, the human OSF tissue sample used was obtained from residual paraffin-embedded specimens from biopsies at Xiangya Stomatological Hospital, Central South University. The cells used were the human keratinocyte cell line (Hacat, ATCC PCS-200-011). Cells were thawed and revived under sterile conditions and cultured in a humidified incubator at 37°C and 5% CO2. The culture medium was DMEM, supplemented with 10% fetal bovine serum (FBS) and a 1% penicillin / streptomycin mixture. When the cells grew to approximately 80-90% confluence, they were passaged using 0.25% trypsin-EDTA digestion, with a passage ratio generally between 1:3 and 1:4. To maintain cell characteristics and avoid over-passaging, mycoplasma testing was performed regularly. Cells in the logarithmic growth phase were selected for in vivo experiments to ensure experimental success.

[0066] In some embodiments, KRTDAP expression level data can be detected by applying methods well known in the art. For example, KRTDAP expression level data can be obtained at the nucleic acid level by measuring the amount of RNA, mRNA, or any other type of RNA using methods well known in the art, including RT-PCR, qRT-PCR, in situ hybridization, RNA sequencing, and fluorescence-activated cell sorting.

[0067] In other implementations, KRTDAP expression level data can also be obtained by measuring expression levels at the protein level, including mass spectrometry-based quantitative proteomics, immunoassays, protein immunoblotting, spectrophotometry, enzymatic assays, ultraviolet assays, kinetic assays, electrochemical assays, colorimetric assays, turbidimetric assays, atomic absorption spectrometry, flow cytometry, mass flow cytometry, or any combination thereof.

[0068] In a specific embodiment of the present invention, the expression level data of KRTDAP are obtained in the following manner.

[0069] Immunohistochemistry was used to detect the expression level of KRTDAP in tissue samples. Paraffin-embedded tissue sections (4 μm thick) fixed in 4% paraformaldehyde were routinely dewaxed to water and incubated with 3% hydrogen peroxide (H2O2) solution at room temperature for 10 min to block endogenous peroxidase activity. Then, antigen retrieval was performed in a microwave oven with sodium citrate buffer (pH 6.0) for 10 min. After cooling to room temperature, the sections were washed three times with PBS for 5 min each time. They were then blocked in 5% bovine serum albumin (BSA) blocking solution at room temperature for 30 min to reduce non-specific binding. Anti-KRTDAP antibody (Thermo Fisher PA5-147376, dilution 1:1000) was added, and the sections were incubated overnight at 4°C. The sections were warmed again the next day, washed with PBS, and incubated with HRP-labeled goat anti-rabbit secondary antibody at 37°C for 30 min. DAB staining was performed, with the staining time controlled under a microscope according to the desired staining intensity. The sections were then counterstained with hematoxylin, dehydrated, cleared, and mounted. The results were observed and photographed under a microscope. KRTDAP expression was mainly located in the cytoplasm, and semi-quantitative scoring was performed based on staining intensity and the proportion of positive cells to assess its expression differences among different tissues or experimental groups.

[0070] KRTDAP expression levels were detected using Western blotting. Fresh cell samples were placed in pre-chilled lysis buffer (RIPA, containing a mixture of 1 mM PMSF and 1× protease inhibitor) and lysed on ice for 20-30 min, with intermittent vortexing for mixing. After lysis, the samples were centrifuged at 12000 g for 10-15 min at 4 °C, and the supernatant was collected as the total protein extract from cells / tissues. Protein concentration was determined using a BCA kit (following the kit instructions), and the protein samples were diluted with an equal volume using 4× loading buffer (containing β-mercaptoethanol or DTT), denatured at 95 °C for 5 min, and then rapidly cooled for later use. An equal amount of protein (usually 20-40 μg per lane, the total protein amount can be adjusted according to protein expression abundance) was separated by electrophoresis on a 10-12% SDS-PAGE gel (separation electrophoresis: 80 V for approximately 20 min (stacking gel), 120 V for approximately 40-60 min (separating gel)). After electrophoresis, the gel was transferred to a pre-activated PVDF membrane (0.45 μm) under the following conditions: constant current 300 mA for approximately 60-90 min or constant voltage 100 V for approximately 60-90 min, both performed at 4°C or in an ice-filled transfer bath to ensure transfer efficiency. The staining was then washed away with TBST. The PVDF membrane was blocked in 5% BSA at room temperature for 1 h to reduce non-specific binding. Anti-KRTDAP antibody (Thermo Fisher PA5-147376, dilution 1:1000) was added and incubated overnight at 4°C. After incubation, the membrane was washed three times with TBST for 5-10 min each time. A suitable HRP-labeled secondary antibody (1:20000) was added and incubated at room temperature for 60 min. The membrane was washed three times with TBST for 5-10 min each time to thoroughly remove free antibody. The membrane was then placed in ECL substrate for development (chemiluminescence), and photographed using a chemiluminescence imaging system. To correct for loading differences, the internal control protein (GAPDH) was simultaneously detected. Semi-quantitative analysis of band grayscale was performed using ImageJ or the software provided with the imaging system. After background subtraction, the integrated density of the target protein band and the corresponding internal control band was measured, and the target protein / internal control ratio was calculated to represent the relative expression level. At least three independent biological replicates were performed for each group, and the mean ± standard deviation (or standard error) were reported. Statistical analysis used a two-sample t-test, with a significance threshold set at P < 0.05.

[0071] The expression level of KRTDAP was detected by qRT-PCR. Cell samples were taken, and total RNA was extracted using a column RNA extraction kit. RNA concentration and purity were determined by fluorescence method (A260 / A280 should be 1.8-2.1). Using 1 μg of total RNA per sample as a template, a reverse transcription kit was used to synthesize one-stranded cDNA. The synthesized cDNA was then diluted (1:10) for later use. Primers for KRTDAP were designed using the NCBI Primer-BLAST online tool to ensure the product length was between 80-200 bp, GC content was 40-60%, and dimers and hairpin structures were avoided. Specific primer sequences are shown in Table 1. SYBR Green or probe-based qPCR Master Mix (according to manufacturer's instructions) was used. A common 20 μL system is as follows: 10 μL of 2× SYBR Green Master Mix; 0.4 μL of upstream primer (10 μM) (final concentration 200 nM); 0.4 μL of downstream primer (10 μM) (final concentration 200 nM); 2 μL of cDNA template; ddH2O to 20 μL; The following program was run on a real-time quantitative PCR instrument: 95℃ for 3 min; 95℃ for 10 s, 60℃ for 30 s (40 cycles, fluorescence reading); melting curve analysis: 95℃ Incubate at 60℃ for 15 s, then gradually increase the temperature to 95℃ and read continuously. Perform at least three technical replicates for each sample; include template-free and reverse transcription-free controls to check for contamination and genomic DNA amplification. Calculate relative expression levels using the ΔΔCq method: results are expressed as mean ± standard deviation (SD) or standard error (SEM), with at least three biological replicates; use ANOVA for statistical testing based on the experimental design, with a significance threshold of P < 0.05.

[0072] Table 1 qRT-PCR primer sequences

[0073]

[0074] The expression level of KRTDAP in cell samples was detected by enzyme-linked immunosorbent assay (ELISA). Fresh tissue or cell samples were taken, and an appropriate amount of pre-chilled lysis buffer (containing protease inhibitor) was added. After lysis on ice for 30 min, the samples were centrifuged at 12,000 × g for 15 min, and the supernatant was collected as protein samples. The total protein concentration was determined and quantified using the BCA method. Following the ELISA kit instructions, standards and samples were added to 96-well microplates pre-coated with anti-KRTDAP antibody (Krishgen Biosystems, KBH5540), and incubated at 37°C for 1 h. The plates were then washed to remove unbound material. Subsequently, biotinylated detection antibody and HRP-labeled streptavidin were added sequentially, and the plates were incubated at 37°C for 30 min each time. After each incubation, the plates were washed with washing buffer to remove non-specific binding. TMB substrate was added for color development, and the reaction was stopped at room temperature in the dark for 10–15 min. The absorbance (OD value) of each well was measured at 450 nm. A standard curve was plotted based on the OD values ​​of the standards, and the relative concentration of KRTDAP in each sample was calculated. All samples were tested in parallel triplets, and the results are expressed as mean ± standard deviation.

[0075] In some embodiments of the present invention, studies have shown that the expression level of KRTDAP is significantly increased in the tissues of patients with oral submucosal fibrosis, and exogenous supplementation of KRTDAP promotes the development of fibrosis. This suggests that KRTDAP can serve as a good biomarker for diagnosing oral submucosal fibrosis, and candidate therapeutic drugs for oral submucosal fibrosis can be screened using computer-aided methods based on KRTDAP.

[0076] In one embodiment of the invention, we demonstrated that the expression level of KRTDAP was significantly increased in OSF tissues ( Figure 6 A, Figure 6 (B) We simultaneously constructed a chemically stimulated oral submucosal fibrosis cell model using 20 μg / ml or 40 μg / ml arecoline stimulation, or induced a physically stimulated oral submucosal fibrosis cell model using a 20g balance weight, and detected the expression level of KRTDAP in these models. The results showed that the expression level of KRTDAP was also increased in the oral submucosal fibrosis models induced by physical or chemical stimulation. Figure 6 C Figure 6 D、 Figure 6 E).

[0077] In another embodiment of the invention, we found that exogenous administration of KRTDAP (cloud clonecorp, RPG294Hu01) to cells significantly upregulated vimentin (…). Figure 7 A) Fibronectin ( Figure 7B), Type III collagen ( Figure 7 C), N-cadherin ( Figure 7 D、 Figure 7 The expression level of E) downregulates the expression level of tight junction proteins (E). Figure 7 E).

[0078] In another embodiment of the invention, we found through scratch assays and Transwell assays that exogenous supplementation with KRTDAP can induce enhanced epithelial cell migration. Figure 8 A, Figure 8 B).

[0079] Cells used in the scratch assay were seeded in 24-well plates using standard culture medium (2.0-3.0 × 10⁶ cells per well). 5 Cells were cultured at 37°C and 5% CO2 until 90-100% confluence of monolayers. After confluence, the cells were washed twice with PBS and starved in serum-free medium for 12 h to inhibit the effect of proliferation on migration. A straight line was drawn vertically on each cell monolayer using a sterile 200 μL pipette tip, followed by gentle washing with PBS to remove detached cells. The required medium for each treatment group was added (0.5, 1, 2, 4 ng / ml KRTDAP (cloud clone corp, RPG294Hu01) / serum-free medium without treatment, 0.5 mL / well). A reference site image (bright field, 4×) was taken under a microscope at the start of the scratch (0 h). Incubation continued, and the same field of view was photographed again at the selected time point (12 h). The wound area or wound width (0 h and subsequent time points) was measured using image software such as ImageJ, and the wound closure percentage was calculated.

[0080] Transwell assays were performed using a 24-well plate with a Transwell insert. The upper chamber was pre-wetted with serum-free medium (200 μL) for 20 min. Cells, which had been digested with trypsin and resuspended in medium containing 1 ng / ml KRTDAP or without treatment, were adjusted to a concentration of 2.5–5.0 × 10⁶ cells / well. 5 Cells / mL, 200 μL added to the upper chamber; 600 μL of culture medium containing a chemotactic agent (10% FBS added as a chemotactic agent) added to the lower chamber. Incubate at 37℃ and 5% CO2 for 12–24 h. After incubation, gently wipe away non-migrating cells from the upper chamber membrane surface with a cotton swab, fix the lower chamber membrane (or remove the filter membrane) in 4% paraformaldehyde for 10–15 min, wash twice with PBS, and stain with 0.1% crystal violet for 10–20 min. Under a light microscope (20×), randomly select 5 fields of view to photograph and count the number of cells that have passed through the membrane in each well. Data are expressed as the average number of cells per well. At least three-well replicates should be performed for each group, and ≥3 independent experiments should be conducted.

[0081] 102: Data Processing: Input the KRTDAP expression level data into the constructed fibrosis diagnostic model, which diagnoses whether the subject has fibrosis based on the KRTDAP expression data.

[0082] In some embodiments of the present invention, the methods for constructing the fibrosis diagnostic model are known to those skilled in the art and can be implemented and realized in different ways, including the steps of associating the expression level of KRTDAP with a certain probability or risk.

[0083] In the context of this invention, the term "machine learning" refers to the use of computers to simulate or implement human learning activities, and technicians typically use various development tools to build algorithmic models for machine learning.

[0084] The development tools include, but are not limited to, TensorFlow, Scikit-Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell.

[0085] The algorithm models include, but are not limited to, linear regression models, logistic regression models, Lasso regression models, Ridge regression models, linear discriminant analysis models, nearest neighbor models, decision tree models, perceptron models, neural network models, support vector machine models, Naive Bayes models, AdaBoost models, GBDT models, XGBoost models, LightGBM models, CatBoost models, and random forest models.

[0086] In some embodiments, after constructing an evaluation model, the effectiveness of the fibrosis diagnostic model can be analyzed using ROC curves.

[0087] An ROC curve is a graph of the true positive rate (sensitivity) versus the false positive rate (100% specificity) of an experiment. It is useful for depicting the performance of a specific characteristic when distinguishing between two populations. Typically, characteristic data are selected across the entire population in ascending order based on the values ​​of a single characteristic. Then, for each value of that characteristic, the true positive and false positive rates of the data are calculated. The true positive rate is determined by counting the number of cases with values ​​higher than the characteristic value and dividing by the total number of cases. The false positive rate is determined by counting the number of controls with values ​​higher than the characteristic value and dividing by the total number of controls. While this definition refers to cases where the characteristic is higher in cases compared to controls, it also applies to cases where the characteristic is lower in cases compared to controls (in which case samples with values ​​lower than the characteristic value are counted). ROC curves can be generated with respect to individual characteristics and can also be generated with respect to other individual outputs. For example, combinations of two or more characteristics can be mathematically combined (e.g., addition, subtraction, multiplication, etc.) to provide individual sum values ​​that can be plotted on the ROC curve. Furthermore, any combination of multiple features derived from individual output values ​​can be plotted on a ROC curve.

[0088] 103: Output results.

[0089] Figure 2 This is a schematic diagram of the system structure for diagnosing fibrosis based on KRTDAP expression levels, as provided by the present invention.

[0090] The system is programmed or otherwise configured to include a data acquisition unit 201, a data classification unit 202, and a result output unit 203.

[0091] Data acquisition unit: used to acquire data on the expression level of KRTDAP in the sample of the subject to be tested, wherein the expression level of KRTDAP includes one or more of the following: nucleic acid expression level, protein expression level.

[0092] Data classification unit: used to classify and diagnose the fibrosis diagnostic model obtained by the data acquisition unit through the construction method provided in the first aspect of the present invention, and to obtain the classification result of whether the subject to be tested has fibrosis.

[0093] Result output unit: Used to output classification results.

[0094] The system may be a user's electronic device or a computer system remotely located relative to that electronic device.

[0095] Figure 3 This is a schematic diagram of the drug screening method based on KRTDAP provided by the present invention.

[0096] 301: Obtain KRTDAP gene and / or protein data.

[0097] 302: Candidate drugs that can inhibit KRTDAP were obtained through computer-aided screening.

[0098] In some implementations, computer-aided drug screening is a technique that uses computer-aided drug design methods to screen drugs. It can help researchers quickly screen a large number of small molecule compounds for candidate drugs that have strong binding affinity to target proteins and potential efficacy.

[0099] Furthermore, the computer-aided screening process includes:

[0100] Obtain the KRTDAP gene sequence and / or protein structure.

[0101] Based on the KRTDAP gene sequence and / or protein structure, substances with the potential to inhibit KRTDAP are screened from the database, including RNA drugs, antibodies, and small molecule compounds.

[0102] The selected substances are subjected to molecular docking with KRTDAP to calculate their affinity / binding energy and obtain a score. The substances are then sorted according to the score, and the top n substances are selected as candidate drugs, where n is a natural number greater than or equal to 1.

[0103] Furthermore, the computer-aided screening process also includes:

[0104] Inhibitory activity experiments were conducted on candidate drugs. The inhibition rate was calculated after each candidate drug was mixed with KRTDAP protein solution, and drugs with inhibitory effects were screened.

[0105] In some implementations, molecular docking is a method for drug design based on the characteristics of the receptor and the interaction between the receptor and drug molecules. It is a theoretical simulation method that primarily studies intermolecular interactions (such as ligand-receptor interactions) and predicts their binding modes and affinities. This method is widely used in the early stages of drug development to help researchers quickly screen compounds with potential pharmacological effects.

[0106] The molecular docking methods described primarily focus on spatial matching and energy matching. Spatial matching refers to the geometric complementarity between the drug molecule and the receptor protein, while energy matching refers to the minimization of the interaction between the drug molecule and the receptor protein. Geometric matching calculations typically employ methods such as grid-based computation and fragment growth, while energy calculations utilize methods such as simulated annealing and genetic algorithms. Based on the degree and method of simplification, molecular docking methods can be categorized into rigid docking, semi-flexible docking, and flexible docking. In rigid docking, the conformation of the docking molecules remains unchanged during the calculation process; only their spatial position and orientation are altered. Semi-flexible docking allows for partial conformational changes during the calculation. Flexible docking allows for even more conformational changes.

[0107] In some implementation schemes, the molecular libraries used in drug screening mainly include the following: ZINC, PubChem, DrugBank, ChEMBL, ChemDB, HMDB, BindingDB, and SMPDB. In addition, there are some commercial databases such as ChemDiv, Enamine, Lifechemicals, Specs, Chembridge, Maybridge, Microsource, Vitas-M, and Interbioscreen, which are also commonly used for drug screening.

[0108] In some implementation schemes, the techniques for computer-aided drug screening include one or more of the following: protein-small molecule docking, protein-protein docking, and protein-nucleic acid docking.

[0109] In some embodiments, protein-small molecule docking refers to a computational simulation process that uses specific algorithms and procedures to dock the structures of proteins and small molecules (such as drug molecules). This process can be used to study the interactions between proteins and small molecules, as well as their potential biological functions. Computational simulations of protein-small molecule docking are typically performed using software such as DOCK. DOCK is a highly automated drug design software capable of docking small molecule ligands with biomolecular receptors. It employs a fragment-based scoring method, enabling rapid and accurate docking.

[0110] In some embodiments, protein-protein docking refers to a computational simulation process that uses specific algorithms and programs to dock the structures of one protein with another. This process can be used to study the interactions between proteins and their potential biological functions. RosettaDock is a commonly used software for protein-protein docking, employing a fragment-based scoring method to achieve fast and accurate docking. This software can precisely adjust the side chain conformation during docking and considers various complex interactions, such as hydrogen bonds, ionic bonds, and hydrophobic interactions.

[0111] In some embodiments, protein-nucleic acid docking refers to a computational simulation process that uses specific algorithms and procedures to dock the structures of proteins and nucleic acids (such as DNA or RNA) together. This process can be used to study the interactions between proteins and nucleic acids, as well as their potential biological functions. Computational simulations of protein-nucleic acid docking are typically performed using software such as NAflex. NAflex is a software specifically developed for nucleic acid structure prediction and design, capable of accurately modeling and docking DNA or RNA molecules.

[0112] In some implementation schemes, the processes and methods for designing drugs based on gene sequences and / or protein structures can be summarized as follows:

[0113] Identifying the target gene / protein: The first step is to identify the target gene / protein for which the drug is to be designed, i.e., the target site. Target sites can be known disease-related genes / proteins, viral antigens, or other biomolecules.

[0114] Gene sequence analysis involves interpreting the nucleotide sequence of a target gene's DNA or RNA to uncover its biological significance, function, and association with phenotypes (such as diseases or traits). This can be achieved using technologies such as Sanger sequencing, NGS high-throughput sequencing, and TGS single-molecule sequencing.

[0115] Protein structure analysis: This involves analyzing the structure of a target protein to understand its three-dimensional conformation, surface configuration, subdomain structure, and other characteristics. This can be obtained using techniques such as X-ray crystallography and nuclear magnetic resonance.

[0116] Determining drug-gene / or protein interactions: Investigating the interaction mechanisms between drugs and target genes / proteins, including binding sites, binding modes, and binding kinetics. This can be accomplished through computer simulations, laboratory experiments, and other methods.

[0117] Drug design: Based on the interaction mechanism between drugs and target genes / proteins, drug molecules are designed to specifically bind to the target genes / proteins. This includes selecting appropriate drug types, designing the chemical structure of the molecules, and optimizing the pharmacodynamic and pharmacokinetic properties of the molecules.

[0118] Drug synthesis and validation: This involves preparing drug molecules through methods such as chemical synthesis and validating their biological activity, safety, and pharmacokinetic properties. This includes different stages such as cell experiments, animal experiments, and clinical trials.

[0119] In some implementations, RNA drugs are a class of drugs designed based on the properties of RNA and its mechanism of action within cells. RNA can act as messenger RNA (mRNA) to guide protein synthesis within cells, or as microRNA (miRNA) to regulate gene expression. Therefore, well-designed RNA drugs can be used to regulate gene expression within cells, thereby achieving the goal of treating diseases.

[0120] In some implementations, antibodies are immunoglobulins produced by plasma cells differentiated from B lymphocytes in response to antigen stimulation by the body's immune system. These antibodies specifically bind to the corresponding antigens. The structure of an antibody is mainly divided into two parts: a constant region and a variable region.

[0121] In some implementation schemes, the general procedure for conducting inhibitory activity experiments on candidate drugs is as follows:

[0122] Selecting appropriate target proteins: Based on research objectives and disease goals, select suitable target proteins as experimental subjects. Ensure that the target proteins have potential interactions with the candidate drugs under investigation.

[0123] Drug candidate preparation: Synthesize or purchase the desired drug candidate, ensuring its purity and structural accuracy. If necessary, the drug candidate can be modified or altered to optimize its inhibitory activity.

[0124] Enzyme activity assays: Design appropriate enzyme activity assays to evaluate the inhibitory activity of candidate drugs and target proteins. This can be achieved using techniques such as fluorescence resonance energy transfer (FRET), radioisotope labeling, and enzyme-linked immunosorbent assay (ELISA). Ensure the assay is reliable, sensitive, and reflects the interaction between the candidate drug and the target protein.

[0125] Figure 4 This is a schematic diagram of the system structure for drug screening based on KRTDAP provided by the present invention.

[0126] The system is programmed or otherwise configured to include a data acquisition unit 401 and a drug screening unit 402.

[0127] Data acquisition unit: Acquire KRTDAP gene and / or protein data.

[0128] Drug screening unit: Candidate drugs that target and inhibit KRTDAP are obtained by using the computer-aided screening process provided in the fourth aspect of the present invention.

[0129] Figure 5 A schematic diagram of the structure of the computer device provided by the present invention.

[0130] The computer device 500 includes a processor 501 and a memory 502 coupled to the processor 501. The memory 502 stores program instructions. When the program instructions are executed by the processor 501, the processor 501 performs the steps of the method for diagnosing fibrosis based on KRTDAP expression levels or the method for screening drugs based on KRTDAP, as described above.

[0131] The processor 501 can also be referred to as a CPU (Central Processing Unit). The processor 501 may be an integrated circuit chip with signal processing capabilities. The processor 501 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0132] Computer device 500 can be a mobile electronic device.

[0133] It should be understood that the systems, apparatuses, and methods described in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, apparatuses, or modules, and may be electrical, mechanical, or other forms.

[0134] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0136] The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of diagnosing fibrosis based on KRTDAP expression level, characterized by, The method is performed by a computer and includes the following steps: Data Acquisition: Acquire data on the KRTDAP expression level in the sample of the subject to be tested. The KRTDAP expression level includes one or more of the following: nucleic acid expression level and protein expression level. Data processing: The KRTDAP expression level data is input into the constructed fibrosis diagnostic model, which diagnoses whether the subject has fibrosis based on the KRTDAP expression data; Output results; The fibrosis is oral submucosal fibrosis.

2. The method of claim 1, wherein, The steps for constructing the fibrosis diagnostic model are as follows: Data on KRTDAP expression levels are obtained, including one or more of the following: nucleic acid expression level and protein expression level; the KRTDAP expression level data are obtained from healthy subjects and fibrosis patients; the KRTDAP expression level data are input into a machine learning algorithm to construct a fibrosis diagnostic model.

3. The method of claim 1, wherein, The fibrosis diagnostic model obtains results using the following criteria: when the KRTDAP expression level is higher than a threshold, the subject is classified as having fibrosis; if the KRTDAP expression level is lower than a threshold, the subject is classified as not having fibrosis.

4. A system for diagnosing fibrosis based on KRTDAP expression levels, characterized by, The system includes: Data acquisition unit: used to acquire data on the expression level of KRTDAP in the sample of the subject to be tested, wherein the KRTDAP expression level includes one or more of the following: nucleic acid expression level, protein expression level; Data classification unit: used to classify and diagnose the fibrosis diagnostic model obtained by the construction method described in claim 2 based on the data obtained by the data acquisition unit, and to obtain the classification result of whether the subject to be tested has fibrosis; Result output unit: Used to output classification results; The fibrosis is oral submucosal fibrosis.

5. A computer device, computer readable storage medium or computer program product for diagnosing fibrosis based on KRTDAP expression level, comprising a computer program, characterized in that, The device includes: a memory and a processor, the memory being used to store program instructions; the processor being used to invoke the program instructions, which, when executed, implement the steps of the method for diagnosing fibrosis according to any one of claims 1-3; The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for diagnosing fibrosis according to any one of claims 1-3; When the computer program is executed by a processor, it implements the steps of the method for diagnosing fibrosis according to any one of claims 1-3; The fibrosis is oral submucosal fibrosis.

6. A method of computer-aided screening of drugs for treating oral submucous fibrosis based on KRTDAP, characterized in that, The oral submucosal fibrosis is diagnosed based on the method for diagnosing fibrosis according to claim 1, the method comprising: Data Acquisition: Acquire KRTDAP gene and / or protein data; Drug screening: Candidate drugs that can inhibit KRTDAP were obtained through computer-aided screening.

7. The method of claim 6, wherein, The computer-aided screening process includes: Obtain the KRTDAP gene sequence and / or protein structure; Based on the KRTDAP gene sequence and / or protein structure, substances with the potential to inhibit KRTDAP are screened in the database, including RNA drugs, antibodies, and small molecule compounds. The selected substances are subjected to molecular docking with KRTDAP to calculate their affinity / binding energy and obtain a score. The substances are then sorted according to the score, and the top n substances are selected as candidate drugs, where n is a natural number greater than or equal to 1.

8. The method of claim 6, wherein, The computer-aided screening process also includes: The candidate drugs described in claim 7 were subjected to inhibitory activity tests. The inhibition rate was calculated after the candidate drugs were mixed with KRTDAP protein solution, and drugs with KRTDAP inhibitory effects were screened.

9. A KRTDAP-based computer-aided system for screening drugs for treating oral submucous fibrosis, characterized by, The oral submucosal fibrosis is diagnosed based on the method for diagnosing fibrosis according to claim 1, and the system comprises: Data acquisition unit: Acquire KRTDAP gene and / or protein data; Drug screening unit: Candidate drugs that target and inhibit KRTDAP are obtained by using the computer-aided screening process described in claim 7 or 8.

10. A computer device, computer readable storage medium or computer program product for computer-aided screening of drugs for treating oral submucous fibrosis based on KRTDAP, comprising a computer program, characterized in that, The device includes: a memory and a processor, the memory being used to store program instructions; the processor being used to invoke the program instructions, and when the program instructions are executed, to implement the steps of the computer-aided method for screening drugs for treating oral submucosal fibrosis as described in claim 6. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the computer-aided method for screening drugs for treating oral submucosal fibrosis as described in claim 6. When the computer program is executed by the processor, it implements the steps of the method for computer-aided screening of drugs for treating oral submucosal fibrosis as described in claim 6.

Images