A method, system and apparatus for evaluating the effectiveness of ptt in the treatment of pancreatic cancer

Abstract

The application discloses a method, system and device for evaluating the treatment effect of PTT on pancreatic cancer. The application first discovers that PTT can treat pancreatic cancer by regulating the caspase-1 / GSDMD pathway, and discovers that the expression level of GSDMD is positively correlated with the drug resistance of pancreatic cancer cells to 5-fluorouracil, irinotecan, paclitaxel and cisplatin, which indicates that for patients with high expression of GSDMD, a local treatment method of photothermal therapy can be adopted instead of traditional chemotherapy. In addition, the application provides a method, system and device for evaluating the treatment effect of PTT on pancreatic cancer and a method, system and device for predicting the sensitivity of a pancreatic cancer patient to a chemotherapeutic drug, thereby assisting doctors in evaluating the treatment effect on the pancreatic cancer patient and guiding a clinician to formulate an individualized treatment plan for the patient.

Description

Technical Field

[0001] This invention belongs to the field of bioinformatics, specifically relating to a method, system, and device for evaluating the therapeutic effect of PTT on pancreatic cancer, and a method, system, and device for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs. Background Technology

[0002] Pancreatic cancer (PC) is one of the deadliest malignancies, with a 5-year survival rate of less than 10%. Despite advancements in modern diagnosis, surgery, and drug therapy, the prognosis for PC remains extremely poor due to its unique immunosuppressive tumor microenvironment (TME) and natural resistance to conventional radiotherapy, chemotherapy, and other treatments. In recent years, immunotherapy, including immune checkpoint inhibitors (ICIs), adoptive T-cell therapy (ACT), and tumor vaccines, has made some progress in the treatment of PC. However, for PC patients with high microsatellite instability (MSI-H), the objective response rate (ORR) in the single-arm KEYNOTE-158 trial was only 18.2%, significantly lower than the response rates for MSI-H cholangiocarcinoma (40.9%), small bowel (42.1%), gastric (45.8%), and endometrial (57.1%) cancers. Furthermore, the use of cancer vaccines and ACTs is limited due to difficulties in large-scale production and standardization.

[0003] Photothermal therapy (PTT) is a promising cancer treatment strategy due to its advantages such as short duration of action, few adverse reactions, good therapeutic effect, and minimal damage to normal tissues. Interventional PTT is a minimally invasive treatment that can effectively eradicate pancreatic tumors. Some studies have reported that PTT can control primary tumors and metastases, possibly due to the induction of immunogenic cell death (ICD) in tumor cells, the release of tumor antigens, and the subsequent enhancement of anti-tumor immune responses.

[0004] Therefore, accurately predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs and evaluating the therapeutic effect of PTT on pancreatic cancer patients plays a very important role in the selection of pancreatic cancer treatment, surgical design, and efficacy assessment. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, the present invention aims to provide a method, system, and device for evaluating the therapeutic effect of PTT on pancreatic cancer, and a method, system, and device for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides a method for evaluating the therapeutic effect of PTT on pancreatic cancer.

[0008] Furthermore, the method is performed by a computer, and the method includes the following steps:

[0009] Data Acquisition: Acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, and IL-1β;

[0010] Data processing: The expression data of the caspasae-1 substrate is input into the constructed PTT evaluation model, which predicts the therapeutic effect of PTT on pancreatic cancer patients based on the expression data of the caspasae-1 substrate;

[0011] Output results.

[0012] Furthermore, the expression data of the caspasae-1 substrate includes mRNA expression level data or protein expression level data.

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

[0014] Furthermore, the protein expression level data includes, but is not limited to, data obtained by Western blotting, immunohistochemistry, enzyme-linked immunosorbent assay (ELISA), and mass spectrometry.

[0015] Furthermore, the construction steps of the PTT evaluation model are as follows:

[0016] Expression data of caspasae-1 substrates are obtained, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, and IL-1β; the expression data of caspasae-1 substrates are obtained from untreated pancreatic cancer patients and pancreatic cancer patients after PTT treatment; the expression data of caspasae-1 substrates are input into a machine learning algorithm to construct a PTT evaluation model.

[0017] Furthermore, the PTT evaluation model obtains results using the following criteria:

[0018] When the expression levels of any one or more of the caspasae-1 substrate cleavage-type GSDMD, IL-18, and IL-1β are above a threshold, a classification result is obtained indicating that PTT is effective in treating pancreatic cancer patients; when the expression levels of any one or more of the caspasae-1 substrate cleavage-type GSDMD, IL-18, and IL-1β are below a threshold, a classification result is obtained indicating that PTT is ineffective in treating pancreatic cancer patients.

[0019] In some embodiments of the present invention, the preset threshold is a representative value of a normal sample from a pancreatic cancer population, including but not limited to the maximum value, the third quartile, and the mean. In some preferred embodiments of the present invention, the population sample includes 20 or more samples, such as 30, 50, 80, 100, 150, 200, 300, 500, or more.

[0020] Furthermore, the machine learning algorithm includes algorithmic models developed using various development tools.

[0021] 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.

[0022] 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.

[0023] Furthermore, the patients include humans and / or mammals.

[0024] Furthermore, the samples include blood, tissue, and pancreatic juice.

[0025] A second aspect of the present invention provides a system for evaluating the therapeutic effect of PTT on pancreatic cancer.

[0026] Furthermore, the system includes:

[0027] Data acquisition unit: used to acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, IL-1β;

[0028] Data classification unit: used to classify and predict whether the data obtained by the data acquisition unit is effective for the treatment of pancreatic cancer patients by the PTT evaluation model obtained by the construction method described in the first aspect of the present invention;

[0029] Result output unit: Used to output classification results.

[0030] A third aspect of the present invention provides a method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0031] Furthermore, the method is performed by a computer, and the method includes the following steps:

[0032] Data Acquisition: Obtain GSDMD expression data in pancreatic cancer patient samples;

[0033] Data processing: The expression data of GSDMD is input into the pre-constructed prediction model, which predicts the sensitivity of pancreatic cancer patients to chemotherapy drugs based on the expression data of GSDMD. The chemotherapy drugs are selected from any one of 5-fluorouracil, irinotecan, paclitaxel and cisplatin.

[0034] Output the prediction results.

[0035] Furthermore, the expression data of GSDMD includes mRNA expression level data or protein expression level data.

[0036] Furthermore, the mRNA expression level data includes, but is not limited to, data obtained by RT-PCR, qRT-PCR, in situ hybridization, and RNA sequencing.

[0037] Furthermore, the protein expression level data includes, but is not limited to, data obtained by Western blotting, immunohistochemistry, enzyme-linked immunosorbent assay (ELISA), and mass spectrometry.

[0038] Furthermore, the steps for constructing the prediction model are as follows:

[0039] GSDMD expression data were obtained from individuals sensitive to chemotherapy drugs and individuals insensitive to chemotherapy drugs, wherein the chemotherapy drugs were selected from any one of 5-fluorouracil, irinotecan, paclitaxel, and cisplatin; the GSDMD expression data were input into a machine learning algorithm to construct a prediction model.

[0040] Furthermore, the prediction model obtains prediction results using the following criteria: when the expression level of GSDMD is higher than a threshold, a classification result of pancreatic cancer patients being insensitive to chemotherapy drugs is obtained; when the expression level of GSDMD is lower than a threshold, a classification result of pancreatic cancer patients being sensitive to chemotherapy drugs is obtained.

[0041] A fourth aspect of the invention provides a system for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0042] Furthermore, the system includes:

[0043] Data acquisition module: used to acquire GSDMD expression data in pancreatic cancer patient samples;

[0044] Data classification module: used to classify and predict whether pancreatic cancer patients are sensitive to chemotherapy drugs by using the prediction model obtained by the construction method described in the third aspect of the present invention on the data obtained by the data acquisition module.

[0045] Output module: Used to output classification results.

[0046] Furthermore, the machine learning algorithm includes algorithmic models developed using various development tools.

[0047] 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.

[0048] 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.

[0049] A fifth aspect of the present invention provides a computer device and a computer-readable storage medium.

[0050] Furthermore, the device includes:

[0051] The invention includes a memory and a processor, wherein the memory is used to store program instructions; and the processor is used to invoke the program instructions, which, when executed, implement the method for evaluating the therapeutic effect of PTT on pancreatic cancer as described in the first aspect of the invention or the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs as described in the third aspect of the invention.

[0052] Furthermore, the computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for evaluating the therapeutic effect of PTT on pancreatic cancer as described in the first aspect of the present invention or the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs as described in the third aspect of the present invention.

[0053] Advantages and beneficial effects of the present invention:

[0054] This invention is the first to discover that PTT treats pancreatic cancer by regulating the caspase-1 / GSDMD pathway, and finds that GSDMD expression level is positively correlated with the resistance of PC cell lines to various chemotherapeutic drugs. Based on this, this invention provides a method, system, and device for evaluating the therapeutic effect of PTT on pancreatic cancer, as well as a method, system, and device for predicting the sensitivity of pancreatic cancer patients to chemotherapeutic drugs, thereby assisting doctors in evaluating the treatment effect of pancreatic cancer patients and guiding clinicians to develop individualized treatment plans for patients. Attached Figure Description

[0055] Figure 1 This is a schematic flowchart of the method for evaluating the therapeutic effect of PTT on pancreatic cancer provided by the present invention;

[0056] Figure 2 This is a schematic diagram of the system structure for evaluating the therapeutic effect of PTT on pancreatic cancer provided by the present invention;

[0057] Figure 3 This is a schematic flowchart of the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs provided by the present invention.

[0058] Figure 4 This is a schematic diagram of the system structure provided by the present invention for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs;

[0059] Figure 5 A schematic diagram of the structure of the computer device provided by the present invention;

[0060] Figure 6 Figure 1: Experimental results of PTT inducing pyroptosis in pancreatic cancer cell lines via the caspase-1 / GSDMD pathway; (a): Real-time morphological tracking of SW-1990-LUC cells after PTT treatment under a bright-field microscope (cells treated with ICG (100 μg / mL)). -1 ) processing, 1 W cm -2 (a) Irradiation for 5 min, white arrows indicate morphological features of pyroptosis (scale bar 100 μm); (b) Pyroptosis index of SW-1990-LUC cells at different time points after PTT; (c and d) LDH release in SW-1990-LUC and Pan02-luc cells after PTT; (e) Expression and cleavage of GSDMD and caspase-1 in SW-1990-LUC cells; (f and g) Morphology and pyroptosis index of SW-1990-LUC cells after PTT with or without VX-765 (a selective caspase-1 inhibitor) (scale bar 100 μm); (h and i) Release of IL-18 and IL-1β from SW-1990-LUC cells in different groups.

[0061] Figure 7 Figure 1 shows the correlation between GSDMD expression level and PC cell line resistance to chemotherapy drugs; (a) Resistance analysis: GSDMD gene expression was positively correlated with PC cell line resistance to 5-fluorouracil, irinotecan, paclitaxel, and cisplatin; (bc): H&E staining and immunohistochemical analysis of PDOs (patient-derived organoids) and anti-GSDMD antibody (scale bar 100 μm); (d): Drug sensitivity of PDOs to 5-fluorouracil, expressed as IC50. 50 As an indicator. Detailed Implementation

[0062] 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.

[0063] 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.

[0064] 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.

[0065] Figure 1 This is a schematic flowchart of the method for evaluating the therapeutic effect of PTT on pancreatic cancer provided by the present invention. Specifically, the method includes:

[0066] 101: Data Acquisition: Acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, IL-1β;

[0067] In some embodiments of the present invention, extensive and in-depth research has revealed that pancreatic cancer cells undergo pyroptosis after PTT treatment. Further exploration of the pyroptosis mechanism showed that the caspase-1 / GSDMD pathway was activated after PTT, and the expression level of cleaved GSDMD was significantly increased. In addition, the inflammatory cytokines IL-18 and IL-1β were activated, and the concentrations of IL-18 and IL-1β in the cell supernatant of the PTT group were also significantly increased. This suggests that cleaved GSDMD, IL-18, and / or IL-1β can serve as good biomarkers for evaluating the therapeutic effect of PTT on pancreatic cancer.

[0068] In some embodiments, the 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 patient may include adults or adolescents (e.g., children). Furthermore, the patient may refer to any living organism that can benefit from the PTT described herein, 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 including rodents, such as rats, mice, and guinea pigs. Examples of non-mammals include, but are not limited to, birds, fish, etc.

[0069] In the context of this invention, the term "sample" as used refers to a composition obtained from or derived from a patient / subject 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 patient / subject 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.

[0070] In a specific embodiment of the present invention, the samples included the human pancreatic adenocarcinoma cell line SW1990-LUC and the mouse pancreatic cancer cell line Pan02-LUC. The human pancreatic adenocarcinoma cell line SW1990-LUC was purchased from Xuan Yi Biotechnology Service Center (Shanghai, China) and cultured in RPMI-1640 medium (8122269, Gibco). The mouse pancreatic cancer cell line Pan02-LUC was purchased from IMMOCELL (Xiamen, Fujian, China) and cultured on Dulbecco's modified Eagle medium (DMEM; 11965092, Gibco).

[0071] In one embodiment of the present invention, indocyanine green (ICG, Dandong Yichuang Pharmaceutical Co., Ltd., China) was selected as the photosensitizer for the PTT. This photosensitizer has good biocompatibility and has been approved by the FDA for clinical use. An 808 nm laser source (MDL-H-808nm-2W-13040029, Changchun New Industrial Optoelectronic Technology Co., Ltd.) was used for the PTT. The output power density was set to 1 W cm⁻¹. -2 Cells in the ICG group and the PTT group were compared with ICG (100 μg / mL). -1 Incubate at 37°C for 6 h. Wash three times with PBS, add normal culture medium, and then irradiate with or without near-infrared laser for 5 min (λ = 808 nm, 1 W cm⁻¹). -2 ).

[0072] In some embodiments, caspasae-1 substrate expression data can be detected by applying methods well known in the art. For example, caspasae-1 substrate expression level data can be obtained at the nucleic acid level by measuring the amount of RNA, mRNA, or any other RNA species using methods well known in the art, including digital PCR and real-time (RT) quantitative or semi-quantitative PCR, fluorescence activated cell sorting (FACS), and in situ hybridization.

[0073] In other implementations, caspasae-1 substrate expression level data can also be obtained by measuring protein expression levels, including mass spectrometry-based quantitative proteomics, immunoassays, Western blotting, 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.

[0074] In a specific embodiment of the present invention, the expression levels of lysed GSDMD, IL-18, and IL-1β were obtained using the following method: GSDMD expression levels were detected by Western blotting. Cells were washed with cold PBS, lysed in IP buffer (20 mM pH 7.5 Tris, 150 mM NaCl, 1% Triton X-100), and a protease inhibitor (Cocktail, Beyotime Biotechnology, China) was added. Total cellular protein was extracted, and protein concentration was determined using the BCA method (P0012, Beyotime Biotechnology, China). Equal amounts of protein were separated by SDS-PAGE and transferred to a PVDF membrane (Millipore, Billerica, MA, USA). Detection was performed using probes with anti-DFNA5 / GSDME antibody (1:1000, ab215191, Abcam, Cambridge, CB2 0AX, UK), anti-caspase-3 antibody (1:1000, 9662, Cell Signaling Technology, Danvers, MA, USA), anti-GSDMD antibody (1:1000, YT7991, Immunoway Biotechnology, Plano, TX, USA), anti-caspase-1 antibody (1:1000, 2225, Cell Signaling Technology), anti-p-IRF3 antibody (1:1000, 4947, CST), and anti-β-Actin antibody (1:1000, HX1827, Huaxing Biotechnology, China). The ratio of mouse and rabbit IgG recognized by the enzyme-labeled secondary antibody was 1:5000. Immunoblotting was performed using an ECL reaction system and gel imaging system (Tanon, China). The release of mature IL-1β and IL-18 from cell culture supernatants was detected using the IL-1β ELISA kit (EH001) and the IL-18 ELISA kit (EH047). Procedure followed the manufacturer's instructions. Absorbance measurements were performed using a microplate reader (Bio-Rad Laboratories, USA) at 450 nm with a calibration wavelength of 655 nm.

[0075] In one embodiment of this invention, we demonstrated that PTT can induce pyroptosis in pancreatic cancer cells. We irradiated ICG-treated SW-1990-LUC and Pan02-luc cells with near-infrared light (808 nm) to observe whether PTT could induce pyroptosis. First, we explored the conditions for PTT and the temperature rise curves corresponding to different ICG concentrations. The results showed that when the ICG solution concentration was 100 μg / mL...-1 The irradiation power density is 1 W cm⁻¹ -2 The temperature was maintained at 42℃~48℃. Afterwards, the morphology of SW-1990-LUC and Pan02-luc cells in different groups was observed. Five minutes after irradiation, the PTT group showed typical pyroptosis morphological features such as cell swelling and large bubbles appearing on the plasma membrane, suggesting that PTT induced pyroptosis. Following PTT, we also recorded real-time morphological changes in SW-1990-LUC cells. Figure 6 a) The pyroptosis index was used to evaluate the dynamic pyroptosis-inducing ability of PTT in vitro. For example... Figure 6 As shown in b, the percentage of pyroptotic cells in PTT-treated SW-1990-LUC cells increased significantly over time. As previously mentioned, cell death puncturing the cell membrane (pyroptosis) is an efficient combination of apoptosis and necrosis, occurring much faster than other programmed cell death processes. Lactate dehydrogenase (LDH) release was detected using supernatants from SW-1990-LUC and Pan02-luc cells. Figure 6 As shown in c, the LDH release in SW-1990-LUC cells of the PTT group was significantly higher than that in the control group (25.25% vs. 6.55%; n=3; P<0.0001) and the ICG group (25.25% vs. 8.75%; n=3; P = 0.0001). Similar results were obtained in Pan02-luc cells. Figure 6 d) The LDH release in the PTT group was significantly higher than that in the control group (22.81% vs. 4.70%; n=3; P<0.0001) and the ICG group (22.81% vs. 8.24%; n=3; P<0.0001). These results collectively demonstrate that PTT induces pyroptosis in pancreatic cancer cell lines.

[0076] In another embodiment of the invention, we demonstrated that PTT-triggered pyroptosis depends on the caspase-1 / GSDMD pathway. Based on current research on pyroptosis pathways, the most common pathways are the GSDMD-dependent classical inflammasome pathway and the GSDME-dependent non-classical pathway. Therefore, we investigated the expression and cleavage of GSDMD and GSDME in pancreatic cancer cell lines after PTT. RT-qPCR detected GSDMA, GSDMB, GSDMC, GSDMD, and GSDME in SW-1990-LUC cells, with GSDMD expression significantly higher than GSDMA (P=0.0002), GSDMB (P<0.0001), GSDMC (P<0.0001), and GSDME (P<0.0001). Secondly, as... Figure 6As shown in Figure e, full-length GSDMD and GSDME (GSDMD-fl and GSDME-fl) were detected in SW-1990-LUC cells. The expression level of GSDMD-fl was lower in the PTT group than in the control group and the ICG group, while the expression level of cleaved GSDMD (GSDMD-n) was significantly higher. There was no difference in GSDME-fl expression among the three groups, and cleaved GSDME (GSDME-n) was not detected. These data indicate that GSDMD, rather than GSDME, was cleaved in pancreatic cancer cells after PTT.

[0077] GSDMD has been identified as a specific substrate for caspase-1. Western blotting was used to detect caspase-1 expression and cleavage. Figure 6 As shown in Figure e, cleaved caspase-1 was detected only in the PTT group, indicating that caspase-1 was cleaved in pancreatic cancer cells after PTT. To further analyze the role of caspase-1 in PTT-triggered pyroptosis, we applied the caspase-1 selective inhibitor VX-765 prior to PTT. Figure 6 As shown in f and g, the pyroptosis index 60 min after PTT was significantly reduced after VX-765 pretreatment (79.77% vs. 7.77%, P=0.0008). These results confirm that caspase-1 is involved in PTT-induced pyroptosis in pancreatic cancer.

[0078] In the GSDMD-dependent classical inflammasome pathway, cleaved caspase-1 activates not only GSDMD but also the inflammatory cytokines IL-18 and IL-1β, which are subsequently cleared from the cells. Therefore, the levels of mature IL-18 and IL-1β in the cell supernatant are also an indicator of the caspase-1 / GSDMD pathway. In this study, the concentrations of IL-18 and IL-1β in the cell supernatant of the PTT group were significantly higher than those in the control group and the ICG group. Figure 6 The above results indicate that PTT-triggered pyrode death depends on the caspase-1 / GSDMD pathway.

[0079] 102: Data processing: The expression data of the caspasae-1 substrate is input into the constructed PTT evaluation model, which predicts the therapeutic effect of PTT on pancreatic cancer patients based on the expression data of the caspasae-1 substrate;

[0080] In some embodiments of the present invention, the method for constructing the PTT evaluation model is known to those skilled in the art and can be implemented and realized in different ways as a step of associating the expression level of caspasae-1 substrate with a certain probability or risk.

[0081] In the context of this invention, the term "machine learning" refers to the use of computers to simulate or implement human learning activities. Technicians typically use various development tools to build machine learning algorithmic models. These 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. The algorithmic 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, or random forest models.

[0082] In one embodiment, after constructing the PTT evaluation model, the effectiveness of the model can be evaluated using ROC curve analysis.

[0083] 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.

[0084] 103: Output the prediction results.

[0085] Figure 2 This is a schematic diagram of the system structure for evaluating the therapeutic effect of PTT on pancreatic cancer, as provided by the present invention.

[0086] 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.

[0087] Data acquisition unit: used to acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, IL-1β;

[0088] Data classification unit: used to classify and predict whether the data obtained by the data acquisition unit is effective for the treatment of pancreatic cancer patients by the PTT evaluation model obtained by the construction method described in the first aspect of the present invention;

[0089] Result output unit: Used to output classification results.

[0090] The system may be a user's electronic device or a computer system remotely located relative to that electronic device.

[0091] Figure 3 This is a schematic diagram of the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs provided by the present invention.

[0092] 301: Data Acquisition: Obtain GSDMD expression data in pancreatic cancer patient samples;

[0093] In one embodiment of the invention, we analyzed the correlation between GSDMD expression levels and the response to five clinically used pancreatic cancer treatments: 5-fluorouracil, irinotecan, paclitaxel, gemcitabine, and cisplatin. Figure 7 As shown in figure a, GSDMD gene expression was positively correlated with resistance to 5-fluorouracil, irinotecan, paclitaxel, and cisplatin in pancreatic cancer cell lines, but not with response to gemcitabine. These results suggest that overexpression of GSDMD in pancreatic cancer may indicate increased resistance to chemotherapy.

[0094] In another embodiment of the invention, we established patient-derived organoids for validation. The establishment process of patient-derived organoids is as follows: Immediately after dissection, tumor tissue was immersed in transfer medium at a temperature of 4°C. After thorough washing with washing buffer (KS100121, Daxiang Biotech), the washed tissue was minced and bound with a dissociation agent (KS100123, Daxiang Biotech). After digestion, cells were collected, suspended, and filtered. The resulting filtrate was centrifuged to collect cells, and then the cells were resuspended in pancreatic cancer organoid culture medium (OC100138, Daxiang Biotech) and 3D matrix (DatrixGel™, Daxiang Biotech). The cell suspension was seeded into 24-well plates for organoid culture. All organoid models were routinely tested for mycoplasma. H&E staining and WES staining were performed using tumor tissue and PDO for validation. PDOs were established using tumor tissue with differential GSDMD expression, named PDO A and PDO B, respectively. Subsequently, we used patient-derived organoids to test 5-fluorouracil drug sensitivity and found that PDO A IC 50 Higher levels of GSDMD expression ( Figure 7 d). These results indicate that GSDMD is a biomarker for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0095] 302: Data Processing: Input the expression data of GSDMD into the constructed prediction model, which predicts the sensitivity of pancreatic cancer patients to chemotherapy drugs based on the expression data of GSDMD, wherein the chemotherapy drugs are selected from any one of 5-fluorouracil, irinotecan, paclitaxel and cisplatin;

[0096] In some embodiments of the present invention, the methods for constructing the prediction model are known to those skilled in the art and can be implemented and realized in different ways to associate the GSDMD expression level with a certain probability or risk.

[0097] In one embodiment, after constructing a predictive model, the diagnostic efficacy of the predictive model can be evaluated using ROC curve analysis.

[0098] 303: Output the prediction results.

[0099] Figure 4 This is a schematic diagram of the system structure provided by the present invention for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0100] The system is programmed or otherwise configured to include a data acquisition module 401, a data classification module 402, and an output module 403.

[0101] Data acquisition module 401: used to acquire GSDMD expression data in pancreatic cancer patient samples;

[0102] Data classification module 402: used to classify and predict the data obtained by the data acquisition module through the prediction model obtained by the construction method described in the third aspect of the present invention, and to obtain the classification result of whether pancreatic cancer patients are sensitive to chemotherapy drugs;

[0103] Output module 403: Used to output classification results

[0104] Figure 5 A schematic diagram of the structure of the computer device provided by the present invention.

[0105] 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 method described above for evaluating the effect of PTT on pancreatic cancer treatment or the method described above for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs.

[0106] 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.

[0107] Computer device 500 can be a mobile electronic device.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural or procedural changes 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 scope of patent protection of this application.

Claims

1. A method for evaluating the therapeutic effect of PTT on pancreatic cancer, characterized in that, The method is performed by a computer and includes the following steps: Data Acquisition: Acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, and IL-1β; Data processing: The expression data of the caspasae-1 substrate is input into the constructed PTT evaluation model, which predicts the therapeutic effect of PTT on pancreatic cancer patients based on the expression data of the caspasae-1 substrate; Output results; The PTT evaluation model obtains results using the following criteria: When the expression levels of any one or more of the caspasae-1 substrate cleavage-type GSDMD, IL-18, and IL-1β are above a threshold, a classification result is obtained indicating that PTT is effective in treating pancreatic cancer patients; when the expression levels of any one or more of the caspasae-1 substrate cleavage-type GSDMD, IL-18, and IL-1β are below a threshold, a classification result is obtained indicating that PTT is ineffective in treating pancreatic cancer patients.

2. The method according to claim 1, characterized in that, The steps for constructing the PTT evaluation model are as follows: Expression data of caspasae-1 substrates are obtained, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, and IL-1β; the expression data of caspasae-1 substrates are obtained from untreated pancreatic cancer patients and pancreatic cancer patients after PTT treatment; the expression data of caspasae-1 substrates are input into a machine learning algorithm to construct a PTT evaluation model.

3. A system for evaluating the therapeutic effect of PTT on pancreatic cancer, characterized in that, The system includes: Data acquisition unit: used to acquire expression data of caspasae-1 substrates in pancreatic cancer patient samples after PTT treatment, wherein the caspasae-1 substrates include one or more of the following: cleaved GSDMD, IL-18, IL-1β; Data classification unit: used to classify and predict whether the data obtained by the data acquisition unit is effective for the treatment of pancreatic cancer patients by the PTT evaluation model obtained by the construction method described in claim 2; Result output unit: Used to output classification results.

4. A method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs, characterized in that, The method is performed by a computer and includes the following steps: Data Acquisition: Obtain GSDMD expression data in pancreatic cancer patient samples; Data processing: The expression data of GSDMD is input into the pre-constructed prediction model, which predicts the sensitivity of pancreatic cancer patients to chemotherapy drugs based on the expression data of GSDMD. The chemotherapy drugs are selected from any one of 5-fluorouracil, irinotecan, paclitaxel and cisplatin. Output the prediction results; The prediction model obtains prediction results using the following criteria: when the expression level of GSDMD is higher than the threshold, the pancreatic cancer patient is classified as insensitive to chemotherapy drugs; when the expression level of GSDMD is lower than the threshold, the pancreatic cancer patient is classified as sensitive to chemotherapy drugs.

5. The method according to claim 4, characterized in that, The steps for constructing the prediction model are as follows: obtaining GSDMD expression data; the GSDMD expression data comes from patients sensitive to chemotherapy drugs and patients insensitive to chemotherapy drugs, and the chemotherapy drugs are selected from any one of 5-fluorouracil, irinotecan, paclitaxel and cisplatin; the GSDMD expression data is input into a machine learning algorithm to construct a prediction model.

6. A system for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs, characterized in that, The system includes: Data acquisition module: used to acquire GSDMD expression data in pancreatic cancer patient samples; Data classification module: used to classify and predict whether pancreatic cancer patients are sensitive to chemotherapy drugs by classifying the data obtained by the data acquisition module through the prediction model obtained by the construction method described in claim 5; Output module: Used to output classification results.

7. The method according to claim 2 or claim 5, characterized in that, The machine learning algorithms include algorithmic models developed using various development tools.

8. The method according to claim 7, characterized in that, 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.

9. The method according to claim 7, characterized in that, 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.

10. A computer device and a computer-readable storage medium, characterized in that, The device includes: A memory and a processor, wherein the memory is used to store program instructions; the processor is used to invoke the program instructions, which, when executed, implement the method for evaluating the efficacy of PTT in pancreatic cancer treatment as described in any one of claims 1-2 or the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs as described in any one of claims 4-5; The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for evaluating the therapeutic effect of PTT on pancreatic cancer as described in any one of claims 1-2, or the method for predicting the sensitivity of pancreatic cancer patients to chemotherapy drugs as described in any one of claims 4-5.

Images