A method, system, device for evaluating the efficacy of a drug for treating sepsis encephalopathy

Abstract

The application discloses a method, system and device for evaluating the curative effect of a drug for treating sepsis encephalopathy. The method is based on protein expression data of p-JNK, p-c-JUN, p-ATF2, c-JUN, Bax and Bcl-2 to evaluate the treatment effect of a cell penetrating peptide on sepsis encephalopathy, thereby providing further guidance for optimizing the treatment of sepsis encephalopathy by the cell penetrating peptide and research, and being beneficial to guiding a clinician to formulate an individualized treatment plan for a patient.

Description

Technical Field

[0001] This invention belongs to the field of intelligent medicine and relates to a method, system, and apparatus for evaluating the efficacy of drugs for treating sepsis encephalopathy. Background Technology

[0002] Sepsis is defined as life-threatening organ dysfunction caused by a dysregulated host response to infection, and is considered one of the leading causes of morbidity and mortality in intensive care units (ICUs) worldwide. As a severe systemic inflammatory response, sepsis is also closely linked to the global disease burden. When microorganisms invade the body, they trigger a systemic immune response to fight off the invading microbes, leading to an inflammatory response. This instinctive protective response can promptly identify, eliminate, and control the infection locally. However, the overactivation of the immune response during sepsis leads to sequential damage to host cells and tissues, causing dysfunction and life-threatening multi-organ failure. The pathophysiology of sepsis is defined as an early, sustained, high-intensity inflammatory state followed by a prolonged state of immunosuppression. Both phases can result in high mortality rates, with the early high mortality attributed to a massive inflammatory response (also known as an inflammatory cytokine storm). The excessive release of inflammatory mediators during a cytokine storm leads to significant endothelial cell damage, resulting in the disruption of the protective barrier, vasodilation, activation of coagulation pathways, platelet aggregation and adhesion, and mitochondrial dysfunction, among other things. Excessive inflammatory and immune dysregulation, and its consequences, ultimately lead to microvascular thrombosis, hypotension, impaired cellular function, insufficient local perfusion, tissue hypoxia, and progressive tissue damage, eventually resulting in refractory shock and multiple organ failure. Cardiovascular dysfunction, acute lung injury and acute respiratory distress syndrome, acute kidney injury, liver dysfunction, central nervous system dysfunction, and related encephalopathy are well-known complications of sepsis, and their underlying mechanisms have attracted considerable attention. These abnormal changes and dysfunctions in tissues and organs collectively contribute to the high mortality rate of sepsis.

[0003] As a major complication of sepsis, sepsis-associated encephalopathy (SAE) manifests as a range of brain dysfunctions, from mild confusion to coma. A large-scale retrospective analysis of a multicenter database showed that 53% (1341 / 2351) of sepsis patients presented with delusions and coma upon ICU admission. This study also indicated that older patients with a history of chronic alcoholism, neurological disorders, prior cognitive impairment, and long-term use of psychoactive drugs may be more prone to SAE. Furthermore, complications including acute renal failure, metabolic disorders, glycemic instability, hypercapnia, and hypernatremia may be risk factors for SAE incidence. Overall, sepsis patients with brain dysfunction appear to have a heavier systemic disease burden and are associated with higher mortality rates. However, whether these systemic diseases and disturbances should be considered confounding factors or diagnostic indicators of SAE is debatable. Researchers generally agree that patients with septic shock are more prone to brain dysfunction. Hypoperfusion, hypoxia, microthrombosis, and internal environment disturbances are considered major causes of multiple organ dysfunction, including brain-related disorders. Guidelines such as the "Surviving Sepsis Campaign" recommend early goal-directed therapy and organ replacement therapy to reverse shock and protect organs. However, given the fragility and irreplaceability of the brain (compared to the kidneys and liver), specific neuroprotective interventions are urgently needed. Although the understanding and research on sepsis-associated encephalopathy (SAE) continues, there is still no specific, evidence-based treatment for SAE in patients. Considering that SAE is secondary to sepsis and does not involve a direct central nervous system infection, the focus of treatment remains on preventing SAE by treating sepsis and suppressing systemic inflammatory response syndrome. Statistics from the United States in 1979-2000 show that bacterial infections accounted for 90% of all sepsis cases, with Gram-positive bacteria accounting for 52%, Gram-negative bacteria for 38%, and multibacterial and fungal infections accounting for 4.7% and 4.6% of all cases, respectively. Furthermore, by definition, viruses can also cause sepsis; COVID-19 has been found to cause critical conditions such as respiratory failure, septic shock, and multiple organ dysfunction in approximately 5% of patients. Therefore, both broad-spectrum and narrow-spectrum antibiotics are essential. Other treatments for sepsis and septic shock, such as fluid resuscitation, administration of vasoactive drugs, glycemic control, and nutritional support, are also recommended.

[0004] In sepsis management, bioactive peptides are considered to possess both therapeutic and protective properties against sepsis, thus becoming a novel and effective treatment option. Among different classes of bioactive peptides, antimicrobial peptides (AMPs) are naturally occurring peptides capable of resisting microbial infections and their associated complications, such as sepsis. Due to their unique antimicrobial mechanism of action, potent antimicrobial efficacy, minimal drug residues, and simplicity of production and modification, AMPs have shown great potential as a promising alternative to antibiotics for decades. Furthermore, AMPs exhibit significantly lower levels of antimicrobial resistance due to their multiple mechanisms not addressed by traditional antibiotics. In addition, anti-inflammatory peptides (AIPs) have shown beneficial effects in bacterial infections and sepsis. The use of these peptides has been shown to reduce inflammation by targeting various nodes in the sepsis inflammatory cascade, thereby reducing the extent of sepsis-related tissue and organ damage and achieving effective therapeutic effects. Therefore, the uniqueness and potential of AMPs and AIPs in bacterial infections and sepsis make them promising research areas for developing new therapies. However, due to the problems with bioavailability and tolerability of bioactive peptides, improving their efficacy and safety is currently a hot research topic. Summary of the Invention

[0005] The purpose of this invention is to provide a method for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-associated encephalopathy. This method can effectively evaluate the efficacy of cell-penetrating peptides on sepsis-associated encephalopathy, thereby providing further guidance for optimizing the treatment and research of cell-penetrating peptides on sepsis-associated encephalopathy.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: According to a first aspect of the present invention, the present invention provides a method for evaluating the therapeutic effect of cell-penetrating peptides on patients with sepsis-associated encephalopathy, the method being performed by a computer, the method comprising the following steps: Protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 were collected from patient samples to be evaluated. The collected protein expression data is input into the constructed efficacy evaluation model, which evaluates the therapeutic effect of the cell-penetrating peptide on the patients to be evaluated based on the protein expression data. Output evaluation results; The amino acid sequence of the cell-penetrating peptide is FLKNCEYGRKKRRQRRR.

[0007] Furthermore, the method for constructing the efficacy evaluation model is as follows: obtain the protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in samples of patients with sepsis-associated encephalopathy who have not been treated with the cell-penetrating peptide and patients with sepsis-associated encephalopathy who have been treated with the cell-penetrating peptide, and input the protein expression data into a machine learning algorithm to construct the efficacy evaluation model.

[0008] Furthermore, the efficacy evaluation model obtains results using the following criteria: when the protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, and Bax are below a threshold, the cell-penetrating peptide is classified as effective in treating the patients to be evaluated; when the protein expression data of Bcl-2 is below a threshold, the cell-penetrating peptide is classified as ineffective in treating the patients to be evaluated.

[0009] Furthermore, the machine learning algorithm includes algorithmic models developed using various development tools.

[0010] Furthermore, the development tools include: 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.

[0011] Furthermore, the algorithm models include: linear regression model, logistic regression model, Lasso regression model, Ridge regression model, linear discriminant analysis model, nearest neighbor model, decision tree model, perceptron model, neural network model, support vector machine model, Naive Bayes model, AdaBoost model, GBDT model, XGBoost model, LightGBM model, CatBoost model, and random forest model.

[0012] According to a second aspect of the present invention, the present invention provides a system for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-related encephalopathy, the system comprising: Information acquisition module: used to collect protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in the patient samples to be evaluated; The efficacy evaluation module is used to input the protein expression data collected in the information collection module into the efficacy evaluation model obtained by the construction method described in claim 2, and to obtain the classification results of whether the cell membrane-penetrating peptide is effective in the treatment of the patient to be evaluated; Output module: Used to output classification results; The amino acid sequence of the cell-penetrating peptide is FLKNCEYGRKKRRQRRR.

[0013] According to a third aspect of the present invention, a computer device is provided, the device comprising: a memory and a processor; the memory being used to store a computer program; and the processor executing the computer program to implement the methods described above.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described above.

[0015] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program, characterized in that the computer program, when executed by a processor, implements the methods described above. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the system structure provided in an embodiment of the present invention; Figure 3 A schematic diagram of a computer device provided in an embodiment of the present invention; Figure 4 The results of successfully establishing a mouse model of sepsis-associated encephalopathy are shown in the figure. (A) Survival rate of mice 72 h after CLP modeling (n=20); (B) Sepsis score (MSS) of mice (n=10); (C) Postoperative rectal temperature measurement of mice (n=6); (D) Detection of mRNA levels of inflammatory factors in the hippocampus of mice 24 h after surgery (n=6); (E) Immunofluorescence staining of early apoptosis factor Caspase-3 in the hippocampus region of mouse brain tissue sections 24 h after surgery (n=3). All data are mean ± standard deviation. Compared with the Sham group, *P < 0.05 and ****P < 0.0001. Figure 5The results of the toxicity test of FLKNCE-Tat short peptide in mice are shown in the figure. (A) Record of body weight change of mice in each group after 7 consecutive days of administration (n=6); (BI) Blood biochemical indicators of liver and kidney function in mice (n=6); ALT: Alanine Aminotransferase; AST: Aspartate Aminotransferase; ALP: Alkaline Phosphatase; TBIL: Total Bilirubin; TP: Total Protein; ALB: Albumin; CRE: Creatinine; BUN: Blood Urea Nitrogen; (J) Comparison of histopathological H&E staining of heart, liver, lung and kidney tissues of normal mice and the FLKNCE-Tat treatment group treated with 50 mg / kg dose for 7 consecutive days of intravenous injection (n=6). Figure 6 The results show that FLKNCE-Tat alleviated CLP-induced brain injury in CLP-induced septic mice. (A) Survival rate of the five groups of mice at 72 h (n=20); (B) Comparison of sepsis (MSS) scores of the five groups of mice at 24 h post-surgery (n=10); (CE) Detection of serum levels of pro-inflammatory cytokines IL-1β, TNF-α, and IL-6 in the five groups of mice at 24 h post-surgery (n=6); (F) and (G) H&E staining and statistical analysis of hippocampal tissue sections (CA1 region) of the five groups of mice at 24 h post-surgery (n=6); Scale bar: 200µm; 50µm. (H) and (I) Nissl staining and statistical analysis of hippocampal tissue sections (CA1 region) of the five groups of mice at 24 h post-surgery (n=6); Scale bar: 200µm; 50µm. All data are expressed as mean ± standard deviation; *P < 0.05, **P < 0.01, ***P < 0.001 and ****P < 0.0001; Figure 7The transcriptome sequencing revealed differentially expressed genes and enriched pathways in the brain tissue of CLP mice after FLKNCE-Tat treatment. (A) A volcano plot shows the differentially expressed genes between the CLP group and the FLKNCE-Tat treatment group (n=4). (B) A heatmap shows the significant differential expression patterns of DEGs between the two groups (n=4). (C) A network diagram of gene-protein interactions with JUN in DEG genes. (D) and (E) GO enrichment and KEGG enrichment analysis plots of DEGs interacting with JUN. (F) and (G) GSEA analysis showed significant upregulation of the Toll-like receptor signaling pathway and the cytokine-cytokine receptor interaction pathway. (H) mRNA expression levels of genes enriched in the Toll-like receptor signaling pathway and cytokine-cytokine receptor interaction pathway (CCL3, CCL5, CD40, IRF7, CD86, FOS, IL1A, and CCR2) in the brain tissue of mice in both groups 24 h post-surgery (n=6). All data are presented as mean ± standard deviation. *P < 0.05, **P < 0.01, ***P < 0.001, and ns indicate no statistical difference; Figure 8 The graphs show the results of FLKNCE-Tat inhibiting the activation of the JNK / c-Jun / ATF2 signaling pathway and alleviating SAE. (A) and (B) show immunoblot images and quantitative analysis statistics of p-JNK / JNK protein in the hippocampus of three groups of mice (n=6). (C) and (D) show immunoblot images and quantitative analysis statistics of p-ATF2 / ATF2 protein in the hippocampus of three groups of mice (n=6). (E) shows immunoblot images and quantitative analysis statistics of c-JUN protein in the hippocampus of three groups of mice (n=6). (F) shows immunoblot images and quantitative analysis statistics of pc-JUN protein in the hippocampus of three groups of mice (n=6). (G) and (H) show immunoblot images and quantitative analysis statistics of Bax and Bcl-2 proteins in the hippocampus of three groups of mice (n=6). All data are presented as mean ± standard deviation. *P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001. Detailed Implementation

[0017] 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.

[0018] 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 S101, S102, 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.

[0019] 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.

[0020] Figure 1 The flowchart of the method for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-associated encephalopathy provided by the present invention is shown below. intention Specifically, the method includes: S101: Collect protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in the patient samples to be evaluated; 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 cell-penetrating peptides described herein, preferably mammals (e.g., humans or non-humans). 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.

[0021] In a specific embodiment of the present invention, the patient is a non-human animal model, specifically a sepsis mouse model prepared by the cecum ligation and puncture (CLP) method.

[0022] All research protocols described in this article were approved by the Laboratory Animal Ethics Committee of Tianjin Medical University General Hospital, and mice were handled in strict accordance with ethical requirements. The experimental animals used in this study were healthy adult male C57BL / 6J mice (6-8 weeks old, 20-25 g), carefully selected from the Laboratory Animal Center of the Academy of Military Medical Sciences in Beijing. The mice were housed in an environment meeting the following conditions: room temperature of 20-25°C, relative humidity of 55-65%; light-dark cycle twice daily; allowing the mice to acclimatize to their new environment for one week; and free access to food and water.

[0023] The procedure for establishing a mouse model of sepsis using the cecum ligation and puncture (CLP) method was as follows: After mice had fully acclimatized to the laboratory environment for one week, they were anesthetized with isoflurane and placed in a prone position. The skin was disinfected, and a 1 cm incision was made in the abdomen to expose the cecum, which was then ligated at 35%. The cecum was then punctured twice with a 21-gauge needle, and approximately 0.3 mL of cecum contents were squeezed out using sterile forceps. The cecum and squeezed contents were then returned to the abdominal cavity, and the abdominal muscles and tissues were sutured using specialized surgical suture needles and sutures. The sham-operated group underwent the same surgical procedure, but without cecum ligation and puncture; only exploratory laparotomy was performed. After model establishment, 1 mL of room-temperature saline was injected subcutaneously into the experimental animals, and lidocaine cream (Cat# H20063466, Ziguang, Beijing) was applied to the suture wound to relieve postoperative pain. The temperature of the postoperative mouse housing environment was controlled at 20-25°C, and a warming blanket was used to keep the mice warm to prevent hypothermia.

[0024] Experimental mice were randomly divided into 5 groups: sham surgery group, sepsis (CLP) group, and CLP + different doses of peptide treatment groups (CLP + 5 mg / kg, CLP + 10 mg / kg, CLP + 20 mg / kg). Mice in the CLP + different doses of peptide treatment groups received intravenous injections of cell-penetrating peptides via the tail vein at 2 h and 6 h after modeling, while the other groups received an equal volume of physiological saline. Animals in the CLP group underwent cecal ligation and perforation, while mice in the Sham group only underwent exploratory laparotomy. Twenty mice were randomly selected from each group, and survival rates were recorded and analyzed at 12 h, 24 h, 48 h, and 72 h post-surgery. Twenty mice from each group were randomly selected for sepsis scoring (MSS score). Mice anesthetized with an overdose of isoflurane after CLP or sham surgery were euthanized by cervical dislocation. Serum and brain tissue samples were collected, and serum levels of cytotoxic cytokines IL-1β, IL-6, and TNF-α were measured using ELISA. Brain tissue was collected from six mice in each group for sectioning, H&E staining, and Nissl staining to observe the degree of neuronal damage. The polypeptide sequence (cell-penetrating peptide, FLKNCE-Tat) was FLKNCEYGRKKRRQRRR.

[0025] The results showed that, compared with the sham surgery group, the survival rate of mice in the CLP group was significantly lower within 73 hours. Figure 4 A, P < 0.05), and CLP group mice showed typical deterioration of sepsis physiological indicators, including an increase in sepsis score (MSS score). Figure 4 B, P < 0.05), body temperature decreased 24 hours postoperatively ( Figure 4 C, P < 0.05. Meanwhile, the release of inflammatory factors in the hippocampus of CLP group mice was significantly higher than that in Sham group (C, P < 0.05). Figure 4 D, P < 0.05. Furthermore, fluorescence staining of early apoptosis factor Caspase-3 in mouse brain tissue sections showed that, compared with the Sham group, the CLP group mice exhibited a large number of apoptotic events in hippocampal neurons (D, P < 0.05). Figure 4 E, P < 0.05). The above experimental results show that a mouse model of sepsis-related brain injury has been successfully established.

[0026] The statistical survival rate analysis method used in this invention is as follows: The survival rates of the two groups of experimental mice were recorded and analyzed at different time points (12h, 24h, 48h, and 72h) within 72 hours post-surgery. Under the same environment as before modeling, the two groups of mice with sepsis were housed in four different cages, and the survival status of both groups was observed and recorded (if any mouse died, its body was removed and disposed of). The experimental mice were continuously observed for 72 hours, and their survival status was analyzed and statistically analyzed (n=20).

[0027] The sepsis score (MSS) used in this invention to assess the morbidity of mice after CLP modeling is as follows: Mice are grouped according to their physical characteristics, level of consciousness, activity level, stimulus response, ocular manifestations, respiratory rate, and respiratory quality (each indicator has a score range of 0-4 points) 24 hours after modeling. Mice that die within 6 hours of CLP modeling are excluded from subsequent experiments.

[0028] This invention uses real-time quantitative PCR to study the release of inflammatory factors. The operation steps include: (1) Extraction of RNA from hippocampal tissue Weigh 10-20 mg of hippocampal tissue and add 500 µl of Buffer RL1. Homogenize the tissue using an electric homogenizer. Transfer the homogenized tissue solution to a DNA purification column, reserving the supernatant in the collection tube. Then, take 500 µl of the reserved supernatant and add 1.6 times the volume of Buffer RL2, gently mixing. Transfer the mixture to an RNA purification column and centrifuge at 12000×g for 1 min, discarding the waste liquid. Next, add 500 µl of Buffer RW1 to the purification column and centrifuge at 12000×g for 1 min, discarding the waste liquid again. Then, add 700 µl of Buffer RW2 to the purification column and repeat the centrifugation and waste liquid discarding steps. Place the purification column back into the collection tube and centrifuge at 12000×g for 2 minutes to remove any residual Buffer RW2 from the column. Finally, the purification column was transferred to a new centrifuge tube, and 50 µl of RNase-free ddH2O preheated at 65 °C was added to the purification column. After incubation at room temperature for 2 min, the column was centrifuged for 1 min, and the RNA solution was finally collected.

[0029] (2) Reverse transcription of hippocampal RNA Prepare a 10 µl mixture according to the instructions, containing 2 µl of 5×Evo M-MLVRT Master Mix, and then add 8 µl of a mixture of RNA and RNase-Free water. Place it in a PCR reverse transcription apparatus and set the reaction conditions as follows: 37°C for 15 min, then 85°C for 5 sec, and finally lower the temperature to 4°C to stop the reaction, obtaining cDNA for subsequent experiments.

[0030] (3) qPCR reaction of hippocampal tissue The qPCR reaction was performed in a 10 µl volume containing 0.5 µl of the first primer, 0.5 µl of the second primer, 4 µl of 2×SYBR Green, and 5 µl of cDNA. The PCR instrument was set as follows: first, 95°C for 30 s, one cycle; second, 95°C for 5 s; and finally, 60°C for 30 s, for a total of 40 cycles. The primer sequences used are shown in Table 1.

[0031] Table 1 Primer Sequences Gene name Preprime sequence Postprimer sequence IL-1β 5'-TGGACCTTCCAGGATGAGGACA-3' 5'-GGGGTCGTTGATGGCAACA-3' IL-6 5'-GTTCATCTCGGAGCCTGTAGTG-3' 5'-CTGCAAGTGCATCATCGTTGTTC-3' TNF-α 5'-GGTGCCTATGTCTCAGCCTCTT-3' 5'-GCCATAGAACTGATGAGAGGGAG-3' GAPDH 5'-AGGTCGGTGTGAACGGATTTG-3' 5'-GGGGTCGTTGATGGCAACA-3' This invention uses enzyme-linked immunosorbent assay (ELISA) to detect the release of inflammatory factors. The steps include: five groups of mice, namely the Sham group, the CLP group, and the CLP + different doses (5 mg / kg, 10 mg / kg, 20 mg / kg) cell-penetrating peptide treatment group, were euthanized 24 hours after the operation of the mice treated with different methods. Serum samples were collected from the five groups of mice, and the levels of systemic inflammatory factors (TNF-α, IL-1β, IL-6) in the serum were detected according to the instructions of the corresponding ELISA kits.

[0032] Following this, a mouse drug toxicity test was conducted to evaluate the toxicological safety characteristics of the self-designed and synthesized cell-penetrating peptide in experimental mice. The experiment consisted of a normal control group and a drug-treated group. Mice in the drug-treated group received daily tail vein injections of the self-designed and synthesized cell-penetrating peptide at doses of 20 mg / kg or 50 mg / kg for 7 consecutive days, while mice in the normal control group received an equal volume of physiological saline. During the drug administration period, changes in body weight and the presence of toxic reactions or abnormal behavioral signs were observed in each group. Seven days after continuous drug administration, the mice were euthanized, and blood biochemical tests were performed on the heart, liver, and kidney function. Simultaneously, H&E staining was performed on the heart, liver, lung, and kidney tissues of both the normal control group mice and the mice that received the 50 mg / kg cell-penetrating peptide for 7 consecutive days to observe for histopathological damage in each organ and tissue.

[0033] The results showed that mice were effectively treated with FLKNCE-Tat cell transmembrane peptide administered via tail vein injection at doses of 20 mg / kg or 50 mg / kg daily for 7 consecutive days. During the administration period, no toxic reactions or behavioral abnormalities were observed in any group of mice, and there was no significant difference in body weight. Figure 5 A, P>0.05). Blood biochemical analysis of liver and kidney function in mice showed no significant differences between the treatment groups and the control group at different doses of cell-penetrating peptide (APP). Figure 5B-5I, P>0.05). Furthermore, histopathological H&E staining of the heart, liver, lung, and kidney tissues showed no significant pathological changes compared to the control group treated with FLKNCE-Tat at a dose of 50 mg / kg for 7 consecutive days. Figure 5 J, P>0.05). Therefore, these results indicate that the FLKNCE-Tat cell-penetrating peptide was well tolerated in mice, and no toxic reactions were detected.

[0034] To evaluate the therapeutic potential of FLKNCE-Tat in mice with septic brain injury, this invention administered different doses (5, 10, and 20 mg / kg) of FLKNCE-Tat cell-penetrating peptide at 2 and 6 hours post-CLP surgery. FLKNCE-Tat treatment improved CLP-induced septic brain injury in mice in a dose-dependent manner. Compared with CLP mice, the survival rates of mice treated with CLP + 10 mg / kg - FLKNCE-Tat (CLP + 10 mg) and CLP + 20 mg / kg - FLKNCE-Tat (CLP + 20 mg) were significantly increased. Figure 6 A, P<0.05 (CLP group: 30%; CLP+10 mg group: 70%; CLP+20 mg group: 75%), while the survival rate of mice treated with CLP+5 mg / kg-FLKNCE-Tat (CLP+5 mg) did not change significantly. Figure 6 A, P>0.05. Compared with the CLP group, mice treated with FLKNCE-Tat cell membrane-penetrating peptide also showed a dose-dependent decrease in MSS score at 24 h post-surgery. Figure 6 B, P<0.05. Furthermore, compared to the CLP group, the serum levels of pro-inflammatory cytokines IL-1β, TNF-α, and IL-6 were significantly reduced in the FLKNCE-Tat treatment group (B < 0.05). Figure 6 C-6E, P<0.05. H&E staining results showed that, compared with the CLP group, the FLKNCE-Tat cell-penetrating peptide treatment groups (CLP+5mg, CLP+10mg, and CLP+20mg groups) showed a significant reduction in damaged pyramidal neurons in the hippocampus of mice, and a significant increase in morphologically regular neurons. Figure 6 F and 6G, P<0.05). Nissl staining results also showed that, compared with the CLP group, mice in the CLP+5mg, CLP+10mg and CLP+20mg groups had increased Nissl bodies and decreased dissolution (F and 6G, P<0.05). Figure 6 H and 6I, P<0.05). This indicates that the self-designed and synthesized cell-penetrating peptide FLKNCE-Tat can effectively alleviate CLP-induced brain damage in CLP-induced septic mice.

[0035] In some embodiments, protein expression data can be detected using methods well known in the art, 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. In a specific embodiment of the invention, Western blotting and immunofluorescence staining are used to obtain protein expression data.

[0036] In some embodiments, transcriptome sequencing revealed differentially expressed genes and enriched pathways in the brain tissue of CLP mice after FLKNCE-Tat treatment.

[0037] To further investigate the molecular pathway mechanisms involved in the treatment of SAE mice with FLKNCE-Tat, transcriptome sequencing was performed on brain tissues from CLP mice and CLP mice treated with FLKNCE-Tat. Differential expression analysis was performed based on the sequencing results, using a fold change (FC) > 1.5 and P < 0.05 as the selection criteria. Volcano plots showed 227 differentially expressed genes (DEGs) between the CLP group and the FLKNCE-Tat treatment group, including 196 upregulated genes and 31 downregulated genes. Figure 7 A). The heatmap more clearly shows the significant differences in the expression patterns of DEGs between the two groups ( Figure 7 B). Since FLKNCE-Tat primarily targets and binds to the c-JUN protein, screening of DEGs revealed 21 genes that interact with the Jun gene, including Atf3, B2m, Casp7, Ccl3, Ccl5, Ccn1, Ccnb1, Ccr2, Cd274, Cd40, Cd53, Cd86, Eif2ak2, Fos, Foxl2, Hspb1, Ifit3, Il1a, Irf7, Irf9, and Itk (…). Figure 7 C). GO and KEGG enrichment analyses were then performed on these DEGs. GO analysis showed that the enriched biological processes were primarily related to mouse behavior and growth (C). Figure 7 D). KEGG pathway analysis showed significant enrichment in several key pathways, including the Toll-like receptor signaling pathway, lipid and atherosclerosis, measles, Kaposi's sarcoma-associated herpesvirus infection, and cytokine-cytokine receptor interactions. Figure 7 E). Meanwhile, GSEA analysis further confirmed a significant upregulation of the Toll-like receptor signaling pathway and the cytokine-cytokine receptor interaction pathway (E). Figure 7 F and 7G). In addition, such as Figure 5As shown in .1H, compared with the CLP group, in the brain tissue of CLP mice treated with FLKNCE-Tat, the mRNA expression levels of key DEGs involved in the Toll-like receptor signaling pathway and the cytokine-cytokine receptor interaction pathway, CCL3, CCL5, CD40, IRF7, CD86, and FOS were significantly increased, while CCR2 expression was decreased. Figure 7 H, P < 0.05).

[0038] In some embodiments, FLKNCE-Tat inhibits the activation of the JNK / c-Jun / ATF2 signaling pathway to alleviate SAE.

[0039] The repair process following sepsis-related brain injury is closely related to the MAPK signaling pathway, which is downstream of the Toll-like receptor signaling pathway. Inhibition of the JNK / c-JUN / ATF2 signaling axis affects downstream anti-apoptotic pathways. For example... Figure 8 As shown in AD and F, compared with the Sham group, phosphorylated JNK (p-JNK) increased by approximately 2.6-fold, phosphorylated c-JUN (pc-JUN) increased by approximately 1.8-fold, and phosphorylated ATF2 (p-ATF2) increased by approximately 3.7-fold in the brain tissue of CLP mice (P < 0.05). In contrast, the levels of p-JNK, pc-JUN, and p-ATF2 in the CLP+FT group after FLKNCE-Tat treatment were significantly reduced by 37.7%, 24.9%, and 49.8%, respectively, compared with the CLP group. Figure 8 AD and F, P < 0.05. The expression level of total c-JUN protein in the CLP group was also upregulated compared to the Sham group, and significantly downregulated after FLKNCE-Tat treatment. Figure 8 E, P < 0.05. Furthermore, compared to the Sham group, the CLP group mice showed a 25.0% reduction in the anti-apoptotic protein Bcl-2, while the pro-apoptotic protein Bax was upregulated by 2.05-fold. Figure 8 G and H, P < 0.05. FLKNCE-Tat treatment significantly reversed this trend, increasing Bcl-2 by 1.25 times and decreasing Bax levels by 30.3% (G and H, P < 0.05). Figure 8 G and H, P < 0.05). The above results indicate that FLKNCE-Tat regulates apoptosis signaling, protects against neuronal death, and effectively reduces brain tissue damage in SAE mice by inhibiting the activation of the JNK / c-JUN / ATF2 signaling pathway.

[0040] In some embodiments, the experimental design of the above research results is as follows: Mice were randomly divided into three groups: a sham operation group (Sham), a sepsis (CLP) group, and a CLP+FLKNCE-Tat (CLP+FT) treatment group. Animals in the CLP group underwent cecal ligation and perforation, while mice in the Sham group only underwent exploratory laparotomy. Mice in the CLP+FT group were treated with intravenous injection of 10 mg / kg FLKNCE-Tat cell-penetrating peptide 2 and 6 hours after CLP modeling, while the other two groups received an equal volume of saline. Mice were euthanized by cervical dislocation 24 hours post-surgery after anesthesia with an overdose of isoflurane. Brain tissue from mice in the CLP and CLP+FT groups (n=4) was collected for transcriptomic sequencing analysis. Simultaneously, brain tissue from all three groups of mice was collected 24 hours post-surgery to obtain hippocampal homogenates for real-time quantitative PCR detection and Western blot experiments.

[0041] In some embodiments, the steps of transcriptome sequencing analysis include: 1. RNA extraction Total RNA extraction using the Trizol method: Trizol reagent is used to extract total RNA directly from cells or tissues, preserving RNA integrity during cell lysis and dissolution. Cells are lysed to release RNA; after adding chloroform and centrifugation, the sample separates into an aqueous layer and an organic layer. Acidic conditions allow RNA to separate from DNA, with RNA remaining in the aqueous layer. After collecting the aqueous layer, the RNA can be reduced by isopropanol precipitation.

[0042] Experimental steps: 1) Take an appropriate amount of tissue, grind it thoroughly in liquid nitrogen, then transfer it to a 1.5 mL centrifuge tube, add 1 mL of Trizol, and mix thoroughly immediately; 2) Let the mixed tissue stand at room temperature for 10 min to allow for complete lysis; 3) Add 200 µL of chloroform, shake thoroughly to mix, centrifuge at 4 ℃ for 12000 rpm for 10 min; 4) Take the upper aqueous phase, add an equal volume of phenol:chloroform (25:24), mix thoroughly, centrifuge at 4 ℃ for 12000 rpm for 10 min; 4) Take the upper aqueous phase, add an equal volume of chloroform, mix thoroughly, and centrifuge at 4 ℃ for 12000 rpm for 10 min; 5. Take the upper aqueous phase, add an equal volume of isopropanol, let stand at -20 ℃ for 1 hour, centrifuge at 4 ℃ for 12000 rpm for 10 min; 6. Discard the supernatant, add 1 mL of 75% ethanol, wash the precipitate, centrifuge at 4 ℃ for 8000 rpm for 5 min, and discard the supernatant; 7. Repeat the previous step; 8. Briefly centrifuge, pipette to remove ethanol, and vacuum dry for 2-4 minutes; 9) Add 20-50 μL of RNase-Free Water, dissolve at room temperature for 10 min, mix well, and then centrifuge briefly; 1) Store at -80℃.

[0043] 2. RNA quality control Nanodrop micro-spectrophotometer detection: NanoDrop detects the OD value of nucleic acids to determine their purity. The A260 / A280 ratio should ideally be between 1.8 and 2.0. An RNA A260 / 280 ratio <1.8 indicates protein or phenol contamination, while a ratio >2.0 suggests a higher probability of RNA sample degradation. Another indicator of nucleic acid purity is the A260 / A230 ratio, which should be around 2.2. A value below 1.8 indicates significant organic contamination such as sugars, peptides, phenols, and salt ions. This is likely due to the organic phase being aspirated during the aspiration of the upper aqueous phase.

[0044] 3. Transcriptome library construction Experimental steps: 1) Prepare the first-strand reaction buffer and random primer mixture (2×).

[0045] 2) mRNA isolation, fragmentation, and primer addition: Eukaryotic mRNA was enriched using magnetic beads with Oligo (dT) coating. 17 µL of pre-prepared First Strand Synthesis Reaction Buffer and RandomPrimer Mix (2×) were added to the tube from the previous step, and the sample was incubated at 95 °C for 15 min to elute the mRNA from the magnetic beads.

[0046] 3) cDNA first-strand synthesis: a) Add the following reagents to the fragmented and primer-added mRNA: Marine RNase Inhibitor--0.5 µL; ProtoScript II Reverse Transcriptase--1 µL; Nuclease Free Water--3.5 µL; Fragmented and primer-added mRNA – 15 µL; Total Volume: 20 µL.

[0047] b) Place the sample in a preheated PCR instrument for reaction (capping temperature: 105 ℃), under the following conditions: 25 ℃ for 10 min, 42 ℃ for 15 min, 70 ℃ for 15 min, and 4 ℃ Forever.

[0048] c) Proceed immediately with the second-chain synthesis reaction.

[0049] 4) cDNA Second-Strand Synthesis: a) Add the following reagents to the first-strand synthesis reaction solution described above (20 µL). b) Mix thoroughly and incubate in a PCR instrument at 16 °C for 1 h. The temperature of the heat-sealed container should not exceed 40 °C. Purify the double-stranded cDNA using 1.8X AgencourtAMPure XP Beads, and transfer 55.5 µL of the supernatant to a new nuclease-free PCR tube.

[0050] 5) cDNA library fragment end preparation: a) Mix the following reagents in a sterile Nuclear Free tube: Purified Double Stranded cDNA--55.5 µL; NEBNext End Repair Reaction Buffer (10×)--6.5 µL; NEBNext End Prep Enzyme Mix--3 µL; Total Volume: 65 µL.

[0051] b) Place the sample in a PCR instrument for reaction (heating temperature 75 ℃), conditions: 20 ℃ for 30 min, 65 ℃ for 30 min, 4 ℃ forever.

[0052] c) Proceed with the connector connection immediately.

[0053] 6) Connect the connectors: a) Add the following reagents directly to the final reaction solution prepared in the previous step (Note: Dilute NEB Next Adaptor with Tris-HCl): End Prep Reaction -- 65 µL; Blunt / TA Ligase Master Mix--15 µL; Diluted NEBNext Adapter--1 µL; Nuclease Free Water--2.5 µL; Total Volume: 83.5 µL.

[0054] b) Place in a PCR instrument and incubate at 20 °C for 15 min. Close the heat seal.

[0055] 7) Purify the ligation reaction solution: Add water to the above reaction solution to 100 μL, purify using AMPure XP Beads, wash with 80% ethanol, elute with ddH2O, and use the eluent for the next reaction.

[0056] 8) PCR library amplification a)NEBNext USER Enzyme--3 µL; NEBNext High-Fidelity PCR Master Mix, 2×--25 µL; Universal PCR Primer (25 µM)--1 µL; Index (X) Primer (25 µM)--1 µL; Total volume: 50 µL.

[0057] b) PCR cycling conditions: 98 ℃--30 s, (98 ℃--10 s; 65 ℃--75 s) 12 cycles; 65 ℃--5 s.

[0058] 9) Purify the PCR products using AMPure XP Beads (1.0X).

[0059] 10) For library quality control, choose either the DNA 1000 assay kit (Agilent Technologies, 5067-1504) or the High Sensitivity DNA assay kit (Agilent Technologies, 5067-4626). The DNA 1000 assay kit can detect sample fragments ranging from 25 to 1000 bp in size and 0.1 to 50 ng / µL in concentration. The High Sensitivity DNA assay kit can accurately quantify pg-level samples and can sometimes be used as a quantitative standard for the assay. It can detect sample fragments ranging from 50 to 7000 bp in size and 5 to 500 pg / µL in concentration.

[0060] 4. Differential gene analysis between groups The input data for gene differential expression analysis was the read counts data obtained from gene expression level analysis. The analysis was performed using edgeR software and consisted of three main parts: 1) Normalize the read counts; 2) Calculate the hypothesis test probability (pvalue) based on the model; 3) Finally, perform multiple hypothesis testing and correction to obtain the FDR value (false detection rate).

[0061] Based on the differential analysis results, genes with FDR < 0.05 and |log2FC| > 1 were selected as significantly differentially expressed genes.

[0062] (1) Volcano plot for comparison: Based on the significantly different genes in each comparison group, we performed volcano plot analysis. The volcano plot can intuitively show the difference in genes between the comparison groups. In the graph, the genes closer to the two ends are more different.

[0063] (2) Differential Gene Clustering Heatmap: Hierarchical clustering of differential gene expression patterns was performed, and a heatmap was used to present the clustering results. These genes with similar expression patterns may have common functions or participate in common metabolic pathways and signaling pathways. The gene expression level of each sample was processed as log 2 (FPKM+1).

[0064] (3) GO Enrichment Analysis: Gene Ontology (GO) is an internationally standardized gene function classification system that provides a dynamically updated controlled vocabulary to comprehensively describe the attributes of genes and gene products in organisms. GO has three ontologies, describing the molecular function, cellular component, and biological process of genes, respectively. The basic unit of GO is the term, and each term corresponds to an attribute. GO functional analysis provides GO functional classification annotations for differentially expressed genes and GO functional significance enrichment analysis for differentially expressed genes.

[0065] (4) KEGG enrichment analysis: In organisms, different genes coordinate with each other to perform their biological functions. Pathway-based analysis helps to further understand the biological functions of genes. KEGG is a major public database of pathways. Pathway significant enrichment analysis uses KEGG pathways as units and applies hypergeometric tests to identify pathways that are significantly enriched in differentially expressed genes compared with background genes.

[0066] (5) Protein-protein interaction network analysis: The interaction relationships in the STRING protein-protein interaction database (http: / / string-db.org) were used to analyze the differential gene-protein interaction network. For species included in the database, we extracted the differential gene set from the database and constructed the interaction relationship network diagram using Cytoscape. For species not included in the database, we first used blastx to align the sequences of the target gene set to the protein sequences of the reference species included in the string database, and then constructed the interaction network using the aligned protein-protein interaction relationships of the reference species.

[0067] (6) GSEA Analysis: GSEA (Gene Set Enrichment Analysis) effectively compensates for the shortcomings of traditional enrichment analysis in extracting effective information about genes with minor effects, and provides a more comprehensive explanation of the regulatory role of a functional unit (pathway, GOterm, or others). GSEA and MSigDB are used to identify GOterms / pathways that differ between the two groups. The expression scale is input, and genes are sorted using Signal2Noisez. Enrichment scores (ES), p-values, and FDR values ​​are calculated using default parameters. Normalization yields |NES|. Generally, gene sets along pathways with |NES|>1, NOM p-val<0.05, and FDR q-val<0.25 are considered meaningful. A larger absolute value of NES and a smaller FDR value indicate higher reliability of the analysis results.

[0068] 5. Real-time quantitative PCR Same as before. The primer sequences used are shown in Table 2 below.

[0069] Table 2 Primer Sequences Gene name Preprime sequence Postprimer sequence GAPDH 5'-AGGTCGGTGTGAACGGATTTG-3' 5'-GGGGTCGTTGATGGCAACA-3' CCL3 5'-ACTGCCTGCTGCTTCTCCTACA-3' 5'-ATGACACCTGGCTGGGAGCAAA-3' CCL5 5'-CCTGCTGCTTTGCCTACCTCTC-3' 5'-ACACACTTGGCGGTTCCTTCGA-3' CD40 5'-ACCAGCAAGGATTGCGAGGCAT-3' 5'-GGATGACAGACGGTATCAGTGG-3' IRF7 5'-CCTCTGCTTTCTAGTGATGCCG-3' 5'-CGTAAACACGGTCTTGCTCCTG-3' CD86 5'-ACGTATTGGAAGGAGATTACAGCT-3' 5'-TCTGTCAGCGTTACTATCCCGC-3' FOS 5'-GGGAATGGTGAAGACCGTGTCA-3' 5'-GCAGCCATCTTATTCCGTTCCC-3' IL1A 5'-ACGGCTGAGTTTCAGTGAGACC-3' 5'-CACTCTGGTAGGTGTAAGGTGC-3' CCR2 5'-GCTGTGTTTGCCTCTCTACCAG-3' 5'-CAAGTAGAGGCAGGATCAGGCT-3' S102: Input the protein expression data collected above into the constructed efficacy evaluation model, which evaluates the therapeutic effect of the cell-penetrating peptide on the patients to be evaluated based on the protein expression data.

[0070] In some embodiments of the present invention, the method for constructing the efficacy evaluation model is as follows: obtaining protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in samples of patients with sepsis-associated encephalopathy who have not been treated with the cell-penetrating peptide and patients with sepsis-associated encephalopathy who have been treated with the cell-penetrating peptide, and inputting the protein expression data into a machine learning algorithm to construct the efficacy evaluation model.

[0071] In some embodiments, the methods for constructing the efficacy evaluation model are known to those skilled in the art and can be implemented and realized in different ways, including the steps of associating protein expression information with a certain probability or risk.

[0072] 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 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.

[0073] In some embodiments of the present invention, after constructing the efficacy evaluation model, the effectiveness of the model can be evaluated using ROC curve analysis.

[0074] 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.

[0075] S103: Output the prediction results.

[0076] In some embodiments of the present invention, the efficacy evaluation model obtains results using the following criteria: when the protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, and Bax in the protein expression data are below a threshold, a classification result is obtained indicating that the cell-penetrating peptide is effective in treating the patient under evaluation; when the protein expression data of Bcl-2 in the protein expression data are below a threshold, a classification result is obtained indicating that the cell-penetrating peptide is ineffective in treating the patient under evaluation.

[0077] In some embodiments of the present invention, the preset threshold is a representative value of a normal sample from a sepsis-associated encephalopathy 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.

[0078] Figure 2 The system structure provided by this invention for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-associated encephalopathy is shown. intention.

[0079] The system is programmed or otherwise configured to include an information acquisition module 201, a treatment efficacy evaluation module 202, and an output module 203. Information acquisition module 201: used to collect protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in the patient samples to be evaluated; Therapeutic efficacy evaluation module 202: used to input the protein expression data collected in the information collection module into the therapeutic efficacy evaluation model obtained by the construction method described in claim 2, and to obtain the classification results of whether the cell membrane-penetrating peptide is effective in the treatment of the patient to be evaluated; Output module 203: Used to output classification results; The amino acid sequence of the cell-penetrating peptide is FLKNCEYGRKKRRQRRR.

[0080] The system may be a user's electronic device or a computer system remotely located relative to that electronic device.

[0081] Figure 3 A schematic diagram of the structure of the computer device provided by the present invention.

[0082] The computer device 301 includes a processor 302 and a memory 303 coupled to the processor 302. The memory 303 stores program instructions. When the program instructions are executed by the processor 302, the processor 302 performs the method described above for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-related encephalopathy.

[0083] The processor 302 can also be referred to as a CPU (Central Processing Unit). The processor 302 may be an integrated circuit chip with signal processing capabilities. The processor 302 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.

[0084] Computer equipment 301 can be a mobile electronic device.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] Although specific embodiments of the invention have been described in detail, those skilled in the art will understand that various modifications and variations can be made to the details based on all the published teachings, and all such changes are within the scope of protection of the invention. The entire scope of the invention is given by the appended claims and any equivalents thereof.

Claims

1. A method for evaluating the therapeutic effect of cell-penetrating peptides on patients with sepsis-associated encephalopathy, characterized in that, The method is performed by a computer and includes the following steps: Protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 were collected from patient samples to be evaluated. The collected protein expression data is input into the constructed efficacy evaluation model, which evaluates the therapeutic effect of the cell-penetrating peptide on the patients to be evaluated based on the protein expression data. Output evaluation results; The amino acid sequence of the cell-penetrating peptide is FLKNCEYGRKKRRQRRR.

2. The method according to claim 1, characterized in that, The method for constructing the efficacy evaluation model is as follows: obtain the protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in samples of patients with sepsis-associated encephalopathy who have not been treated with the cell-penetrating peptide and patients with sepsis-associated encephalopathy who have been treated with the cell-penetrating peptide, and input the protein expression data into a machine learning algorithm to construct the efficacy evaluation model.

3. The method according to claim 1, characterized in that, The efficacy evaluation model obtains results using the following criteria: When the protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, and Bax are below the threshold, the classification result of the cell-penetrating peptides as effective in treating the patients to be evaluated is obtained. When the protein expression data of Bcl-2 in the protein expression data is lower than the threshold, the classification result of the cell-penetrating peptide as ineffective in the treatment of the patients to be evaluated is obtained.

4. The method according to claim 1, characterized in that, The machine learning algorithms include algorithmic models developed using various development tools.

5. The method according to claim 4, characterized in that, The development tools include: TensorFlow, ScikitLearn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell.

6. The method according to claim 4, characterized in that, The algorithm models include: linear regression model, logistic regression model, Lasso regression model, Ridge regression model, linear discriminant analysis model, nearest neighbor model, decision tree model, perceptron model, neural network model, support vector machine model, Naive Bayes model, AdaBoost model, GBDT model, XGBoost model, LightGBM model, CatBoost model, and random forest model.

7. A system for evaluating the therapeutic effect of cell-penetrating peptides on sepsis-associated encephalopathy, characterized in that, The system includes: Information acquisition module: used to collect protein expression data of p-JNK, pc-JUN, p-ATF2, c-JUN, Bax, and Bcl-2 in the patient samples to be evaluated; The efficacy evaluation module is used to input the protein expression data collected in the information collection module into the efficacy evaluation model obtained by the construction method described in claim 2, and to obtain the classification results of whether the cell membrane-penetrating peptide is effective in the treatment of the patient to be evaluated; Output module: Used to output classification results; The amino acid sequence of the cell-penetrating peptide is FLKNCEYGRKKRRQRRR.

8. A computer device, characterized in that, The device includes: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-6.

Images