Antibacterial and anti-inflammatory peptide based on deep learning model and application of antibacterial and anti-inflammatory peptide
Through deep learning models, the screening and synthesis of polypeptides with antibacterial and anti-inflammatory activities has been solved, and the problem of insufficient research on antibacterial and anti-inflammatory peptides in the prior art has been achieved, and the broad-spectrum anti-bacterial and anti-inflammatory effects are achieved. It is suitable for the preparation of antibacterial and anti-inflammatory drugs and daily chemicals, and has significant antibacterial and anti-inflammatory effects.
Patent Information
- Application Number
- CN202510619928.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-14
- Publication Date
- 2025-08-26
AI Technical Summary
In the prior art, there are few researches on polypeptides that have both antibacterial and anti-inflammatory activities, and lack polypeptides with broad-spectrum antibacterial and high activity, making it difficult to effectively use the preparation of antifungal, antibacterial and anti-inflammatory drugs or daily chemicals.
By constructing an XGBoost classification model based on deep learning models, polypeptide sequences with potential antibacterial and anti-inflammatory activities were screened, and 12 polypeptides were synthesized and verified, with the preferred amino acid sequences being SEQ ID NO: 2, 6, 9, 10, 12, which were used to prepare antibacterial and anti-inflammatory drugs and daily chemicals.
It has achieved efficient antibacterial and anti-inflammatory effects, significantly inhibited bacterial growth, reduced inflammatory response, enhanced antioxidant enzyme system activity, and provided safe and effective solutions to treat and prevent infections and inflammatory diseases.
Smart Images
Figure CN120544684A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of biomedical technology and relates to a class of antibacterial and anti-inflammatory peptides based on deep learning models and their application in preventing and treating fungal and bacterial infections and inflammatory diseases. Background Art
[0002] Antimicrobial peptides originally refer to a class of basic polypeptides with antimicrobial activity induced by insects. They have a molecular weight of approximately 2,000 to 7,000 and are composed of 20 to 60 amino acid residues. Most of these active peptides possess strong alkalinity, thermal stability, and broad-spectrum antimicrobial properties. Previous studies have shown that antimicrobial peptides inhibit the growth of pathogenic bacteria, with different antimicrobial peptides exhibiting varying levels of killing abilities against bacteria, fungi, protozoa, and viruses. Antimicrobial peptides also exhibit selective immune activation and regulatory functions. Currently considered one of the most promising candidates for anti-infective drug development, antimicrobial peptides have been widely used in the medical, agricultural, and food industries.
[0003] Similar to antimicrobial peptides, anti-inflammatory peptides are a class of small molecule polypeptides with broad anti-inflammatory activity. They originate from a part of the innate immune system. Anti-inflammatory peptides exert their anti-inflammatory effects through multiple mechanisms, including: directly inhibiting the production of inflammatory mediators such as prostaglandins and leukotrienes, thereby inhibiting the onset and progression of inflammatory responses; inhibiting the chemotaxis, adhesion, and phagocytosis of inflammatory cells such as neutrophils and macrophages, thereby reducing tissue damage; regulating the secretion of inflammatory cytokines such as IL-1, IL-6, and TNF-α, thereby alleviating inflammatory responses; and enhancing the activity of antioxidant enzyme systems, thereby reducing oxidative damage to tissues caused by oxygen free radicals.
[0004] At present, there are few studies on peptides with both antibacterial and anti-inflammatory effects. However, new bioactive peptides with antibacterial and anti-inflammatory functions that are different from existing single-functional peptides are still a direction that needs further research to further expand the diversity of bioactive peptides. Summary of the Invention
[0005] The present invention aims to address the deficiencies of the prior art by providing an antibacterial and anti-inflammatory peptide and its application. The novel antibacterial and anti-inflammatory peptide provided by the present invention has the advantages of broad-spectrum antibacterial activity and high anti-inflammatory activity, and can be used to prepare antifungal, antibacterial, and anti-inflammatory drugs or daily chemical products.
[0006] The specific technical solutions of the present invention are as follows:
[0007] A class of active peptides, the amino acid sequences of which are shown in SEQ ID NO: 1-NO: 12.
[0008] SEQ ID NO:1: EQCGRQAGGKLCPNNLCCSQWGWCGSTDEYCSX;
[0009] SEQ ID NO:2:HIQKEDVPSERYLGYLEQLLRLKKYK;
[0010] SEQ ID NO:3: SKEKIGKEFKRIVQRIKDFLRNLV;
[0011] SEQ ID NO:4: SNVMEERKIKVYLPRMKMEE;
[0012] SEQ ID NO:5: RDNIQGITKPAIRRRLARRGGVKRISGLIY;
[0013] SEQ ID NO:6: IGKEFKRIVQRIKDFLRNLVPRTES;
[0014] SEQ ID NO:7: VQRIKDFLRNLVPRT;
[0015] SEQ ID NO:8: ILELAGNAARDNKKTRIIPRHLQL;
[0016] SEQ ID NO:9:HIQKEDVPSERYLGYLEQLLRLK;
[0017] SEQ ID NO:10: HIQKEDVPSERYLGYLEQLLRLKK;
[0018] SEQ ID NO:11: KRIVQRIKDFLRNLVPRTES;
[0019] SEQ ID NO: 12: IGKEFKRIVQRIKDFLRNL.
[0020] Preferred active peptides are SEQ ID NOs: 2, 6, 9, 10, and 12.
[0021] Another object of the present invention is to provide a DNA molecule encoding the active peptide of the present invention.
[0022] Another object of the present invention is to provide an expression vector for expressing the active peptide, wherein the expression vector is a plasmid, a phage, a virus or a host cell. Preferably, the host cell is selected from Escherichia coli, yeast, and lactobacillus.
[0023] Another object of the present invention is to provide a live bacteria preparation comprising the expression vector of the present invention.
[0024] Another object of the present invention is to provide the use of the antimicrobial and anti-inflammatory peptide, DNA molecule, expression vector, or live bacterial preparation in the preparation of antifungal, antibacterial, or anti-inflammatory drugs or antifungal, antibacterial, or anti-inflammatory daily chemicals. The drug comprises the antimicrobial and anti-inflammatory peptide or live bacterial preparation of the present invention and a pharmaceutically acceptable carrier or excipient.
[0025] The excipients include one or more of antioxidants, emulsifiers, diluents, preservatives, solubilizers, disintegrants, wetting agents, adhesives or lubricants.
[0026] The dosage form of the medicine is injection, tablet, capsule, oral liquid preparation, granule, and ointment.
[0027] The drugs of the present invention can be administered in various known ways, such as oral administration, injection, topical application to the skin, etc. The drugs of the present invention can be administered alone or in combination with other drugs. Oral compositions can be in any orally acceptable dosage form, including but not limited to tablets, capsules, and oral solutions.
[0028] Sterile injectable compositions can be formulated using suitable dispersing agents or wetting agents and suspending agents according to techniques known in the art. Pharmaceutically acceptable carriers and solvents that can be used include water, sodium chloride solution, and the like.
[0029] The actual dosage level of the active ingredient in the medicament of the present invention can be varied to obtain an amount of the active ingredient that is effective to achieve the desired therapeutic response for a particular patient, composition, and mode of administration, without being toxic to the patient. The selected dosage level depends on a variety of factors, including the route of administration, time of administration, rate of excretion, duration of treatment, other drugs, compounds, and / or materials used in combination, the age, sex, weight, general health, and previous medical history of the patient being treated, and similar factors well known in the medical arts.
[0030] The daily chemical products are facial cleansers, hand soaps, skin care products (such as skin creams, water or lotions), cosmetics or feminine care lotions.
[0031] Advantages of the present invention:
[0032] The present invention sorted out 1678 positive anti-inflammatory peptide sequences (length ≤ 50 amino acids) and 2516 non-anti-inflammatory peptide sequences (experimentally verified to be negative anti-inflammatory cytokines) from the IEDB database (immune epitope database) to construct an original data set for predicting anti-inflammatory activity. BLAST (Basic Local Alignment Search Tool) was used to preliminarily screen the sequences in the DBAASP antimicrobial peptide database, and 12506 antimicrobial peptide sequences with a length of 5-50 amino acids were collected as a prediction data set. The original data set for predicting anti-inflammatory activity was used to train a deep learning model (XGBoost classification model). The antimicrobial peptide data set was input into the model to generate scores for polypeptide sequences with potential activity. Sequences with higher probability and importance scores of functional polypeptides predicted by the model were selected for blast verification. Based on the blast evaluation, 12 polypeptide sequences were selected. After homology alignment analysis of multi-species reference genomes and in vitro experimental verification, 5 of the polypeptide sequences were determined to have good antimicrobial and anti-inflammatory activities. The antimicrobial and anti-inflammatory peptides described in this invention can not only be used to prepare antimicrobial and anti-inflammatory drugs, but can also serve as prebiotics, significantly improving intestinal dysbiosis and related diseases. They can be used to prevent and treat various infections and inflammatory diseases, and can also be used as natural ingredients in anti-inflammatory cosmetics and their derivatives, offering the advantages of high safety and effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 The antibacterial and anti-inflammatory peptides of the present invention have an inhibition rate on bacterial growth (A is Staphylococcus aureus, B is Escherichia coli, and C is Propionibacterium acnes).
[0034] Figure 2 Analysis of the anti-inflammatory activity of the antibacterial and anti-inflammatory peptides of the present invention (A 4h, B 8h, C 12h).
[0035] Figure 3 The cytotoxicity test results of the antibacterial and anti-inflammatory peptides of the present invention on the HaCaT cell line. DETAILED DESCRIPTION
[0036] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0037] Unless otherwise specified, the terms used in the present invention generally have the meanings commonly understood by those skilled in the art.
[0038] In the following examples, various processes and methods not described in detail are conventional methods well known in the art.
[0039] Example 1. Construction of antibacterial and anti-inflammatory peptides using deep learning models
[0040] 1. Dataset Division
[0041] (1) Training and testing data sets: 1678 positive anti-inflammatory peptide sequences (length ≤ 50 amino acids) and 2516 non-anti-inflammatory peptide sequences (experimentally verified to be negative anti-inflammatory cytokines) were compiled from the IEDB database (immune epitope database) to construct an original data set for anti-inflammatory activity prediction. The data set was randomly divided into 80% training set and 20% test set for model training and preliminary verification.
[0042] (2) Prediction Dataset: BLAST (Basic Local Alignment Search Tool) was used to perform a preliminary screening of sequences in the DBAASP antimicrobial peptide database to ensure that the selected sequences had a certain degree of sequence homology with known antimicrobial peptides. The specific screening parameters were as follows: Screening criterion: E-value ≤ 1e-5.
[0043] Objective: To quickly narrow the screening scope and obtain candidate peptide sequences that are similar in sequence to antimicrobial peptides.
[0044] A total of 12,506 antimicrobial peptide sequences ranging from 5 to 50 amino acids in length were collected from the pre-screened DBAASP antimicrobial peptide database as a prediction dataset. Once the model training was complete, this dataset was used as new input to construct the model for the identification of potential antimicrobial peptides with anti-inflammatory activity.
[0045] 2. Model Training
[0046] (1) Model selection:
[0047] An XGBoost classification model was used to identify the anti-inflammatory activity of sequences.
[0048] XGBoost is suitable for classification tasks of biological sequence data due to its superior performance in handling sparse data and complex features.
[0049] (2) Parameter settings:
[0050] Training epochs: 300.
[0051] Optimization algorithm: Stochastic Gradient Descent (SGD).
[0052] Momentum: 0.8
[0053] Learning rate: Set to 0.005 to control the step size of each update.
[0054] Maximum depth (max_depth): Set to 6 to limit the depth of each tree to prevent overfitting.
[0055] Subsample: Set to 0.8, which means each tree uses 80% of the data.
[0056] Column sampling rate (colsample_bytree): Set to 0.8 to control the proportion of features randomly sampled by each tree.
[0057] Regularization parameters: λ (L2 regularization) and α (L1 regularization), set to 1 and 0 respectively, control the model complexity.
[0058] Number of iterations (n_estimators): 200, indicating the maximum number of trees. The early stopping strategy is used for automatic adjustment in actual training.
[0059] (3) Hyperparameter optimization:
[0060] Grid Search and 5-fold cross-validation were used to tune the model hyperparameters to ensure model stability and reduce overfitting.
[0061] In each fold, the best configuration is found by adjusting parameters such as learning rate, maximum depth, subsampling rate, etc.
[0062] (4) Model evaluation:
[0063] Evaluation is performed using training and test datasets, and metrics such as accuracy, recall, precision, and F1 score are calculated to comprehensively assess the classification performance of the model.
[0064] 3. Construct candidate sequences:
[0065] After the XGBoost model training was completed, the predicted data set was input into the model as new data to construct potential antimicrobial peptides with anti-inflammatory activity. First, the sequences with higher probability and importance scores of functional peptides predicted by the model were subjected to subsequent blast verification. Based on the blast evaluation, 12 candidate antimicrobial peptide sequences with anti-inflammatory activity (P1-P12, SEQ ID No:
[0066] 1-12).
[0067] Example 2. Synthesis of antibacterial and anti-inflammatory peptides
[0068] 1. The target short peptide was synthesized using the Fmoc solid-phase synthesis strategy and the CEM Liberty Blue automatic peptide synthesizer.
[0069] 2. Rink amide AM resin was selected as the solid phase support, and the resin substitution degree was 0.5 mmol / g.
[0070] 3. Amino acids were used in 4-fold excess, and 0.2 M N,N'-diisopropylcarbodiimide (DIC) and 0.5 M acetylimidazole (HOBt) were used as condensing agents.
[0071] 4. Each condensation cycle includes:
[0072] a) The Fmoc protecting group was removed using a 20% piperidine / DMF solution, twice for 3 minutes each time.
[0073] b) Wash with DMF three times, 30 seconds each time.
[0074] c) Amino acid coupling reaction was carried out at 50°C for 10 minutes.
[0075] d) Wash with DMF three times, 30 seconds each time.
[0076] 5. Peptide chain cleavage and side chain deprotection:
[0077] a) Use TFA / TIS / H2O (95:2.5:2.5, v / v / v) cleavage reagent and react at room temperature for 2 hours.
[0078] b) The reaction mixture was filtered and the filtrate was collected.
[0079] c) The peptide was precipitated with ice-cold ether and the precipitate was collected by centrifugation at 4°C.
[0080] 6. Use semi-preparative reverse-phase HPLC for purification and freeze-drying to obtain the purified polypeptide.
[0081] 7. Preparation of peptide solution:
[0082] a) Weigh 10 mg of freeze-dried polypeptide powder (accurate to 0.1 mg).
[0083] b) Add 10 mL of sterile, pyrogen-free PBS (137 mM NaCl, 2.7 mM KCl, 10 mM Na2HPO4, 1.8 mM KH2PO4) to prepare a 1 mg / mL stock solution.
[0084] c) Measure the pH of the solution using a pH meter and adjust it to pH 7.4 ± 0.1 with 1 M NaOH or 1 M HCl.
[0085] d) Sterilize by filtration using a 0.22 μm filter membrane.
[0086] 8. Dilute the solution to a concentration of 3-500 μM using PBS and adjust the pH to 7.4 before conducting subsequent validation experiments.
[0087] Example 3. Evaluation of antibacterial activity
[0088] A small amount of Staphylococcus aureus was inoculated into 5 ml of LB medium and cultured overnight at 37 ° C and 180 rpm. Then 1 ml of the overnight culture solution was diluted into 50 ml of fresh LB medium and cultured at 37 ° C and 180 rpm until the OD600 was about 0.6. Serial dilutions were performed to obtain 1 × 10 6 CFU / ml of bacterial solution. The 12 purified polypeptide solutions prepared in Example 2 were diluted to different concentrations with sterile PBS solution, and a control group without polypeptide was set up. Further, 100 μl of the diluted bacterial solution was added to the 96-well plate, and then 100 μl of polypeptides of different concentrations (4, 8, 16, 32, 64, 128, 256, 512 μg / ml) were added to the corresponding wells. After incubation in a 37°C incubator for 6 hours, the sample was diluted and spread on the LB plate, and then incubated at 37°C overnight. The number of colonies on the plate was counted the next day, and the inhibition rate was calculated. The results are as follows. Figure 1 As shown, the results showed that P2, P6, P9, P10, and P12 had obvious antibacterial effects.
[0089] Example 4. Evaluation of anti-inflammatory activity
[0090] RAW 264.7 cells were cultured at 37°C in 5% CO2 until the logarithmic growth phase in RPMI 1640 medium containing 10% fetal bovine serum, 100 u / mL penicillin, and 0.1 mg / mL streptomycin. Cells were plated in 96-well plates (5 × 10 5 cells / ml) to ensure the same cell density in each well. An inflammatory model was first induced using LPS at a working concentration of 0.1 μg / mL. The cells were co-incubated for 6 hours. After observing significant changes in cell morphology under a microscope, the peptide solution was added. After co-incubating the cell line with 64 μg / ml of purified peptide for 4, 8, and 12 hours, total RNA was extracted and reverse transcribed into cDNA. The relative expression of the inflammatory factor TNF-α was further detected by RT-qPCR. The results are shown in Figure 2. Figure 2 As shown, the results showed that after 12 hours of co-incubation, P2, P6, P9, P10, and P12 had significant anti-inflammatory activity.
[0091] Example 5. Cytotoxicity evaluation
[0092] HaCaT cells were routinely cultured in DMEM complete medium containing 10% FBS and digested and passaged when the cells grew to 80-90% confluence. After trypsinization, the cell concentration was adjusted and 5×10 cells were seeded per well in a 96-well plate. 3 cells, add 100 μL of complete culture medium to each well, and culture in a 37°C, 5% CO2 incubator for 24 hours to allow the cells to adhere. The polypeptide was prepared into the required concentration (32 μg / mL and 160 μg / mL) with sterile PBS, and 5 replicate wells were set for each concentration. At the same time, a control group with only culture medium was set up. After replacing the fresh culture medium containing the corresponding concentration of polypeptide, the culture was continued for 24 hours. During the detection, 10 μL of CCK-8 reagent was added to each well, and the cells were incubated in the incubator for 1-4 hours (the specific time was determined according to the color change). The OD value of each well was measured at a wavelength of 450 nm using an enzyme reader. At the same time, a blank control group containing only culture medium and CCK-8 was set up. Finally, the cell survival rate was calculated according to the formula: Cell survival rate (%) = [(OD value of the experimental group - OD value of the blank control) / (OD value of the control group - OD value of the blank control)] × 100%. The entire experiment needs to be repeated 3 times independently to ensure the reliability of the results. During the experiment, attention should be paid to aseptic operation to avoid bubbles during the liquid addition process that affect the reading results. The results are as follows Figure 3 As shown in the figure, the results showed that the 12 antibacterial and anti-inflammatory peptides had no significant toxicity to HaCaT cells.
[0093] The antibacterial and anti-inflammatory peptides of the present invention can act on the gastrointestinal tract to effectively prevent and treat various inflammatory diseases, and are a natural, safe and effective treatment option.
Claims
1. A class of active peptides characterized by The amino acid sequences are shown in SEQ ID NO: 1-NO:
12.
2. A DNA molecule characterized in that Encodes the active peptide according to claim 1.
3. The expression vector of active peptide is characterized by Expressing the active peptide according to claim 1.
4. The expression vector according to claim 3, characterized in that The expression vector is a plasmid, a phage, a virus or a host cell.
5. The expression vector according to claim 4, characterized in that The host cell is selected from Escherichia coli, yeast, and lactobacillus.
6. A live bacteria preparation, characterized in that Comprising the expression vector according to any one of claims 3 to 5.
7. Use of the active peptide according to claim 1, the DNA molecule according to claim 2, the expression vector according to any one of claims 3 to 5, or the live bacterial preparation according to claim 6 in the preparation of antifungal, antibacterial, anti-inflammatory drugs or daily chemical products.
8. The use according to claim 7, characterized in that The medicine comprises the active peptide according to claim 1 or the live bacterial preparation according to claim 6 and a pharmaceutically acceptable carrier or excipient thereof.
9. The use according to claim 8, characterized in that The dosage form of the drug is injection, tablet, capsule, oral liquid preparation, granule or ointment.
10. The use according to claim 8, characterized in that The daily chemical product is a facial cleanser, hand soap, skin care product, cosmetics or feminine care lotion.