334 results about "Drug action" patented technology

The present invention provides a method and intelligent agent for data collection and drug safety signal mining for PMS, which relates to the field of drug monitoring technology, including standardizing PMS data using a medical text pre-training model, and integrating drug molecular characteristics and clinical medication information to construct a multi-layer drug knowledge graph. A heterogeneous graph neural network with a time series feature extraction function is used to represent the graph, and the drug action mechanism rules are integrated into the training process to obtain a node vector representation of multi-dimensional information fusion. Based on the node vector representation, a multi-task learning framework is constructed to simultaneously complete the drug-adverse reaction association probability prediction and risk level prediction, and combine time series analysis to detect dynamic change characteristics to generate candidate signals. Finally, a hierarchical evaluation system is constructed to verify the candidate signal, and its reliability is confirmed in combination with clinical data, the target signal is output, the warning level is determined, and differentiated monitoring cycles and trigger thresholds are set to perform real-time risk warnings.

The invention discloses a drug target activation and inhibition relation prediction method based on a depth map neural network, and aims to improve the modeling precision and prediction performance of an activation or inhibition action mechanism between a drug and a target. According to the method, on the basis of a fine-grained graph interaction modeling mechanism, multi-scale structural characteristics of drug molecules and three-dimensional space structural information of protein residue levels are fused, and a heterogeneous interaction graph between drugs and proteins is constructed. The method comprises the following steps: firstly, acquiring a drug-target sample with an activation / inhibition tag through a public database, predicting a protein structure by utilizing AlphaFold2, and constructing a protein residue map and a drug molecular map; multi-scale structure semantic representation is obtained through sub-graph decomposition, atomic-scale feature extraction and graph neural network coding of drug graph features; protein graph node features are combined with context embedding generated by a pre-training language model, DSSP coding, secondary structure spectrum and atomic structure features are constructed, and edge features are designed based on the geometrical relationship between residues. Then, based on constraints such as spatial distance and biochemical similarity, a fine-grained mapping relation between drug atoms and protein residues is established, an interaction graph is constructed, and coding is carried out through a GraphSAGE network; and finally, fusing the interacted multi-source embedding, and completing the prediction of the activation / suppression relationship through a multi-layer perceptron. A cross entropy loss function, an Adam optimizer and hyper-parameter grid search are adopted in model training; in the evaluation stage, five-fold cross validation and an independent test set are adopted, and indexes such as the accuracy rate, the recall rate, the F1 score, the specificity and the Morse correlation coefficient are used for comprehensively evaluating the performance of the model. Experimental results show that compared with an existing method, the method has the advantages that the prediction accuracy and mechanism interpretability are remarkably improved, and the method has good generalization ability and application prospects and is suitable for multiple fields of drug action mechanism research, new drug discovery and the like.

The invention provides a method for drug screening and disease model construction of liver organoid, relates to the technical field of medical research, and adopts multi-modal data acquisition, fusion and intelligent analysis and quantum computing processing to optimize comprehensive application of data, so that the richness, accuracy and analysis efficiency of the data are remarkably improved, and the risk of drug screening and disease model construction of liver organoid is reduced. Multi-source data of genomics, transcriptomics and the like are collected comprehensively, an accurate research system of immune-hepatic disease interaction based on organoid is constructed, an in-vivo complex immune-hepatic disease microenvironment can be highly simulated, the proportion and activation state of immune cells are accurately regulated and controlled in an in-vitro model, functional and phenotypic changes of the immune cells are monitored in real time, and the immune-hepatic disease interaction accuracy is improved. According to the present invention, the interaction mechanism between the immune cells and the liver organ cells is deeply revealed, such that the accurate information basis is provided for the accurate determination of the drug action target, the development of the innovative drug for the immune check point or tumor microenvironment regulation is easily achieved, and the pertinence and the success rate of the drug research and development are substantially improved.

The invention discloses a patient immune response monitoring method and system for cell drug clinical research, and the method comprises the following steps: 1, obtaining a peripheral blood sample of a patient, and preprocessing the peripheral blood sample to obtain patient sample components; multi-dimensional immune indexes and cell drug specific immune response are detected by comprehensively utilizing multiple technologies, immune cell subsets, cell factors, immune globulin, T cell response and the like are covered, and therefore a complex immune response system is comprehensively reflected; peripheral blood samples are collected at multiple time points according to a cell drug action mechanism and a half-life period, and the whole-course change of the immunoreaction is effectively tracked, so that the development trend of the immunoreaction is accurately grasped; the method has the advantages that the characteristics are visually presented by constructing the immune response atlas of the patient, evaluation and prediction are assisted, real-time monitoring reports and treatment suggestions are provided according to evaluation and prediction results, doctors are assisted to adjust treatment in time, and accordingly the safety and effectiveness of cell drug treatment are improved.

The invention relates to an oral mucosa repairing medicine and a preparation method thereof, and belongs to the technical field of medicines, the medicine comprises barnacle peptide, salivary lactobacillus, resveratrol, a biphasic adhesion matrix, hydroxyapatite, vitamin B family and other components. The preparation method comprises the following steps: sequentially carrying out enzymolysis on barnacle gooseneck by pepsin and lumbrukinase to obtain barnacle peptide. The double-phase adhesion matrix comprises a water-phase matrix, an oil-phase matrix and lecithin; the water-phase matrix contains a chondroitin sulfate-chitosan quaternary ammonium salt compound, sodium alginate and other components; the oil-phase matrix comprises sesame oil, beeswax, a polylactic acid-glycolic acid copolymer and the like. According to the invention, barnacle peptide and salivary lactobacillus are prepared by adopting a special method and are matched with resveratrol for use, so that multi-target and multi-path promotion of oral mucosa repair can be realized; the chondroitin sulfate-chitosan quaternary ammonium salt compound is prepared through electrostatic and physical embedding, the chondroitin sulfate-chitosan quaternary ammonium salt compound is matched with other components to prepare the biphasic adhesion matrix, the biocompatibility is good, the adhesion is high, and the action time of a sustained-release drug is well prolonged.

The invention belongs to the technical field of biological medicines, and particularly relates to application of oxibenzophenone in preparation of a medicine for treating pathological cardiac hypertrophy and / or heart failure. Research results in myocardial cells of primary newborn rats show that Exibenzophenone can inhibit pathological hypertrophy of myocardial cells induced by phenylephrine (PE). Animal experiments show that the epoxybenzophenone can improve cardiac dysfunction induced by aortic arch constriction (TAC) and reduce cardiac hypertrophy and cardiac tissue fibrosis. The invention provides a new drug research and development approach and a drug action target for treating pathological cardiac hypertrophy and heart failure, and has very important medicinal value.

Disclosed is an acylated insulin, a pharmaceutical formulation thereof, a pharmaceutical composition thereof with a long-acting GLP-1 compound, and a medical use of the acylated insulin, the pharmaceutical formulation and the pharmaceutical composition. Compared with insulin degludec or other insulin derivatives, the acylated insulin has an unexpected, significantly increased drug effect, a longer duration of action, a longer in vivo half-life, an excellent bioavailability, as well as better physical and chemical stabilities.

The invention discloses intestinal bacteria and serum metabolites which can be used as biomarkers of type 2 diabetes mellitus (prediabetes mellitus (PDM), new diagnosis diabetes mellitus (NDDM) and diabetes mellitus (P2DM) after medication) in different disease stages, and application of the intestinal bacteria and the serum metabolites. Aiming at type 2 diabetes mellitus, predictive markers including staphylococcus aureus, escherichia coli, klebsiella pneumoniae, branched chain amino acids (leucine, valine and isoleucine) and the like, especially staphylococcus aureus of which the genome contains acetolactate synthase (ALS), are efficiently screened out. The type 2 diabetes mellitus marker disclosed by the invention can be used for early warning the illness risk of type 2 diabetes mellitus and guiding the adjustment of an intestinal microbial environment; the method can be used for indicating the correlation between the intestinal microbial environment and the type 2 diabetes mellitus and is used for assisting diagnosis; and drug action target research, accurate medication, pathogenesis research and the like are realized.

The invention discloses a wound healing state evaluation method and system based on artificial intelligence, and belongs to the field of wound healing evaluation. The method comprises the following steps: integrating medical record data and wound physiological parameters, and extracting relevance between a medication history and an infection type to form a multi-dimensional pathological factor; hemoglobin oxygenation, blood flow and metabolic heat are subjected to cross-period correlation analysis to construct dynamic physiological time-space information, pathological factors and the physiological time-space information are fused into a heterogeneous graph, nodes comprise drug intensity quantized values, infection risk levels and microcirculation fluctuation values, and edge weights are determined by the time sequence matching degree of drug doses and blood flow changes; based on the node weight and the edge association relationship, the treatment time and the physiological parameter acquisition period are aligned to generate a spatio-temporal evolution matrix, the spatial distribution of the infection risk level and the metabolic heat value characteristics are combined, the dynamic association of the drug action intensity and the microcirculation fluctuation is analyzed, and wound healing evaluation information is generated. The accuracy of wound healing state evaluation can be improved.

The invention relates to double-encapsulated lipid nanoparticles entering brain through nose and a preparation method and application thereof, the double-encapsulated lipid nanoparticles comprise lipid nanoparticles, drugs in the lipid nanoparticles and rana odorata lectin coupled to the surfaces of the lipid nanoparticles, and the drugs comprise hydrophilic drugs and hydrophobic drugs. According to the invention, the rana odorata lectin and the lipid nanoparticles are coupled, and the rana odorata lectin can be specifically combined with L-fucose residues expressed by olfactory epithelial cells, so that the adhesion of the lipid nanoparticles to olfactory epithelium during nasal administration is enhanced, and the brain entering efficiency of the lipid nanoparticles is finally improved. After entering the brain, the lipid nanoparticles respond to diseased regions with high active oxygen content so as to release drugs. In addition, double-drug encapsulation can target different pathogenesis of central nervous system diseases, and the limitation that a traditional treatment drug is single in action target is improved.

The invention relates to a drug-loaded bone filling material, a preparation method thereof and application of the drug-loaded bone filling material in inhibition of relapse of opioid drugs. The drug-loaded bone filling material is prepared from the following raw materials: powder and curing liquid, the powder comprises a mixture of an opioid receptor antagonist and inorganic calcium salt; in the powder, the mass ratio of the opioid receptor antagonist to the inorganic calcium salt is 4-20%. After a performance test, the drug-loaded bone filling material has the advantages of proper coagulation time, good compressive strength and better drug sustained release characteristic, on one hand, artificial bones capable of promoting osteoblast differentiation can be filled in a bone defect area, and on the other hand, side effects caused by opioid drugs can be relieved, and symptoms can be relieved; meanwhile, for relieving opioid addicts, long-time drug action can be maintained, relapse can be prevented or reduced, and the pharmaceutical composition has great application potential in promoting osteoblast differentiation or inhibiting relapse of opioid drugs.

The invention provides a xenomeline pharmaceutical composition, which comprises xenomeline pamoate and a pharmaceutically acceptable carrier, and can be used for preparing a suspension or a freeze-drying preparation for injection. The suspension has stable particle size, is not easy to cause particle sedimentation, and has good heavy suspension property; the freeze-drying preparation is easy to re-suspend to obtain a uniform suspension. The composition has good stability, can quickly take effect after administration, prolongs the drug action time, reduces the administration frequency, reduces the side effects of the drug, and significantly improves the life quality of patients.

The invention discloses an application of a reagent for promoting MARCH2 gene expression in preparation of a medicine for treating aortic aneurysm / dissection, and provides a novel medical application of the MARCH2 gene, the disease progress of the aortic aneurysm / dissection can be slowed down and the prognosis of a patient can be improved by exogenous administration of MARCH2; the invention also provides a reagent for detecting MARCH2 gene expression in preparation of a reagent or a kit for detecting aortic aneurysm / dissection, and also provides a pharmaceutical composition for treating aortic aneurysm / dissection, the pharmaceutical composition comprises a pharmaceutically acceptable carrier and an effective amount of active ingredients, and the active ingredients comprise the reagent for promoting MARCH2 gene expression. The invention reveals that MARCH2 can improve aortic aneurysm / dissection vascular injury for the first time, provides a new drug action target for diagnosis and treatment of aortic aneurysm / dissection, and has important clinical value.

The invention provides a nanocrystalline composite oral ulcer film agent as well as a preparation method and application thereof. The nanocrystalline composite oral ulcer film agent comprises a waterproof backing layer and a drug-loading adhesion layer coated on the waterproof backing layer, the drug-loaded adhesion layer comprises a macromolecular hydrogen bond compound formed by a weakly acidic polymer and a nonionic proton receptor polymer, and a nanocrystalline drug. Compared with the prior art, the preparation method has the advantages that the polyacrylic acid polymer and the nonionic cellulose polymer interact to form IPC serving as an adhesion layer film-forming material, the nanocrystals are loaded into the adhesion layer film-forming material, the waterproof backing layer is coated with the adhesion layer film-forming material, and the oral ulcer film agent is prepared after drying and cutting. The obtained film agent has good comfort and adhesive power, shows good drug stability and permeation promotion performance, can be used as a carrier of an oral administration route, prolongs the drug action time and improves the curative effect. The preparation method of the film agent is simple and easy for industrial mass production.

According to the big data-based adverse drug reaction monitoring method and system provided by the invention, the drug action feature data and the patient reaction feature data are accurately extracted from clinical feedback big data, and the feature data are creatively fused to generate more comprehensive drug clinical feedback features, so that the clinical feedback big data is more accurate. And a solid foundation is laid for subsequent adverse drug reaction analysis. Furthermore, the characteristic combination meeting the application conditions of the medicine combination can be intelligently searched and identified in huge clinical feedback characteristics, and the precise prediction and evaluation of the adverse reaction under the combined use of the medicines are realized. Finally, based on the feature groups, the drug adverse reaction labels corresponding to the target drugs can be automatically generated, data support is provided for drug research and development, clinical application and supervision, the occurrence risk of adverse reactions in the drug use process is effectively reduced, and the drug use safety of patients is guaranteed.

The invention relates to the technical field of biological medicine, in particular to anti-acne hydrogel and a preparation method thereof. The anti-acne hydrogel is prepared from metal-polyphenol network nanoparticles and a hydrogel base material, the metal-polyphenol network nanoparticles comprise a first polyphenol compound, a second polyphenol compound and metal ions, the first polyphenol compound is a tannic acid compound, and the second polyphenol compound is a flavonoid compound; the hydrogel base material comprises a hydrophilic high-molecular polymer and a cationic polymer. The metal-polyphenol network nano-particles are creatively utilized, the anti-inflammatory and anti-oxidation activity of flavonoid compounds, the convergence and protein binding characteristic of tannin and the antibacterial activity of metal ions are integrated at the same time, and the vicious circle of acne can be intervened at the same time from multiple links of antibacterial, anti-inflammatory, anti-oxidation and keratinization adjustment; and the defect of single action target spot of the existing medicine is overcome.

The invention discloses a methotrexate-cationic polypeptide conjugate as well as a preparation method and application thereof, and belongs to the technical field of medicinal chemistry. According to the conjugate, MTX and cationic polypeptide with the amino acid sequence shown as SEQ ID NO: 1 are connected through chemical bonding, the membrane binding characteristic of oligomeric lysine and the transmembrane capacity of TAT cell-penetrating peptide are creatively fused, and a polypeptide carrier system with efficient cell penetrating capacity is constructed; mTX obtains amphipathy and electropositivity through peptide fragment modification, stable nanoparticles can be spontaneously formed, and the problems of poor water solubility and instable acidity of raw material medicines are effectively improved; according to the conjugate, the accumulation efficiency of the medicine at a diseased region is remarkably improved by utilizing the targeting characteristic of the polypeptide carrier, the action time of the medicine is prolonged through a precise delivery mechanism, and meanwhile, the system toxicity is reduced. The preparation method adopts mild coupling reaction conditions, and the product is high in purity and excellent in stability; the compound is suitable for treating immune-mediated inflammatory diseases and specific malignant tumors, and provides an innovative solution thought for treating related diseases.

The invention provides an artificial intelligence customer service management method and system for medical services, and relates to the technical field of artificial intelligence, and the method comprises the steps: processing consultation information through a medical term mapping network and a medical image unified recognition framework; fusing the standardized term information, the drug feature information and the prescription feature information to generate standardized consultation data; carrying out risk identification and grading processing based on a drug action relation network; outputting corresponding response information according to the grading result; and updating the identification framework parameters through user feedback. The intelligent medical consultation service is realized, and the risk identification accuracy and the response efficiency are improved.

Compositions comprising two pHLIP® peptides linked to a STING agonist, which is a dimer with a carboxylic acid subsituent (carboxyl group) at the terminal position of both monomers of the dimer, pharmaceutical compositions thereof, and methods of treatment using such compositions are disclosed herein.

The invention discloses an application of a compound Isaridin E or a pharmaceutical salt thereof in preparation of anti-vascular calcification drugs and related diseases, and relates to the technical field of medical biology. A classical high phosphate induced smooth muscle cell calcification model and an in-vivo vascular calcification model induced by a high dose of vitamin D3 are adopted, and through an in-vitro cell experiment, an in-vitro experiment and an overall animal experiment, it is found that the compound Isaridin E has a remarkable improvement effect on vascular calcification caused by calcium and phosphorus metabolism disorder. The medicine has the effects of remarkably inhibiting vascular smooth muscle cell osteogenic differentiation induced by high phosphate and vitamin D3, inhibiting vascular calcification and remarkably reducing formation of calcium-phosphorus crystals on vascular walls. The invention develops a brand new medical application of the marine compound Isaridin E, and the marine compound Isaridin E can be used for research and development of drugs for treating vascular calcification and calcification-related diseases.

The invention relates to a heart rehabilitation management method based on rehabilitation requirements. The method comprises the following steps: acquiring oxygen saturation time sequence data of a patient through wearable equipment, performing biological rhythm feature extraction on the data to construct a fluctuation model so as to capture a physiological cycle rule, and constructing a drug action factor based on a drug taking record to perform drug action calibration on original data so as to eliminate exogenous interference. Candidate time windows with consistent physiological statuses are screened through sliding window stability analysis; dynamic baseline calculation is performed on the candidate window based on long-term monitoring data to establish an individualized reference standard, when the dynamic baseline reaches the standard, the biological rhythm parameters and the drug action factors are fused to score and screen the time window, and finally, an individualized rehabilitation training scheme is generated in combination with physiological feature matching of a patient. Dynamic synergy of drug metabolism, physiological rhythm and historical baselines is achieved, the problem of physiological load imbalance caused by a static training plan is solved, and the rehabilitation efficiency is improved while the heart compensation risk is remarkably reduced.

The invention belongs to the technical field of computer biology, and relates to a lightweight drug-target interaction prediction method based on double pre-training language models. Downloading a protein information data set of required drug compounds and drug action targets from a public database; sending the protein sequence into an encoder to obtain a generated vector; the method comprises the following steps: labeling a compound sequence of a drug by using a tokenizer, pre-defining a corresponding relation between a compound sequence label and an integer, then converting into an integer value, and inputting the integer value into an encoder to generate a vector; splicing the class tokens to obtain a drug target pair, and feeding the drug target pair into an interaction head; and calculating an interaction probability between the two. According to the method, the drug pre-training language model and the protein pre-training language model are introduced at the same time, deep semantic coding is performed on the SMILES sequence and the amino acid sequence, molecular structure characteristics and protein sequence characteristics can be comprehensively captured, and the expression ability is remarkably enhanced.

The invention discloses a microfluidic multi-organ tumor chip targeted drug test AIGC system, and relates to the technical field of medical drug test information processing. The microfluidic multi-organ tumor chip targeted drug test AIGC system comprises a multi-omics data acquisition module for acquiring and preprocessing disturbance response data and dynamic expression data; the disturbance response pre-screening module is used for carrying out strength evaluation on drug action strength and reconstructing channel mapping; the characteristic space reconstruction module is used for performing action analysis on the whole medicine action state and dynamically adjusting a liquid medicine blending rule; the drug effect prediction module is used for predicting and evaluating the response degree of the organoid under the intervention of the specific drug and deducing the individualized drug effect intensity; and the feature augmentation self-closed loop module constructs a negative supervision signal and dynamically corrects a disturbance perception and feature embedding path. The problems that current multi-omics data is high in dimension, large in redundancy and large in noise, key features are difficult to extract under limited samples, and model generalization is difficult to maintain are solved.

The invention relates to the technical field of traditional Chinese medicine extract preparation, and discloses taste-masking enteric-coated traditional Chinese medicine extract particles which comprise drug-loaded pellets and enteric-coated coatings coating the drug-loaded pellets. The invention relates to a drug-loaded pellet. The coating comprises 20-45 parts of pure powder of the traditional Chinese medicine extract and 5-10 parts of dextrin; according to the taste-masking enteric-coated traditional Chinese medicine extract particle and the preparation method thereof, a stable barrier is formed in gastric juice through a carboxymethyl chitosan-lipidosome copolymer coating, and the degradation rate of effective components is reduced to 1t from 40-60% of a traditional preparation; the pH-responsive coating ensures that the rapid release rate of the intestinal tract is as high as 90%, the bioavailability is improved by 2-3 times, the bitter taste is completely covered by the coating layer, and the coating layer can be mixed with food to feed pets; the prepared sustained-release dosage form prolongs the action time of the medicine, reduces the medication frequency, reduces the medication cost of pet owners, and improves pet welfare.

The invention discloses a drug action analysis method based on tumor organoid three-dimensional roughness characterization, and relates to the technical field of tumor organoid. According to the method, the original three-dimensional structure data of the tumor organoids are obtained through three-dimensional interference without fluorescent reagent labeling, and then the connected domain data corresponding to each organoid in the target organoid cluster are segmented and determined, so that the morphological parameters of each organoid are determined, according to the method, the morphological parameters of at least one of the entity volume, the cavity volume, the post-filling volume, the post-filling surface area, the longest axis, the shortest axis and the sphericity of each similar organ are determined through internal hole filling, and the surface of each similar organ after internal hole filling is smoothed; according to the volume change caused by the smooth processing relative to the filled volume, the morphological parameter of the roughness corresponding to each organoid is determined, the roughness can perform quantitative characterization on the organoid heterogeneity to a great extent, and the accuracy of the tumor organoid drug effect is improved.

This invention discloses an AfBPP-based active molecular probe for thiostreptin, its preparation, and its application, belonging to the field of chemical biology. This invention introduces a bifunctional tag integrating a photocrosslinking group (bisacrididine) and a bioorthogonal reactive group (alkynyl group) into the structure of thiostreptin. While retaining the original biological activity of the parent compound, it endows the probe with highly efficient probe function, solving the technical problem of target loss during washing and purification of traditional non-covalent probes. After target labeling, the probe can specifically connect to reporter groups such as fluorescein or biotin through click-chemical reactions, achieving efficient enrichment of drug targets. Combined with mass spectrometry analysis, it enables global identification of potential targets in cells or complex biological samples at the omics level, such as chemical proteomics, providing a powerful molecular tool for in-depth revelation of the potential targets and pharmacological mechanisms of thiostreptin.

The invention discloses a mitochondrial / lysosome dual-targeting viscosity response AIE probe as well as a preparation method and application thereof. According to the probe, tetraphenylethylene (TPE) is used as an AIE light-emitting framework, and two flexible side chains containing hydrophilic units are introduced by utilizing the excellent structural modifiability of the TPE. The tail end of each side chain is modified with a trimethylamine group, quaternary ammonium salt cations derived from the trimethylamine group have localized positive charges, and combination with water molecules can be enhanced through ion-dipole interaction, so that the water solubility and biocompatibility of the molecules are effectively improved. Based on the design, the invention provides the AIE polymer probe which is constructed by taking TPE as a core and taking an amphiphilic flexible chain as a functional unit. The probe can establish a three-dimensional linear relationship among drug action time-regional viscosity-fluorescence lifetime (t-eta-tau) by capturing fluorescence lifetime signals inside and outside cells, so as to realize visual detection and quantitative analysis of average viscosity change of mitochondria and lysosome in the mitochondrial autophagy process.

The invention discloses an application of DL-3-phenyllactic acid in treatment of cardiac mucinoma. Based on metabonomics, it is found that the level of endogenous DL-3-phenyllactic acid in serum of a patient is remarkably reduced, pharmacodynamic verification is conducted by means of a cardiac mucinoma tissue-derived cardiac mucinoma organ model of the patient, it is proved that DL-3-phenyllactic acid can inhibit proliferation of cardiac mucinoma organs in a dose-dependent mode, and the half inhibitory concentration IC50 value of DL-3-phenyllactic acid is 95.52 mu M. The DL-3-phenyllactic acid can inhibit proliferation of cardiac mucinoma organs in a dose-dependent mode. Network pharmacological analysis indicates that the drug action mechanism may involve key targets such as AKT1 and SRC. The invention discloses the therapeutic efficacy of the DL-3-phenyllactic acid on the cardiac mucinoma for the first time, and provides a solid preclinical experimental basis for developing the DL-3-phenyllactic acid into the medicine for treating the cardiac mucinoma. The invention has non-obvious and important clinical application value.

The invention discloses a drug-miRNA interaction prediction method based on a meta-path expert network, belongs to the field of biological information, and relates to a drug-miRNA interaction prediction method. Prediction of the interaction between the drug and the miRNA not only contributes to revealing the drug action mechanism, but also can provide theoretical support for drug target discovery, drug relocation and individualized treatment. A traditional method mainly verifies drug-miRNA association based on biological experiments, but has the problems of high cost and long consumed time. However, the existing calculation method does not fully excavate the relationship between the drug and the miRNA. The invention provides a drug-miRNA interaction prediction method based on a meta-path expert network, and the method comprises the steps: firstly fusing various similarities, and constructing a heterogeneous graph in combination with the known drug-miRNA interaction; a heterogeneous graph is converted into a plurality of isomorphic graphs through meta-paths, semantic information of different meta-path graphs is learned by using a graph convolutional network, and node features with rich semantics are obtained. And finally, fusing node features of different meta path diagrams by using a hybrid expert model to obtain final drug node features and miRNA node features, and performing interaction prediction through MLP.

The invention discloses a precise regulation and control injection device for extraocular muscle toxin, and belongs to the technical field of medical instruments. The precise regulation and control injection device for extraocular muscle toxin comprises a microneedle assembly, a handle, a suction head and an injection regulation and control part, wherein the injection regulation and control part is used for controlling the microneedle assembly to be connected with the suction head. When the precise regulation and control injection device for the extraocular muscle toxin is used, the micro-needle assembly can be in suction connection with the suction head arranged at the tail end of the handle through adjustment of the injection regulation and control part, so that in the process that an operator injects the extraocular muscle toxin to a patient, it is ensured that a micro-needle does not deviate or loosen in the injection process, and the injection efficiency is improved. The precise positioning of an injection part is ensured; and the injection regulation and control part can regulate the action range of the microneedle on the microneedle assembly to be more concentrated, so that the concentration of the action range of the medicine and the accurate delivery of the medicine to the target muscle layer can be ensured, the out-of-control diffusion of the medicine is avoided, and the risk of penetrating through the sclera is reduced.