1125 results about "Drug candidate" patented technology

A computer implemented method may collect a set of known drug compounds from a database, and create augmented datasets with labeled and unlabeled chemical data and biological data. A computer implemented method may train a neural network using the expanded training set to generate a prediction score of bioactivity of candidate drug compounds towards the biological target, wherein the contribution of the second plurality of unlabeled samples in training the neural network is scaled by a parameter. A computer implemented method may output one or more refined neural network models capable of generating candidate drug compounds with predicted activity. A computer implemented method may generate a candidate drug compound by inputting a candidate drug compound with chemical data into the trained neural network model.

The invention discloses a five-membered sulfur-containing heterocyclic nucleoside derivative and application thereof in an anti-human immunodeficiency virus (HIV) active medicine, and belongs to the technical field of medicinal chemistry. A series of five-membered sulfur-containing heterocyclic ring nucleoside compounds are synthesized through a Sulfa-Michael / Aldol cascade reaction. The result shows that in an anti-HIV virus test, the five-membered sulfur-containing heterocyclic nucleoside lead compound 42a has the optimal anti-HIV-1 virus activity, and a new structural unit is provided for antiviral candidate drug molecules.

The invention belongs to the technical field of drug screening, and provides a multi-target drug screening and optimizing method based on machine learning, which comprises the following steps: S1, carrying out feature screening on compound molecular descriptors by utilizing a machine learning algorithm, and determining the molecular descriptor which has the most significant influence on biological activity; s2, constructing a quantitative structure-activity relation model, and predicting the biological activity of the compound; s3, based on a multi-objective optimization algorithm, combining absorption, distribution, metabolism, excretion and toxicity properties of the compound; according to the method, feature screening is carried out on compound molecule descriptors by utilizing a machine learning algorithm, a QSAR model is constructed to predict the biological activity, ADMET property classification prediction is combined, the biological activity, ADMET properties and pharmacokinetic characteristics of drugs are comprehensively considered, and the accuracy and accuracy of drug activity prediction are improved. The method can efficiently and accurately screen and optimize drug candidate compounds with potential drug effects and good pharmacokinetic characteristics, so that the success rate of drug research and development is increased, and the research and development cost and time are reduced.

The invention belongs to the technical field of chemistry, and particularly relates to a diaryl methyl pyrimidine piperazine compound as well as a preparation method, a pharmaceutical composition and application thereof. The structural formula of the diaryl methyl pyrimidine piperazine compound is shown as a formula I, and R is a substituted aromatic group. The preparation process is simple, the prepared diaryl methyl pyrimidine piperazine compound or the pharmaceutically acceptable salt thereof has the activity of efficiently inhibiting WDR5-MLL 1, and a targeted therapy scheme and novel, safe and efficient candidate drug molecules are provided for treating acute myeloid leukemia with WDR5-MLL fusion mutation. Experimental results show that the tumor inhibition rates of mouse tumor-bearing groups treated by the compounds 5c, 5k and 5l prepared by the invention are 79%, 85% and 75% respectively and are superior to those of a positive control group, and the compounds have good development prospects.

The invention relates to the technical field of electronic prescriptions, in particular to a dynamic electronic prescription generation method and system based on artificial intelligence. The method comprises the following steps: collecting the latest physiological state parameter flow of a patient, carrying out real-time health state evaluation, and generating a personalized patient state map; historical medical records of a patient are extracted, time sequence pathological evolution tracking is carried out, and a pathological evolution trajectory is generated; performing multi-parameter time sequence difference comparison calculation and drug curative effect quantitative evaluation based on the personalized patient state map and the pathological evolution trajectory to obtain a curative effect evaluation report; performing allergic drug identification on the patient based on the historical medical record of the patient, and performing secondary drug screening to obtain a drug candidate set; and performing intelligent matching calculation on the drug candidate set according to the curative effect evaluation report, and performing combinatorial optimization analysis to generate a final effective electronic prescription. The electronic prescription is automatically updated and adjusted based on the state change of the patient, the risk of allergic prescriptions is reduced, and the safety of the prescriptions is improved.

Provided are a new drug candidate discovery system and a computer program implementing a new drug candidate discovery platform. A new drug candidate discovery system may include an automatic data preprocessing module configured to receive a target protein information from a user through a web interface, and perform preprocessing on a protein structure file obtained based on the target protein information; a simulation setting module configured to predict an Enzymatically Active Pocket for Docking Calculation (EAPDC) from the protein structure file using an artificial intelligence language model, and determine a docking calculation site; and a docking simulation module configured to perform a docking simulation for the docking calculation site.

A computer implemented method may collect a set of known drug compounds from a database, and create augmented datasets with labeled and unlabeled chemical data and biological data. A computer implemented method may train a neural network using the expanded training set to generate a prediction score of bioactivity of candidate drug compounds towards the biological target, wherein the contribution of the second plurality of unlabeled samples in training the neural network is scaled by a parameter. A computer implemented method may output one or more refined neural network models capable of generating candidate drug compounds with predicted activity. A computer implemented method may generate a candidate drug compound by inputting a candidate drug compound with chemical data into the trained neural network model.

The invention discloses a medication assisting system and device based on symptom-medicine two-way verification, and belongs to the technical field of intelligent medical treatment. The system comprises a data preprocessing module, an entity extraction and alignment module, an atlas retrieval module, a case retrieval module and a bidirectional verification and auxiliary decision module. The system extracts a medical entity through an AC automaton rule engine and a knowledge enhanced BERT model, and realizes mapping with a knowledge graph entity by adopting a two-stage term alignment strategy; performing knowledge graph query by adopting an operation chain generation mechanism driven by cue words to obtain a candidate drug set; meanwhile, similar cases are retrieved based on vector similarity, and an associated drug set is generated; and finally, fusing external medicine knowledge base data, executing a bidirectional verification and completion strategy, and outputting medicine recommendation with clinical safety and coverage range. The invention further provides a device structure for realizing the functions of the system, and the accuracy and interpretability of clinical medication aid decision making are effectively improved.

An artificial intelligence system for drug discovery and development, consisting of: a data integration module configured to collect and process pharmaceutical data from multiple sources, including molecular structures, protein-protein interactions, drug-protein interactions, and clinical trial data, and to standardize the collected data into a uniform format; a machine learning engine configured to: analyze the standardized data using deep learning algorithms, generate predictive models for drug-protein interactions, and identify potential drug candidates based on molecular features; a drug development module configured for the following purposes: generation of novel molecular structures using generative contradictory networks, evaluation of the synthetic feasibility of generated molecules, and prediction of the biological activities of developed molecules; A clinical trial optimization module configured to: analyze patient data to select optimal study participants; predict drug efficacy based on molecular and patient-related characteristics; and create study protocols based on the predicted outcomes; and a validation module configured for evaluating the accuracy of generated predictions, validating synthetic routes for drug candidates, and assessing the safety profiles of developed molecules.

The invention discloses a virtual screening method of candidate drugs. The virtual screening method comprises the following steps: 1) providing an FXR receptor; providing a TGR5 receptor; oCA with a modified structure is used as a lead compound; providing an FXR ligand small molecule; 2) according to an active pocket of the FXR, performing molecular docking scoring on the lead compounds and the FXR, and screening the lead compounds to obtain a first compound; 3) according to an active pocket of the TGR5 receptor, performing molecular docking scoring on each first compound and the TGR5 receptor, and screening out a second compound from the first compounds; and 4) screening the second compound by adopting a pharmacophore model constructed on the basis of FXR ligand small molecules. The method provided by the invention can effectively reduce blindness of traditional drug design experiments, has high efficiency and low cost, can greatly reduce the time required for improving the compound, and increases the success rate. The candidate drug can regulate lipid metabolism and has no side effect.

The invention discloses a tumor personalized drug recommendation method and system based on fusion of multiple clinical guidelines, and belongs to the technical field of bioinformatics and precision medicine. The method comprises the following steps: acquiring gene variation data and clinical feature information of a patient; generating a preliminary drug candidate list based on drug recommendation rules of a plurality of clinical guidelines; calculating the weight of each guide by adopting a dynamic weight distribution algorithm; obtaining drug-gene-disease associated information through multi-hop reasoning of the knowledge graph; calculating a drug evidence score by adopting a multi-dimensional scoring algorithm; carrying out personalized score adjustment in combination with individual features of the patient; and outputting a personalized drug recommendation result. According to the method, through multi-guide dynamic fusion, multi-dimensional evidence scoring, knowledge graph reasoning and personalized adjustment, the problems of incomplete guide coverage, lack of personalization, low response speed and the like in the prior art are solved, the method has the advantages of high accuracy, high clinical applicability, quick response and the like, and the clinical real-time decision-making requirement can be met.

Disclosed herein are methods for identifying novel drug candidates.

A method is disclosed for using an artificial intelligence engine to generate candidate drug compounds, wherein the method comprises: generating candidate drug compounds comprising sequences via a creator module of the artificial intelligence engine. The method includes generating, via a descriptor module, a respective description for each of the candidate drug compounds at nodes in a knowledge graph, wherein the knowledge graph comprises a multi-dimensional representation of the candidate drug compounds and the respective description comprises drug compound structural information, drug compound activity information, and drug compound semantic information. The method includes determining a shape of the multi-dimensional representation of the candidate drug compounds; determining, based on the shape, a slice configured to be obtained from the representation; determining, using a decoder, which dimensions are included in the slice; and based on the dimensions, determining an effectiveness of a biomedical feature of the slice.

The invention relates to the technical field of drug research and development, in particular to a target AKT1 drug molecule discovery and delivery integrated system and method based on deep learning. Aiming at the problems of molecular design, optimization and delivery link separation and low research and development efficiency of drugs in the prior art, the system constructs a multi-module collaborative framework, and comprises a target analysis module for analyzing a target structure and formulating a generation strategy; the molecule generation and optimization module is used for generating and optimizing candidate molecules in combination with the generation model and reinforcement learning; the delivery scheme design module is used for matching a delivery carrier based on molecular physicochemical properties; and a verification module that predicts and evaluates the molecule-deliverer combination using molecular docking and ADMET. An evaluation result of the verification module is fed back to the molecule generation and optimization module to form a closed-loop optimization mechanism, so that an automatic process from target analysis to output of candidate drug molecules and matched delivery schemes thereof is realized. Compared with the prior art, the efficiency and success rate of early drug discovery can be improved.

The present disclosure is a screening procedure allowing the identification of inhibitors of cell envelope proteases (CEP) in pathogenic bacteria by using lactic acid bacteria (LAB). The screening platform can be used to screen compound libraries, and thus generate a high throughput evaluation of drug candidates, and as exemplified below one screening of 6808 compounds has resulted in the identification of 20 compounds inhibiting the CEP of Lactococcus lactis.

According to pharmaceutical composition for preventing or treating Parkinson's disease, containing a pyruvate dehydrogenase kinase (PDK) inhibitor as an active ingredient, a pharmaceutical preparation for preventing or treating Parkinson's disease, containing same, and a method for predicting a Parkinson's disease therapeutic effect of a candidate drug, of the present invention, it can be expected that a candidate drug treating Parkinson's disease and having an optimal therapeutic effect can be selected.

The invention discloses application of carbaspillin calcium in preparation of a medicine for treating hydrocephalus, belongs to the technical field of medicines for treating hydrocephalus, and particularly relates to application of carbaspillin calcium in preparation of a medicine for treating hydrocephalus, and the medicine takes carbaspillin calcium as a unique or main effective component. The effect of carbaspillin calcium in treating hydrocephalus is found for the first time, the fourth ventricle area of the hydrocephalus model zebrafish can be remarkably reduced, and the swimming distance, swimming time, swimming speed and rotational motion frequency of the hydrocephalus model zebrafish can be remarkably increased; experimental data provided by the invention show that the carbaspillin calcium has a huge application prospect in treatment of hydrocephalus, and an effective candidate drug is provided for relieving the treatment pain of a patient with hydrocephalus and reducing the treatment risk and cost; and the action range of the carbaspirin calcium is widened.

The invention discloses an application of cryptotanshinone in preparation of an anti-mycobacterium tuberculosis drug, and relates to the technical field of bioengineering. The molecular formula of the valerianin disclosed by the invention is C19H20O3. The mycobacterium tuberculosis is a mycobacterium tuberculosis H37Rv strain. Cryptotanshinone is disclosed as a natural-source compound for the first time, has the dual advantages of high efficiency and low toxicity, has an obvious effect of resisting mycobacterium tuberculosis, provides a brand new candidate drug scheme with development potential for solving the difficulty of tuberculosis treatment, and has great scientific value and application prospect.

The invention discloses an ultrashort-sequence antibacterial peptide rich in lysine and tryptophan, an antibacterial peptide hydrogel and application of the ultrashort-sequence antibacterial peptide and the antibacterial peptide hydrogel. The preparation method comprises the following steps: combining lysine and tryptophan to obtain polypeptide containing five or six amino acids; then amidation is carried out on the C terminal of the polypeptide, fatty acid chain modification is carried out on the N terminal and side chain amino groups, the ultra-short sequence antibacterial peptide rich in lysine and tryptophan is obtained, and the antibacterial peptide has broad-spectrum antibacterial activity for resisting gram-positive and gram-negative bacteria. An antibacterial peptide micelle self-assembly experiment shows that C12-2KW can be self-assembled into stable hydrogel in a 7.17 mu M PBS (Phosphate Buffer Solution), the hydrogel internally has a compact net-shaped structure, can completely cover the peritoneal injury surface and physically isolate the peritoneal injury surface from surrounding tissues, and has a good effect on treating wound infection caused by MRSA (Methicillin-Resistant Staphylococcus Aureus); meanwhile, the compound has the effect of resisting intestinal wall and abdominal wall adhesion after an operation, is low in toxicity, has a very good application prospect in the aspect of preparing clinical antibacterial drugs, and is expected to become a candidate drug of a novel antibiotic.

The invention discloses a five-membered sulfur-containing heterocyclic nucleoside lead compound and application thereof in anti-hand-foot-and-mouth virus active drugs, and belongs to the technical field of medicinal chemistry. A series of five-membered sulfur-containing heterocyclic ring nucleoside compounds are synthesized through a Sulfa-Michael / Aldol cascade reaction. A result shows that in an anti-EV-A71 virus test, the five-membered sulfur-containing heterocyclic ring nucleoside lead compounds 33a, 5b and 30b have relatively good anti-EV-A71 virus activity, and a new structural unit is provided for antiviral candidate drug molecules.

The invention relates to the field of biomedical application of inorganic materials, in particular to application of lanthanum carbonate in preparation of drugs for resisting liver cirrhosis and inhibiting liver inflammations, the drugs comprise lanthanum carbonate and pharmaceutically acceptable auxiliary materials, the drugs are ground and then mixed with food to prepare a drug mixture, and the drug mixture is prepared into the drug for resisting liver cirrhosis and inhibiting liver inflammations. The mass ratio of the lanthanum carbonate in the medicine mixture is 1-10%, and the mechanism of the lanthanum carbonate for treating the liver cirrhosis is as follows: interference or blocking of activation and proliferation of hepatic stellate cells, inhibition of extracellular matrix generation and promotion of extracellular matrix degradation. According to the invention, a rat liver cirrhosis model is constructed through chemical induction, and the effects of reversing liver cirrhosis and inhibiting liver inflammation are found when a rat is treated by taking lanthanum carbonate orally, so that a new candidate drug is provided for clinical treatment of liver cirrhosis.

The invention relates to the technical field of traditional Chinese medicine carbon dots, in particular to ligusticum wallichii carbon dots, a medicine and application. The ligusticum wallichii carbon dots disclosed by the invention are obtained by carbonizing ligusticum wallichii by a hydrothermal method, wherein the hydrothermal method carbonization is a hydrothermal reaction at 175-195 DEG C for 8-12 hours; research finds that the ligusticum wallichii carbon dots have the characteristic of treating myocardial apoptosis caused by myocardial ischemia reperfusion injury, and compared with ligusticum wallichii carbon dots synthesized by ligustrazine and a pyrolysis method, the ligusticum wallichii carbon dots have the advantage that the heart function can be better recovered. The invention provides a new candidate drug for treating myocardial ischemia reperfusion injury.

The invention provides application of Fe3O4 nanoparticles in preparation of a medicine for treating benign prostatic hyperplasia, and relates to the technical field of biological medicines. The invention further discloses application of the Fe3O4 nano-particles in preparation of a medicine for treating benign prostatic hyperplasia. The research result of the invention emphasizes that the ferroferric oxide nanoparticles are a promising candidate drug for targeted therapy of BPH and related prostate diseases, and new possibility is provided for treatment intervention of urinary surgery. The inventor studies the effect of the Fe3O4 nanoparticles in inhibiting benign prostatic hyperplasia. Results of the inventor show that the nanoparticles not only effectively reduce the proliferation rate of prostate cells, but also improve related biochemical indexes. Therefore, the polypeptide has potential application in treatment of prostatic hyperplasia.

The invention relates to the technical field of image analysis, in particular to a targeted drug curative effect prediction method based on image recognition, which comprises the following steps: acquiring tissue images and nuclear morphological parameters by a microscope, establishing a database in combination with transcripts, extracting an injury area, recognizing image features through a convolutional neural network, and constructing a prediction model; and inputting candidate drug molecular structures for molecular docking, calculating a repair progress by combining animal verification to establish a curative effect model, predicting drug scores and response time based on the curative effect model to generate a ranking list, screening high-score drug cells, verifying monitored survival, comparing, predicting and outputting a result. The method comprises the following steps: extracting a cell nucleus form, revealing a relation between damage and molecular abnormality in combination with a transcriptome, identifying a target spot corresponding to an abnormal mode and pathological change through deep learning, performing affinity prediction and animal verification on a drug structure, quantifying the repair progress by adopting image difference, and evaluating the curative effect with two dimensions of structure and function. And curative effect scores and response prediction are output to realize system sequencing, so that drug screening is more accurate and practical.

The invention discloses a novel application of emodin as an endonuclease inhibitor. The emodin inhibits replication and transmission of viruses by inhibiting the activity of NSP15 ribonuclease, and recovers host interferon reaction so as to enhance the antiviral effect. The application has the advantages that the action target of the emodin is defined, the effectiveness of the emodin in the aspect of preventing and treating coronavirus infection is further revealed, and the broad-spectrum antiviral potential of the emodin is embodied through the link of playing the antiviral effect by inhibiting the virus replication link; the researches provide candidate drugs and scientific basis for research and development of novel broad-spectrum anti-coronavirus drugs, and promote clinical application of the anti-virus traditional Chinese medicines.

The method comprises the following steps: acquiring compound data, biological target point data and biological activity data between a compound and a biological target point, establishing a compound and target point data set, performing feature extraction on the compound data and the biological target point data respectively, and obtaining a target point data set; performing feature fusion on the obtained compound feature vector and the biological target feature vector, and constructing a deep learning model; a prediction error of a focus loss function measurement model is defined, a deep learning model is trained, the trained deep learning model is evaluated through a Marius correlation coefficient, a compound and biological target data set is predicted, and candidate drugs are screened out; according to the method, the recognition rate of the model to real interaction is improved by defining the focus loss function, the robustness of the model is enhanced, in addition, a traditional Adam optimizer is improved, and the training efficiency and prediction precision of the model are improved through a quadratic regularization term and an adaptive learning rate strategy.

The invention discloses an application of PNO1 in construction of an ulcerative colitis animal model. PNO1 is applied to at least one of the following items: (1) preparing a product for diagnosing ulcerative colitis; (2) screening candidate drugs for preventing and / or treating ulcerative colitis as targets; and (3) constructing the ulcerative colitis animal model. The invention firstly finds that the PNO1 gene is positively correlated with the ulcerative colitis and can be used as a marker for diagnosing the ulcerative colitis, so that the ulcerative colitis is more accurately and quickly diagnosed, and a new therapeutic target and a new therapeutic approach are provided for treating colon cancer. The invention further constructs an ulcerative colitis animal model which can be better used for pathogenic mechanism and treatment research of ulcerative colitis and screening of colitis candidate drugs.

The invention provides application of B-AP15 in preparation of antituberculosis drugs, and particularly belongs to the technical field of drug preparation. The B-AP15 is used for preparing the antituberculous drugs and has relatively good inhibitory activity on MTB standard strains, MTB sensitive strains and clinical drug-resistant strains, so that a drug lead compound and a drug candidate are provided for development of the novel antituberculous drugs, and the B-AP15 has important significance on prevention and / or treatment of tuberculosis.

The invention belongs to the field of new application of medicines, and particularly relates to application of SIRT4-IN-1 in preparation of medicines for treating autoimmune diseases. It is found for the first time that SIRT4-IN-1 reduces the activation degree of immune response induced by HSV-1 virus infection by up-regulating acetylation modification of cGAS, inhibits abnormal activation of immune response in Trex1 deficient mouse cells and peripheral blood mononuclear cells of systemic lupus erythematosus patients, and improves abnormal activation of autoimmune response. The invention provides a new candidate drug for clinical treatment of systemic lupus erythematosus.

Disclosed in the present invention are a drug-based cancer inhibition sensitivity prediction method and device based on a graph neural network. The method comprises: acquiring a candidate drug and cancer cell line original data; extracting drug information features of the candidate drug, and expanding the drug information features; constructing a drug molecule feature vector according to the drug information features, and constructing a drug adjacency matrix, a node feature matrix, and an edge feature matrix by taking atoms of a drug as nodes and chemical bonds as edges; constructing and iterating a graph neural network model to obtain a drug graph feature; obtaining a drug characterization after the drug graph feature and the drug molecule feature vector are aggregated; acquiring and storing the expression quantities of gene expression, gene mutation, gene methylation and gene copy number, in a cancer cell line, of a gene sequence, and extracting a cancer cell line characterization; and performing feature fusion on the drug characterization and the cancer cell line characterization to obtain a drug-cancer cell line instance pair, inputting the instance pair into a drug-based cancer inhibition sensitivity prediction model, and predicting to obtain an IC50 value of the candidate drug in a cancer cell line environment.