144 results about "Virtual screening" patented technology

The invention discloses a hexapeptide with a hypoglycemic effect as well as a preparation method and application thereof, and belongs to the technical field of biological medicines. The amino acid sequence of the hexapeptide is Ile-Trp-Asp-Pro-His-Phe, and the amino acid sequence of the hexapeptide is as shown in the specification. The novel hexapeptide IWDPHF with prominent DPP-IV inhibition ability is successfully identified from mulberry leaf proteolysis products through liquid chromatography-mass spectrometry and a virtual screening method, the hexapeptide IWDPHF shows the blood glucose reducing effect superior to that of part of known peptides in an in-vitro enzyme activity inhibition experiment and a zebra fish hyperglycemia model, and no obvious side effect exists; the compound has a good potential of being developed into a hypoglycemic functional product or a drug lead compound. The invention further provides the mulberry leaf peptide with the peptide fragment IWDPHF, and the mulberry leaf peptide can be applied to preparation of drugs or food for reducing blood sugar. The invention provides a new scheme and theoretical basis for treatment of diabetes, and has good market prospect and application potential.

According to the screening method for the potential protein biomarkers and the drug targets of the gastric cancer, Mendel randomization analysis in a proteome range is adopted, the genetic causal relationship between circulating plasma protein and the risk of the gastric cancer is evaluated, and finally the remarkably related protein is identified. According to the screening method of the potential protein biomarker and the drug target of the gastric cancer, provided by the invention, the potential association between circulating plasma protein and the gastric cancer is systematically revealed by integrating Mendel randomization, single-cell RNA sequencing analysis, space transcriptome analysis, virtual drug screening, molecular docking, molecular dynamics simulation and other methods.

The invention relates to the field of drug discovery and delivery collaboration, in particular to an autonomous evolutionary drug discovery and delivery collaboration method and system based on a large language model. The method comprises the following steps: aiming at a given biological target three-dimensional structure, generating a candidate molecular library which is complementary with a target pocket and gives consideration to druggability through an SE (3) isovariant hybrid generation model; according to a two-stage funnel type high-throughput virtual screening process, screening out the molecule with the highest comprehensive potential from the candidate molecule library; generating a customized delivery scheme through a three-stage process; in a digital twinborn model for simulating a real in-vivo tumor microenvironment, a targeted delivery process of a drug and carrier complex is simulated, and efficiency is evaluated; atomic-scale performance confirmation is carried out on a medicine, carrier and target point ternary system through molecular dynamics simulation. The invention is suitable for drug research and development.

The invention discloses a generative adversarial network optimization method for small molecule drug virtual screening, and belongs to the field of computer-aided drug design. The method comprises the following steps: constructing a small molecule drug data set; building a GAN basic model comprising a generator and a discriminator; performing multi-objective optimization training (optimizing chemical effectiveness, combining affinity and structural diversity) on the model through a joint loss function; generating candidate molecules by using the optimized model, and screening through a threshold value; and carrying out molecular docking verification on the screening result and outputting a final result. The quality of generated molecules is improved through multi-objective optimization, the drug research and development cycle is shortened, and the method is suitable for efficiently screening potential drug molecules.

The application discloses a virtual screening method of a small-molecule compound targeting TLR4. The application screens potential compounds capable of combining with TLR4 through three-dimensional molecular docking, and preliminarily proves that three compounds, Z1410232649, F27210326 and HY-N0029, have better TLR4 inhibiting effects through experimental verification. Among them, Z1410232649 performs most outstandingly, can significantly inhibit the release of inflammatory factors IL-6, TNF-alpha and IFN-gamma induced by LPS, and can be used as a novel anti-inflammatory drug or immunotherapy drug targeting TLR4.

The invention discloses a urate oxidase mutant and application thereof in improving the thermal stability of urate oxidase, and belongs to the technical field of biology. The urate oxidase mutant disclosed by the invention is T68L / T75S / E222D / K299E, T68L / T75S / K299E or T75S / K299E, and the urate oxidase mutant disclosed by the invention is T68L / T75S / K299E. According to the method, the key sites influencing the thermal stability are mined in the modes of directed evolution, high-throughput screening, multiple virtual screening and the like, and the stability is improved through mutation. And finally, a plurality of key sites and mutants influencing the stability are excavated, and the thermal stability is improved.

The invention relates to the technical field of biological medicines, in particular to a preparation method of an inhibitor targeting a MAX-PD-L1 promoter specific binding motif and a double-target inhibitor, through ChIP-seq and site-directed mutagenesis experiments, a core binding motif of MAX and a PD-L1 promoter, such as 5 '-CAC [GA] TG-3', is defined, it is ensured that the inhibitor only targets a key site of MAX-PD-L1 interaction, and the activity of the MAX-PD-L1 promoter specific binding motif is improved. The off-target effect is avoided, and a high-specificity target spot is provided for subsequent inhibitor design. The cell permeability of the DNA aptamer screened based on the specific binding motif is improved after cholesterol modification, and the affinity of the DNA aptamer is obviously higher than that of a traditional antibody. A small molecule compound virtually screened through a molecular docking model is optimized through hydrogen bond and hydrophobic interaction, and then the binding affinity with MAX is improved. After treatment with the inhibitor, the combination inhibition rate of MAX and the PD-L1 promoter is high, the transcriptional activity of PD-L1 is obviously reduced, the killing rate of T cells to tumor cells is also improved, and immune escape is effectively blocked.

The invention discloses a method for preparing a VA-ECMO lung injury treatment medicine by using ginkgolide A to regulate YARS1, and relates to the technical field of biological medicine, the method comprises the following steps: by using ginkgolide A as a YARS1 protein regulator, preparing the medicine for treating the VA-ECMO lung injury through virtual screening, binding affinity confirmation and cell efficacy confirmation; wherein the virtual screening is based on a protein structure model of YARS1, and bilobalide A with high affinity binding energy with YARS1 is screened out through molecular docking. It is proved that ginkgolide A can effectively improve the lung ventilation function by regulating YARS1, repair the alveolar epithelial barrier structure and inhibit the inflammatory oxidative stress reaction, and the lung injury treatment effect and clinical transformation safety under the support of VA-ECMO are improved.

The invention belongs to the technical field of medicinal chemistry, and particularly relates to a quinoxaline compound as well as a preparation method and application thereof. Specifically, the quinoxaline compound provided by the invention is screened by adopting virtual screening and pharmacophore modes, is novel in structure, has relatively good inhibitory activity on MELK, and solves the problem of insufficient development of an existing MELK inhibitor that the activity is not ideal enough, the chemical structure is not diversified enough and the like.

The invention discloses a macromolecular protein cutting method and system based on multi-source protein feature scoring, and a storage medium, and belongs to the field of computational biology and intelligent drug research and development. In order to solve the technical problem that macromolecular protein is difficult to directly input into an existing calculation model, an amino acid position cutting comprehensive score is obtained by obtaining multi-source feature data such as a protein disorder region and structural domain annotation, candidate cutting sites are screened and a final cutting scheme is determined in combination with double constraints of a structural domain hard boundary and fragment length, and the method is suitable for large-scale industrial production. And generating a protein fragment adaptive to downstream calculation. According to the method, the integrity of the protein structural domain is guaranteed, the cut fragment can be directly used as model input such as AlphaFold, the accuracy and stability of structural prediction and molecular docking are improved, the method is suitable for scenes such as virtual screening and computer-aided drug design, and the problem that an existing cutting method is lack of systematic consideration is solved.

The application provides a target-specific virtual screening method and system based on machine learning. Active molecules and inactive molecules are docked with multiple conformations of a target, and protein-ligand interaction features of the docked molecules and related features of the ligands are extracted as input features of a machine learning model. A scoring function model is constructed using multiple machine learning models, and based on the advantages of multiple target-specific scoring function models, an integrated target-specific scoring function model is finally obtained by combining a model integration method. The integrated model can more effectively process complex protein-ligand interaction data, has excellent prediction performance and virtual screening capability, provides more reliable prediction results, and improves the virtual screening capability.

The invention relates to the technical field of biology, in particular to a method for improving affinity of a nano antibody based on computer-aided design. According to the method, a series of bioinformatics tools for nano antibody affinity maturation are investigated and researched in literatures, and part of databases, servers and software are optimized to construct a set of computer-aided design (CAD) nano antibody affinity improvement method by evaluating the operability and the improvement effect of the tools. In order to verify the effectiveness and universality of the method, based on the method, a high-affinity mutant nano antibody is virtually screened out of an Anti-Nectin-4 camel source nano antibody NBNT-1 and an Anti-PD-L1 shark source nano antibody NBNT4 screened in a synthetic library through model construction, model evaluation, site prediction, molecular docking, structural analysis, mutation prediction and mutation evaluation. Traditional in-vitro affinity maturation methods, such as error-prone PCR, are low in screening efficiency, large in randomness introduced by mutation, long in experimental period, large in workload and difficult to accurately optimize the affinity of target molecules. According to the method, various defects of a traditional in-vitro affinity maturation method are overcome, and the success rate and efficiency of affinity maturation are improved.

The invention discloses a machine learning-based inhibitor drug screening method for targeting KRAS G12D mutation, and the method is used for predicting the binding capacity of candidate small molecules and KRAS G12D protein targets by constructing an integrated graph neural network (GNN) and molecular feature embedded deep learning model. Compared with a traditional virtual screening method, the method has remarkable advantages in the aspects of improving the recognition capacity of KRAS G12D mutation specific small molecules and reducing the false positive rate and has high application potential and industrial transformation value, and molecular dynamics simulation results of screened compounds show that compared with existing KRAS G12D mutation targeted drugs in research, the method has the advantages that the application potential and industrial transformation value of the screened compounds are greatly improved, and the application prospect of the KRAS G12D mutation targeted drugs is widened. The screened compound has a more stable binding trend with targeting protein in MD simulation, is expected to become a new KRAS G12D targeting inhibitor, and provides new possibility for treating pancreatic cancer.

The application provides a HBV inhibitor screening method based on a molecule-gene interaction constraint graph convolution network. In view of the limitation of a traditional drug discovery method in processing complex biological data, the application is based on a constructed compound library verified by anti-HBV in-vitro activity, a plurality of gene targets associated with the corresponding compound and an interaction network thereof, a graph data processing capacity of a graph convolution network model is used, and a molecule-gene interaction constraint graph convolution network model is constructed. The model combines an interaction matrix of a target protein corresponding to the gene, a gene feature matrix and a compound activity label, and effectively predicts the biological activity category of the compound. The specific steps include data processing, graph data generation, graph convolution network model training, hyperparameter optimization and model evaluation. The model parameter AUC value is 0.97, and the model effect is good. The application provides a new path and idea for virtual screening of anti-HBV drugs, and has potential application value.

The invention discloses haliotis discus hannai I-type collagen peptide as well as a screening method and application thereof, and belongs to the technical field of bioactive peptides. The peptide sequences of the haliotis discus hannai I type collagen peptide are GAAGDK and DSQSAR; the screening method specifically comprises the following steps: (1) virtual enzymolysis of the haliotis discus hannai I-type collagen; (2) screening the bioactive peptide; and (3) molecular docking. According to the invention, through rational design and a virtual screening strategy, a human gastrointestinal tract digestion process is simulated to carry out targeted virtual enzymolysis, a multi-target molecular docking technology is combined, brand-new bifunctional peptides GAAGDK and DSQSAR are accurately predicted and screened from a specific collagen sequence, and aiming at a dual-action mechanism of AGE-RAGE axis and oxidative stress, the application has the advantages of high sensitivity, high sensitivity and high stability. The composition has remarkable synergistic interaction potential in the aspects of preventing diabetic complications and delaying skin and body senescence, and a brand new core raw material is provided for developing next-generation anti-saccharification functional food and skin care products.

The invention discloses a parameterized constraint system and method for efflux pump avoidance and off-target risk inhibition, which are applied to the field of biological medicines, and aims to solve the dual problem that toxic risks are caused by efflux pump mediated drug resistance enhancement and off-target combination of existing antibacterial drugs. The method comprises the following steps: constructing an efflux pump identification avoidance five-dimensional feature space and a target spot specificity geometric-electrical constraint boundary, performing structure mapping and deviation degree evaluation on candidate molecules, and triggering directional modification; the target matching is verified through molecular docking, and if the target does not reach the standard, the pharmacophore is locally adjusted; virtual screening is carried out based on an off-target protein database, a secondary structure disturbance mechanism is started for high-risk molecules, and a stereoisomerism or electrical reversal group is introduced to destroy non-target binding; according to the method, collaborative optimization of antibacterial efficacy, drug resistance avoidance and safety risk is achieved, and the research and development efficiency and druggability of candidate molecules are remarkably improved.

This application relates to a source-aware activity ranking-based method for screening DPP-IV repressive peptides, comprising: constructing a training dataset containing positive samples and at least three levels of negative samples; extracting multimodal features of peptides, including at least sequence deep semantic embedding features and pocket structure features; explicitly aligning the above features using a cross-attention mechanism to generate fusion features; inputting the fusion features into the classification branch and ranking branch of a decoupled prediction architecture, outputting classification probability and activity ranking score respectively, wherein the ranking branch uses an independent ranking model and is trained based on preference pairs constructed from data within the same assay source; and performing virtual screening output by combining classification probability, activity ranking score, multidimensional confidence judgment, and ADMET safety screening results. This application achieves structurally interpretable characterization of substrate-enzyme binding modes and improves the statistical significance and generalization stability of peptide activity ranking under cross-laboratory batch effects.

The invention provides application of a virtual screening compound in preparation of an NLRP3 inflammasome inhibitor, and relates to the technical field of medicines.The application is characterized in that NLRP3 protein is used as a target point, and LRamp is adopted; an RF-ECFP4 integrated machine learning model is used for carrying out preliminary screening on a ZINC compound database, and nine small molecule compounds with high binding affinity are finally obtained by combining molecular docking, clustering analysis, in-vitro activity detection and ADMET property prediction. Experimental results show that the compounds can be stably combined with NLRP3 protein key residues, can significantly inhibit expression of inflammatory factors IL-1beta, IL-18 and TNF-alpha in an in-vitro level, and show good drug-likeness, oral absorption characteristic and safety. The compounds can be used for preparing drugs for treating NLRP3 inflammasome abnormal activation related diseases, and important lead compounds are provided for developing novel anti-inflammatory drugs.

The invention belongs to the technical field of medicines, and particularly relates to application of a compound targeting DOCK1 protein in preparation of a medicine for treating leukemia. The compound capable of being combined with the DOCK1 protein is obtained through virtual screening and a surface plasmon resonance experiment; cell experiments verify that the related compounds can inhibit the survival rate of acute myelogenous leukemia cells, induce apoptosis of the acute myelogenous leukemia cells and weaken the colony ability of the acute myelogenous leukemia cells. The compound provided by the invention inhibits proliferation and development of acute myelogenous leukemia cells, reduces damage to normal tissues and improves tolerance of patients by targeting DOCK1 protein and inhibiting the activity of the DOCK1 protein, and provides a new strategy for treatment of acute myelogenous leukemia.

The invention relates to pressed salted duck antioxidant peptide and a preparation method thereof. The method comprises the following steps: carrying out synergistic inoculation and fermentation treatment on lactobacillus curvatus and staphylococcus mimicus, and carrying out pickling, air drying and peptide extraction processes to obtain the small molecular peptide with the molecular weight of less than 10 kDa. Through nano-LC-MS / MS (Liquid Chromatography-Mass Spectrometry / Mass Spectrometry) detection, computer virtual screening and molecular docking, three peptide sequences, namely GIRLGLDPKL, PAPAAKAGASTGRIV and PEKPPTIDWA, with remarkable antioxidant activity are determined. According to the method, protein degradation can be effectively promoted, the yield of the antioxidant peptide is increased, and the obtained peptide has good stability and safety and is suitable for development of functional food and health care products.

This invention relates to the field of bio-intelligent manufacturing technology, and particularly to an intelligent manufacturing equipment and method for a multi-biological targeted nutritional protection compound preparation. The equipment includes a manufacturing shell, the interior of which is equipped with an AI molecular design and virtual screening unit, an intelligent targeted delivery system preparation unit, a multi-scale online quality monitoring module, a four-biological effect simulation and verification unit, and a central control and digital twin server. In this invention, when vibrations generated during the repeated reciprocating motion of the microfluidic sampling needle and the use of other components cause a misalignment between the microfluidic sampling needle and the support frame, the pointer slides on the surface of the scale plate. The deviation distance is magnified and displayed using a magnifying glass. Then, a drive source is activated, causing the threaded rod to rotate, which in turn moves the pull plate left and right. This pushes the moving frame, the moving plate, and the magnetic block to slide on the electromagnet, thereby adjusting the position of the support frame and the microfluidic sampling needle, and returning the pointer to its initial position.

This application discloses a method for predicting the quantitative activity of endocrine disruptors, relating to the field of virtual screening of endocrine disruptors. The method includes: acquiring in vitro experimental data of nuclear receptors and removing duplicate data, as well as removing compound sets that do not contain the simplified molecular linear input canonical (SMILES) representation; using a molecular fingerprinting method to extract the primary, secondary, and tertiary structural features of the compounds. For each compound cluster, a quantitative prediction model based on machine learning or quantitative read-across is constructed to predict the quantitative activity value of the compound. Addressing the low efficiency of existing methods for predicting the quantitative activity of endocrine disruptors, this application extracts multi-level structural features of the compounds and constructs corresponding quantitative prediction models for compound structural clusters of different sizes. Through molecular docking and molecular dynamics simulations, the interaction mechanism between endocrine disruptors and nuclear receptors is studied from a structural biology perspective, thus improving efficiency.

The invention discloses a drug virtual screening task scheduling method and device based on an intelligent agent and a medium. The method comprises the steps that drug virtual screening task information is received; a directed acyclic graph of at least one task execution path is determined according to the medicine virtual screening task information through the trained intelligent model, the directed acyclic graph of the task execution path is composed of a plurality of cascaded atomic task nodes, and each atomic task node is responsible for a corresponding medicine virtual screening sub-task; according to the directed acyclic graph of the task execution path, determining a calling sequence of services matched with the atomic task node; and calling the services according to the calling sequence of the services so as to execute the medicine virtual screening sub-tasks in charge of the atomic task nodes through the services, and the services matched with the atomic task nodes are obtained by packaging a medicine virtual screening algorithm or tool through a model context protocol (MCP). Automation and intelligentization of the whole process of virtual drug screening are achieved, the use threshold is greatly lowered, and the drug research and development efficiency is improved.

The invention discloses an MIF small-molecule inhibitor as well as a screening method and application thereof, and belongs to the technical field of medicinal chemistry. The inhibitor is composed of seven compounds with specific structures and pharmaceutically acceptable salts thereof, and the compounds and the pharmaceutically acceptable salts can effectively inhibit the tautomerase activity of MIF. The lead compounds are efficiently found from a large number of compounds through a computer-aided virtual screening method. In-vitro and in-vivo experiments show that the compound F3277-0933, especially the compound F3277-0933, shows remarkable MIF inhibitory activity and anti-tumor effect in enzyme level, cellular level and animal models, and the effect of the compound F3277-0933 is superior to that of an existing inhibitor ISO-1. The MIF small-molecule inhibitor disclosed by the invention provides a new candidate compound for developing medicines for treating MIF-related diseases such as colorectal cancer.

The invention discloses a high-throughput drug membrane permeability calculation and analysis method and system based on a coarseness model and a storage medium. The method comprises the following steps: constructing a coarseness simulation system containing a phospholipid bilayer and a solvent environment; all-atom structure information of to-be-detected drug molecules is obtained, and molecular fragment correspondence is automatically predicted through a machine learning model based on a random forest, so that a coarse-grained topological structure compatible with a Martini force field is generated; placing the drug coarseness model in a simulation system, and executing molecular dynamics simulation with umbrella-shaped sampling along the normal direction of the membrane; and based on the simulated trajectory, reconstructing an average force potential by using a weighted histogram analysis method, and calculating a membrane permeability coefficient according to a heterogeneous dissolution-diffusion model. According to the method, machine learning and physical simulation are combined, full automation of small molecule parameterization is achieved, the problems that a traditional method depends on artificial experience and is low in efficiency are solved, and high-throughput and high-precision virtual screening of a large-scale compound library can be achieved with low calculation cost.

The application provides a kinase inhibitor leading compound, a virtual screening method thereof and application of the kinase inhibitor leading compound in preparation of branched-chain alpha-keto acid dehydrogenase kinase inhibitors and / or drugs for treating diseases mediated by branched-chain alpha-keto acid dehydrogenase kinase. The virtual screening method provided by the application combines various virtual screening platforms to screen a large-scale compound library, improves the true positive rate of screening results, reduces the number of compounds needing experimental screening, and saves screening time and cost. In addition, the compounds I-III screened out with good binding affinity to BCKDK can be used in researches on targeting BCKDK to treat major diseases such as obesity, insulin resistance, maple syrup urine disease, neurological dysfunction, liver cancer, colorectal cancer and tumor cachexia.

The invention belongs to the technical field of molecular biology, and particularly discloses a theophylline aptamer and a virtual screening method and application thereof. The theophylline aptamer is selected from one or more of MUT9, MUT16, MUT67, MUT78 or MUT89. The invention further discloses a preparation method of the theophylline aptamer. The invention discloses a theophylline aptamer as well as a virtual screening method and application thereof, the theophylline aptamer is high in affinity and specificity, the virtual screening method remarkably improves the accuracy and efficiency of virtual screening, the theophylline aptamer can be quickly obtained at low cost, and a powerful calculation tool is provided for rational design and application of the aptamer.

The invention relates to a GNN-RNN hybrid network-based small sample serum toxicity parameter prediction method and application, and the prediction method comprises the steps: inputting an SMILES character string of a to-be-detected compound, processing the character string through a trained serum toxicity parameter prediction model, and outputting a predicted toxicity parameter dichotomy result, the step of training the serum toxicity parameter prediction model comprises the steps of obtaining descriptor features, obtaining graph features, obtaining sequence features, fusing multi-modal features and training and optimizing the model. The prediction method and application provided by the invention are a calculation method for performing small sample learning by using a graph neural network, a recurrent neural network and meta learning. The method can predict abnormal conditions of specific serum toxicity parameters possibly caused by small molecule compounds in vitro or in vivo, and can be used as an efficient and low-cost virtual screening tool in the early stage of drug research and development.

The invention discloses application of a compound in preparation of a medicine for treating or relieving ADPGK activation related concurrent diseases in chronic kidney diseases. The compound is found to be capable of effectively inhibiting the activity of ADPGK through computer virtual screening in combination with an in-vitro platelet activation experiment. In CKD patient and mouse models, the Z809269780 significantly reduces the glycolysis flux of platelets, lactic acid generation and RHOA lactylation level, thereby inhibiting the excessive activation and high reactivity of the platelets, and effectively relieving thrombosis events (such as platelet aggregation, adhesion, blood clot retraction and arterial thrombosis). Animal experiments show that intraperitoneal injection of the Z809269780 (10 mg / kg) has a good antithrombotic effect, and the Z809269780 does not show obvious toxicity under the dosage of 20 mg / kg. The invention provides a safe and effective novel targeted treatment strategy for preventing thrombotic complications of CKD patients.

The invention relates to the technical field of machine learning models, and discloses an end-to-end drug design method and device based on multi-agent collaboration.The method comprises the steps that a natural language instruction is analyzed through coordination agents, and a drug design target is determined; obtaining protein structure information and background knowledge information related to a drug design target through a retrieval agent based on the drug design target; generating an initial candidate molecule set conforming to a drug design target based on protein structure information through a generation agent; performing multi-dimensional virtual screening on candidate molecules in the initial candidate molecule set through an evaluation agent, and generating an evaluation report containing prediction attributes of the candidate molecules; whether candidate molecules meeting preset optimization conditions exist or not is judged based on the evaluation report through the coordination agent, and finally the candidate molecules meeting the preset optimization conditions are output to serve as final candidate molecules. Through coordinated operation of multiple agents, the automation level and efficiency of drug design can be effectively improved.