37 results about "Molecular vector" patented technology

The invention provides a molecular characterization model training method, a molecular characterization model retrieval method and a molecular characterization model retrieval device, which are applied to the technical field of artificial intelligence. The model training method comprises the following steps: acquiring a training sample set which comprises a molecular character string sample and a molecular text description sample; performing feature coding on the molecular character string sample through an encoder to obtain a first molecular vector representation of the molecular character string sample, and performing feature coding on the molecular text description sample to obtain a first text vector representation of the molecular text description sample; aggregating the first molecular vector representation into at least one first molecular feature class by utilizing a clustering algorithm, and aggregating the first text vector representation into at least one first text feature class by utilizing the clustering algorithm; obtaining a first loss function according to the at least one first molecular feature class and the at least one first text feature class; and according to the first loss function, updating parameters of the encoder to obtain the molecular characterization model. Therefore, the accuracy of chemical analysis and interpretation of molecules can be improved.

The disclosure provides, in various embodiments, compositions, such as polypeptides, polynucleotides, gene editing system, small molecules, vectors or host cells, that comprises and / or modulate expression or activity of immune regulation-associated proteins. The disclosure also provides, in various embodiments, methods of treating aging, senescence, fibrosis, a metabolic disease, cardiovascular disease, an endocrine-associated disorder, a genetic disease, cancer, an infection, an immunological disease, an indication treated with hormone, growth factor and / or protein replacement, or a combination thereof using an agent that comprises and / or modulates expression or activity of an immune regulation-associated protein and methods of identifying said agent.

This platform is a privacy-preserving, federated learning system designed to integrate whole-slide digital pathology images with matched molecular profiling and clinical metadata for improved diagnosis, subtyping, and prognostic estimation of gynecologic tumors. The architecture comprises local institutional nodes that retain raw patient data while participating in distributed model training coordinated by a central orchestration server. Each local node preprocesses whole-slide images into patch-level tensors, extracts visual embeddings via convolutional backbones, and processes molecular vectors (e.g., somatic mutations, expression summaries, copy-number measures) via a molecular encoder. A multimodal fusion module - implemented as an attention- based transformer - integrates image and molecular embeddings into a unified representation used by multi-task heads for classification (histologic subtype, diagnostic label) and regression (risk score). The federated learning controller aggregates encrypted model updates (FedAvg) and returns improved global weights without exchanging raw data, enabling cross-site generalization while preserving patient privacy. Explainability components generate attention maps and tile-level saliency (Grad-CAM style) linked to molecular features, providing interpretable morpho- molecular correlations to pathologists. The platform supports API integration with PACS / LIMS, conforms to privacy standards via optional differential privacy and secure aggregation layers, and is extensible to additional omics modalities or transfer / fine-tuning workflows for related tumor types. By combining multimodal fusion, federated training, and clinician-facing interpretability, the system accelerates robust, generalizable AI for precision pathology in gynecologic oncology.

Provided are a broad-spectrum anti-COVID-19 vaccine immunogen composition, and the preparation and a use thereof. Specifically, provided is an immunogen composition, comprising an RBD recombinant chimeric antigen, wherein the chimeric antigen comprises S protein RBD domains from two or more COVID-19 subtypes, or functional fragments thereof. The immunogen composition can further comprise a multimerization domain and a T-cell immunogen domain. Further provided are a use of the immunogen composition, a corresponding encoding molecule therefor, a vector, and / or a host cell in preparing an anti-COVID-19 vaccine. The vaccine can induce a broad-spectrum protective effect against a prototype strain and various currently prevalent variants, and can also elicit a potent cross-protective T-cell response, thereby achieving effective and broad-spectrum prevention against COVID-19 and achieving a protective effect against other coronaviruses.

The application relates to the technical field of molecular property prediction and digital medical treatment, and discloses a molecular property prediction model training method, a storage medium, a computer device and a molecular property prediction device. The method comprises the following steps: acquiring molecular graphs of a plurality of sample molecules, splitting the molecular graphs to obtain candidate graph prompts, extracting a preset number of candidate graph prompts as target graph prompts according to a preset candidate graph prompt extraction rule; encoding the target graph prompts into target graph prompt vectors, calculating the importance weights of the target graph prompt vectors on the molecular graphs, calculating a global graph prompt vector according to the target graph prompt vectors and the importance weights; splicing the global graph prompt vector with feature vectors of the sample molecules respectively to obtain molecular vectors of the sample molecules; and training a molecular property prediction model according to preset molecular property labels corresponding to the sample molecules and the molecular vectors. The trained model can simultaneously predict a plurality of molecular properties, and the drug research and development efficiency is improved.

The present invention discloses a 3'UTR for improving mRNA translation efficiency and its application, belonging to the field of biotechnology. The present invention provides a 3'UTR sequence for regulating mRNA translation efficiency, a corresponding DNA molecule, a vector, a host cell, and an RNA molecule. The present invention also provides a method for improving mRNA translation efficiency and related applications. The 3'UTR sequence provided by the present invention can significantly improve the expression efficiency of mRNA. Regardless of whether the base is modified or unmodified, the improved mRNA translation efficiency is 2-3 times that of a commonly used 3'UTR sequence.

The present invention provides, in part, a protein-drug conjugate comprising an anti-fibroblast growth factor receptor 3 (FGFR3) (e.g., human FGFR3) antigen-binding protein (e.g., scFv, Fab) conjugated to a molecular cargo (e.g., a polynucleotide, a polypeptide, a liposome, or a lipid nanoparticle), for delivering the molecular cargo to a target tissue (e.g., the brain). Methods are provided for treating various diseases or disorders, such as neurological disorders, with the conjugate.

The disclosure provides, in various embodiments, compositions, such as polypeptides, polynucleotides, gene editing systems, small molecules, vectors or host cells, that comprise and / or modulate expression or activity of immune regulation-associated proteins, such as cytokines. The disclosure also provides, in various embodiments, methods of treating inflammation, aging, senescence, fibrosis, autoimmunity, cancer, an infection, and / or an immunological disease using an agent that comprises and / or modulates expression or activity of an immune regulation-associated protein, and methods of identifying said agent.

Provided are a phytase mutant and a coding DNA molecule thereof, a vector, and a host cell. The phytase mutant comprises an amino acid sequence having at least 90% identity with SEQ ID NO: 3, and compared with SEQ ID NO: 3, and contains an amino acid substitution at at least one position selected from the group consisting of 36, 126, 211, 253, 258, and 266. The heat resistance of the mutant is significantly improved, thus facilitating the wide application of phytase in feed.

The application discloses a plant-expressed varicella-zoster virus gB recombinant antigen and a preparation method, product and application thereof, and belongs to the technical field of plant molecular biology and vaccine engineering. The technical problems to be solved are that the existing VZV gB protein has low heterologous expression, poor stability and insufficient antigen activity; the existing VZV vaccine has high production cost, is difficult to popularize and has a single antigen with an immune escape risk; and the plant expression system is not mature in VZV gB antigen production, and lacks a complete preparation scheme and related products. The technical solution is that the natural VZV gB protein is modified, a furin protease cleavage site is knocked out, and a H527P mutation is introduced, related nucleic acid molecules, vectors and plant source cells are constructed, high-activity antigens are obtained through culture and purification, and the high-activity antigens are applied to the preparation of VZV drugs / vaccines, and have the advantages of low cost, high safety and strong immunogenicity.

The invention relates to a preparation method of a beta-endarphin (beta-endarphin, human) detection kit using a chemiluminescence immunoassay technology, and particularly relates to a preparation method of a beta-endarphin (beta-endarphin, human) detection kit. Endophalin is also called as brain endophine, is a morphine-like biochemical synthetic hormone and is secreted by pituitary gland. Beta-enorphin is small in molecular weight and poor in immunogenicity and has various structural analogues, so that when a corresponding antibody is prepared, firstly, a proper derivative site needs to be selected, and a derived hapten is coupled with a specific macromolecular carrier to prepare a complete antigen. The invention mainly relates to the design and synthesis of a beta-enorphin hapten, the preparation of a beta-enorphin complete antigen and an anti-beta-enorphin antibody, a method for measuring the concentration of beta-enorphin, and composition and components of a reagent. The design and synthesis of the hapten mainly comprise design and chemical synthesis of a beta-ennorphin derivative. The beta-ennorphin derivative disclosed by the invention has a structure as shown in a formula (I) which is described in the specification.

The disclosure provides, in various embodiments, compositions, such as polypeptides, polynucleotides, gene editing systems, small molecules, vectors or host cells, that comprise and / or modulate expression or activity of immune regulation-associated proteins, such as cytokines. The disclosure also provides, in various embodiments, methods of treating a disease or condition (e.g., a disease or condition associated with the Genome-Wide Association Study (GWAS), the Cancer Genome Atlas (TCGA), whole genome sequencing, phenome-wide association study (PheWAS), expression quantitative trait locus (cQTL) studies, or a combination thereof) using an agent that comprises and / or modulates expression or activity of an immune regulation-associated protein, and methods of identifying said agent.

This application belongs to the field of immunoassay technology, specifically relating to specific binding proteins of hepatitis B viruses (MHBs), nucleic acid molecules, vectors, cells, detection kits, and their preparation methods and applications. This application provides a specific binding protein of MHBs with specific CDRs, exhibiting high affinity and specificity. It solves the problem in existing technologies of being unable to distinguish between large, medium, and small hepatitis B virus proteins, and ensures that the antibody does not cross-react with large and small proteins, thus improving detection specificity and avoiding false positive results. The specific binding protein of MHBs in this application can bind to a chemiluminescent detection system, thereby achieving highly sensitive detection of MHB antigen levels in clinical samples, with high consistency with nucleic acid detection results, providing an important tool for monitoring hepatitis B infection status and disease progression.

This application belongs to the field of immunoassay technology, specifically relating to LHBs-specific binding proteins, nucleic acid molecules, vectors, cells, detection kits, and their preparation methods and applications. This application provides an LHBs-specific binding protein with specific CDRs, exhibiting high affinity and specificity. It solves the problem in existing technologies of being unable to distinguish between large, medium, and small hepatitis B virus proteins, and ensures that the antibody does not cross-react with medium and small proteins, thus improving detection specificity and avoiding false positive results. The LHBs-specific binding protein of this application can bind to chemiluminescent detection systems, thereby achieving highly sensitive detection of LHBs antigen levels in clinical samples, with high consistency with nucleic acid detection results, providing an important tool for monitoring hepatitis B infection status and disease progression.

The invention discloses a compound fat solubility prediction method based on a multilevel feature fusion graph neural network, and relates to the field of computational pharmacology and chemical information.The method comprises the steps that an atomic-scale graph structure, molecular-scale global features and group-scale substructure features of a target molecular compound are obtained; performing feature extraction on the atomic-scale graph structure to obtain an embedded representation of each atom in the target molecular compound, and performing global average pooling on the embedded representation of each atom to obtain an atomic vector; normalizing the molecular-level global features to form molecular vectors; splicing the atom vector, the molecule vector and the substructure vector to obtain a global vector; predicting the fat solubility of the target molecular compound according to the global vector; according to the method, an atom-molecule-substructure multilevel characteristic system is constructed, and the characteristics with different granularities and different properties are organically combined for combined prediction, so that more comprehensive molecular characterization and more accurate fat solubility prediction of molecular compounds are realized.

The invention discloses a knee joint targeting stem cell exosome composition as well as a preparation method and application thereof, and relates to the technical field of biological medicines. The composition comprises a core-shell structure consisting of a stem cell exosome and a targeting stabilized functional macromolecule coating the surface of the stem cell exosome, the targeting stabilizing functional macromolecule is formed by connecting a biocompatible polysaccharide skeleton, a membrane anchoring hydrophobic group and a knee joint focus targeting ligand through covalent bonds. Through integrated molecular design, a stabilizing function and a targeting function are integrated on the same macromolecular carrier, and the macromolecular carrier is worn on the surface of the exosome through a self-assembly technology, so that the technical contradiction that stability and targeting cannot be achieved at the same time in an existing stem cell exosome technology is solved.

The application discloses a kind of knee joint targeting stem cell exosome compositions and preparation method and application thereof, it is related to biological medicine technical field.The composition includes the core-shell structure that is made of stem cell exosome and the targeting stable functional macromolecule that is coated on the surface of stem cell exosome;The targeting stable functional macromolecule is made of biocompatible polysaccharide skeleton, membrane anchoring hydrophobic group and knee joint lesion targeting ligand by covalent bond connection composition.The application is integrated in the same macromolecule carrier by integrated molecular design, and by self-assembly technology, it is " dressed " on the surface of exosome, solves the technical contradiction that stability and targeting cannot be obtained in existing stem cell exosome technology.

Short hairpin RNA (shRNA) molecules that target human endogenous retrovirus K (HERV-K) nucleic acid, as well as vectors containing the coding sequences for the shRNA molecules, are described. In some instances, the vector containing the shRNA coding sequences is an adeno-associated virus (AAV) vector, such as a self-complementary AAV vector. Use of the shRNA molecules, vectors and compositions thereof for the treatment of neurological disorders, such as motor neuron diseases, and cancer is also described.

The application discloses a compound liposolubility prediction method based on a multi-level feature fusion graph neural network, relates to the field of computational pharmacology and chemical informatics, and comprises the following steps: acquiring an atomic-level graph structure, a molecular-level global feature and a group-level substructure feature of a target molecular compound; performing feature extraction on the atomic-level graph structure to obtain an embedding representation of each atom in the target molecular compound, and performing global average pooling on the embedding representation of each atom to obtain an atomic vector; performing normalization on the molecular-level global feature to form a molecular vector; splicing the atomic vector, the molecular vector and a substructure vector to obtain a global vector; predicting the liposolubility of the target molecular compound according to the global vector; and constructing a multi-level feature system of 'atoms-molecules-substructures', and combining the features with different granularities and different properties organically to perform joint prediction, so that more comprehensive molecular representation and more accurate liposolubility prediction of the molecular compound are realized.

Provided herein are engineered Epstein-Barr virus nuclear antigen 1 (EBNA1), coding molecules thereof, vectors and mammalian cell expression systems comprising the same, and polypeptide of interest recombinantly produced by the foregoing. Also provided are methods for the preparation of the engineered EBNA1s, coding molecules thereof, vectors and mammalian cell expression systems and methods for using the same in recombinant expression.

The invention discloses a chromatographic outflow curve prediction method and system based on ensemble learning and computational chemistry, and belongs to the field of analytical chemistry and machine learning. The chromatographic outflow curve prediction method based on ensemble learning and computational chemistry comprises the following steps: acquiring chromatographic experimental parameters, and processing the chromatographic experimental parameters to obtain experimental parameter vectors; obtaining a molecular identifier, and processing the molecular identifier to obtain a multi-modal molecular vector; combining the experimental parameter vector and the multi-modal molecular vector to obtain an input vector; and based on the input vector, predicting by adopting a machine learning regression model or an integrated learning method to obtain chromatographic outflow curve information. According to the method, chemical and physical methods are combined to process experimental parameters, a computational chemistry method is adopted to obtain accurate molecule descriptors, a graph neural network is utilized to capture molecular structure information, in addition, the method supports reverse reasoning of proper experimental conditions, and pre-experimental consumption is reduced.

This application provides a virtual drug screening method, a target computing device, and a storage medium, relating to the field of drug screening technology. The method includes: dividing all small drug molecules into multiple groups of small molecules based on the total number of target accelerators included in multiple computing nodes; encoding a group of small molecules corresponding to each computing node within each group of small molecules to obtain a molecular vector; encoding protein pockets in the target target to obtain a pocket vector; determining multiple candidate small molecules similar to the target target from the drug molecules included in the target drug molecule library based on the pocket vectors and molecular vectors; and using a physical simulation method to determine highly active small molecules that stably bind to the target target from the multiple candidate small molecules. In this application, multiple groups of small molecules with consistent data amounts are allocated to multiple target accelerators to avoid wasting computing resources due to idle target accelerators, thereby improving the screening efficiency of small molecules.

The invention discloses a construction method of an aspergillus niger strain for efficient heterologous synthesis of Monacolin J. According to the invention, in saccharomyces cerevisiae BY4741, a transformation coupled recombination (TAR) technology is utilized to construct an expression vector of a lovastatin precursor Monacolin J, wherein the expression vector is formed by serially connecting lovB, lovC, lovG and lovA genes regulated and controlled by a strong promoter and a strong terminator of filamentous fungi. According to the invention, the steps of expression vector construction and aspergillus niger homologous recombination transformation are simplified, the lovastatin is efficiently and heterologously synthesized in the aspergillus niger by optimizing fermentation components, and a research idea is provided for the construction of a macromolecular vector and the research of metabolic engineering and synthetic biology of filamentous fungi.

The invention provides a metal cage, a ligand and a preparation method and application of the metal cage and the ligand, and relates to the technical field of metal-organic materials, and the structural formula of the metal cage is shown in the formula (II). The metal cage provided by the invention is asymmetric in structure, large in cavity size and stable in property, the fat-soluble dye can be efficiently and accurately identified and effectively wrapped due to the characteristics of the large cavity size, good water solubility and the like, then the fat-soluble dye is separated and released from a main body, and the metal cage has excellent regeneration performance and recycling stability and is suitable for industrial production. Selective capture and controllable transfer of fat-soluble dyes can be realized, and a novel efficient molecular carrier is provided for the fields of dye separation and purification, environmental pollutant removal and the like.

The present disclosure relates to a chimeric protein molecule comprising a degradation domain including an E3 ubiquitin ligase motif without lysine residues and a targeting domain comprising a substrate-binding motif which is heterologous to the E3 ubiquitin ligase motif. A linker couples the degradation domain to the targeting domain. Also disclosed are compositions as well as methods of treating a disease, substrate silencing, forming a ribonucleoprotein, screening agents for therapeutic efficacy against a disease, and methods of screening for disease biomarkers, as well as mRNA molecules, vectors, and encapsulated nucleic acid molecules encoding chimeric protein molecules.

5-Hydroxytryptamine (5-HT) was first discovered in serum and is also known as serotonin. Due to its small molecular weight and poor immunogenicity, the antibodies prepared with 5-HT do not meet the specificity and affinity requirements of immunoassay reagents. This invention innovatively uses N-acetyl-5-hydroxytryptamine, with a larger molecular weight, for hapten design. By coupling it with a specific macromolecular carrier, the prepared intact antigen possesses excellent specificity and strong affinity. This invention mainly relates to the design and synthesis of N-acetyl-5-hydroxytryptamine haptens, the preparation of intact N-acetyl-5-hydroxytryptamine antigens and anti-N-acetyl-5-hydroxytryptamine antibodies, as well as methods for determining 5-hydroxytryptamine concentration, and the composition and components of the detection reagents, belonging to the field of biomedical detection technology. The N-acetyl serotonin derivative of this invention has the structure shown in formula (Ⅰ): where R is —(CH2). n —COOH, where n is an integer between 1 and 10.

The invention discloses a molecular data verification method and device based on an SOL structure. The method comprises the steps that to-be-verified molecular data and a pre-established rule database are obtained; converting the to-be-verified molecular data into a molecular vector; performing vector calculation according to the molecule vector and a molecule legality verification rule in the rule database to obtain a vector calculation result; and determining a legality verification result of the to-be-verified molecule according to the vector calculation result.

The invention provides a metal cage and a preparation method and application thereof, and relates to the technical field of metal-organic materials, and the structural formula of the metal cage is as shown in formula (I). The metal cage provided by the invention is asymmetric in structure, large in cavity size and stable in property, the fat-soluble dye can be efficiently and accurately identified and effectively wrapped due to the characteristics of the large cavity size, good water solubility and the like, then the fat-soluble dye is separated and released from a main body, and the metal cage has excellent regeneration performance and recycling stability and is suitable for industrial production. Selective capture and controllable transfer of fat-soluble dyes can be realized, and a novel efficient molecular carrier is provided for the fields of dye separation and purification, environmental pollutant removal and the like.

Provided herein are antibody molecules that bind specifically to C-MET and related nucleic acid molecules, vectors and host cells. Also provided herein are medical uses of such antibody molecules.