12 results about "Molecular classification" patented technology

The invention discloses a molecular classification prediction method based on molecular biomarkers and images, and relates to the technical field of medical image processing. Comprising the following steps: constructing a molecule and image matching correlation analysis model; training by using the training data set; the channel number of the target preoperative medical image data is increased through the feature extraction convolution block; a space matching relation between an image and a molecular biomarker in the processed target preoperative medical image data is established through an image molecule fine granularity insight module, and a feature map after the space relation is established is obtained through a space molecule mapping map output module; adjusting the feature map into a corresponding molecular channel through a space molecular mapping map output module to obtain a space molecular mapping map; and pooling the spatial molecular mapping map through a global average pooling module, and activating and calculating a molecular category prediction probability through Sigmoid to obtain a molecular classification prediction result. According to the invention, the spatial relation between molecules and images is established.

This invention discloses a breast cancer classification method based on Piezo1 expression. After obtaining tumor tissue samples from patients, the method detects the Piezo1 protein expression level using immunohistochemistry and classifies them into high-expression and low-expression types according to a validated scoring standard. This classification result guides individualized treatment, with high-expression patients recommended for treatment regimens including inhibitors of mechanotransmission pathways. By integrating tumor mechanotransmission characteristics into the clinical classification system, this invention can identify a subgroup of breast cancer driven by an abnormal mechanotransmission microenvironment that cannot be distinguished by traditional molecular classification. This not only improves and supplements the existing classification framework, making the understanding of breast cancer heterogeneity more comprehensive, but also more accurately predicts the invasiveness, metastasis potential, and poor prognostic risk of these patients.

This disclosure generally relates to a molecular classification of cancer and particularly to molecular markers for predicting response to cancer therapy, including cancer immune therapy, and methods of use thereof.

The application discloses a molecular typing method of Staphylococcus capitis, and first establishes an operation technology for molecular typing of Staphylococcus capitis by using a multi-locus sequence typing system (MLST). Seven conservative gene fragments are confirmed by screening, all known Staphylococcus capitis genomes are typed based on the combined sequences, ST types and CC types are defined, and a system evolution tree based on core genome SNP differences is compared, so that reliable typing results can be obtained. Seven pairs of PCR primers are designed and verified, and the Staphylococcus capitis can be typed by MLST. The seven conservative gene combinations and amplification primers used in the typing technology are used for the first time, and the PCR reaction system and conditions are optimized by the inventors. The technical process can be used for molecular classification and epidemiological monitoring of Staphylococcus capitis.

The invention provides a molecular classifier for detecting gastric cancer miRNA. A preparation method of the molecular classifier comprises the following steps: depositing a PABA modification layer on the surface of a screen-printed electrode; activating carboxyl on the surface of the para aminobenzoic acid modification layer by adopting an EDC / NHS composite system; carrying out amination modification on an MXene material, and coating the surface of the activated para aminobenzoic acid modification layer with the modified MXene material to form an MXene functional layer; depositing gold nanoparticles on the surface of the MXene functional layer to obtain an electrochemical activity sensing interface; a signal reporter molecule is combined with an aptamer probe, the signal reporter molecule is a DNA tetrahedron-methylene blue complex, and the combined complex is dropwise added on the surface of an electrochemical activity sensing interface, so that the aptamer probe is combined on the surface of the electrochemical activity sensing interface. The molecular classifier can be used for preparing gastric cancer miRNA detection products, and the problems that in the prior art, a classifier is high in complexity and high in signal leakage risk are solved.

The invention discloses a molecular classification diagnosis system for diagnosing prostatic cancer through a multi-target combined weight system, and belongs to the technical field of biological medicine. The method comprises the following steps: establishing a mathematical logic relationship among multiple targets through data training by utilizing an existing clinical database containing information of patients with prostatic cancer and benign hyperplasia, namely, a weight ratio of four biomarkers related to prostatic cancer to diagnosis of prostatic cancer, and obtaining a weight diagnosis formula for classification of prostatic cancer and benign hyperplasia of prostatic; a weight detection system is established, a DNA tetrahedral framework nucleic acid dimer structure is used as a signal output substrate, and a multi-target combined intelligent diagnosis system is constructed by pricing and modifying different signal molecules on a signal output probe, so that precise classification of prostatic cancer and benign prostatic hyperplasia is realized, and the accuracy of early diagnosis of prostatic cancer is improved.

The application discloses a molecular classification diagnosis system for diagnosing prostate cancer through a weight system combined with multiple targets, and belongs to the technical field of biological medicine. By using an existing clinical database containing information of prostate cancer and benign hyperplasia patients, a mathematical logic relationship between multiple targets is established through data training, that is, weight matching of four prostate cancer related biomarkers for prostate cancer diagnosis, so that a weight diagnosis formula for classifying prostate cancer and prostate benign hyperplasia is obtained; a weight detection system is established, a DNA tetrahedral framework nucleic acid dimer structure is used as a signal output base, different signal molecules are modified on a signal output probe, an intelligent diagnosis system combined with multiple targets is constructed, and accurate classification of prostate cancer and prostate benign hyperplasia is realized, thereby improving the accuracy of early diagnosis of prostate cancer.

The application provides a method for accurately calculating mean square displacement (MSD) of molecular dynamics simulation based on multi-phase state identification, which accurately classifies target molecules in the system into four states: near impurity target molecules, target molecules in hydrates, target molecules in clusters and target molecules in liquid phase. The classification process adopts a multi-stage screening strategy to ensure the independence of each type of molecule. Traditional MSD calculation only requires molecules to be in the target phase state at the start and end frames, but the intermediate frame may undergo phase transition, such as entering the hydrate from the liquid phase, resulting in a deviation of the calculation result from the intrinsic diffusion behavior. The application tracks the occurrence state of the molecule during the entire simulation process, accurately finds the state that needs to be calculated, and ensures that MSD only reflects the continuous diffusion process of the molecule in the pure liquid phase through a state persistence verification mechanism, excluding the interference of phase transition, and performing targeted MSD calculation.

The application is suitable for the technical field of molecular classification, and provides a self-supervised molecular classification method based on a deep learning model, which comprises the following steps: step 1, an original molecule is processed into a form represented by an adjacency matrix and a feature matrix, and then represented by a graph; step 2, the graph is taken as an input of a graph neural network module, local features of the molecule are obtained, and the properties of the molecule are predicted; and step 3, a standard binary classification cross-entropy loss function is used to adjust a self-supervised learning task between a positive sample pair and a negative sample pair. The method has important significance for screening candidate drugs for specific diseases, especially for a new molecular data set without labels, and can achieve the purpose of rapid classification. Not only can the method replace time-consuming manual labeling of researchers and shorten the time to a short range, but also can control errors to a certain extent, so that real-time performance and accuracy are ensured.

The application belongs to the technical field of new species gene detection of insects, and particularly relates to a Guizhou large-mouthed worm new species, a DNA standard detection gene thereof and application. The Guizhou large-mouthed worm is separated from a freshwater environment in Guizhou province of China, the worm can actively prey on Rhabditis sp. nematodes, and the Guizhou large-mouthed worm is identified by combining traditional morphological identification and molecular classification methods, so that the accuracy of species identification can be ensured.

The invention generally relates to a molecular classification of disease predisposition and particularly to molecular markers for cancer predisposition and methods of use thereof.

The application provides a molecular classification method based on heterogeneous graph embedding, and belongs to the technical field of molecular classification; comprising: simplex extraction on a heterogeneous graph; processing structural information of the heterogeneous graph based on the extracted simplex to obtain a local and global information enhancement operator; processing feature information of the heterogeneous graph based on the extracted simplex to obtain a feature matrix; performing hash iteration on the heterogeneous graph based on the local and global information enhancement operator and the feature matrix to obtain graph-level embedding; and performing molecular classification on the graph-level embedding to obtain a molecular classification result. By combining simplex and hash algorithm, the application can effectively capture high-order interaction information and heterogeneous features, significantly improve the calculation efficiency, and provide an efficient and scalable solution for heterogeneous graph analysis.