1326 results about "Cancer" patented technology

The present invention relates to a compound as shown in formula (A) having a pan-RAS inhibitory effect, or an isotopic derivative or stereoisomer thereof, or a pharmaceutically acceptable salt thereof, and a pharmaceutical composition containing the compound, and the use of the compound of formula (A) in the prevention and / or treatment of cancers, tumors, inflammatory diseases, autoimmune diseases or immune-mediated diseases.

The invention relates to the technical field of assessment and early warning systems, and particularly discloses a rectal cancer operation risk assessment and early warning system based on multi-modal data fusion, which comprises a multi-modal data acquisition module, a data preprocessing module, a cross-modal fusion module, a dynamic risk assessment module, an intelligent early warning module and a system self-checking module. By integrating multi-modal data and dynamically allocating weights, real-time risk updating in the whole operation period is achieved, the comprehensiveness, timeliness and precision of risk assessment are comprehensively improved by combining the grading early warning function, the autonomous detection calibration function and the risk tracing and countermeasure matching function, long-term reliable operation of the system is guaranteed, powerful support is provided for clinical decision making, and the risk assessment method is suitable for clinical decision making. The surgical risk and the complication occurrence rate are effectively reduced.

Provided are a compound represented by formula (I) and a pharmaceutical composition comprising the compound, and a use of a compound of formula (A) for preventing and / or treating cancer, tumor, inflammatory disease, autoimmune disease, or immune-mediated disease.

Disclosed are approaches to data acquisition, analysis, and computational forecasting that employs quantitative MRI data to predict the response of cancer to therapy. Example protocols detail how to acquire needed images followed by registration, segmentation, quantitative perfusion and diffusion analysis, model calibration, and prediction. The response of individual cancer patients to therapy is forecast by application of a biophysical, reaction-diffusion model to these data. Application of the protocol results in coregistered MRI data from at least two scan visits that quantifies an individual tumor's size, cellularity and vascular properties. This enables a spatially resolved prediction of how a particular patient's tumor will respond to therapy. A modified therapy can be determined based on predicted response.

The invention relates to the field of medical health and artificial intelligence, and discloses a cancer patient low-molecular heparin individualized dose dynamic optimization method based on reinforcement learning, and the method comprises the steps: S1, collecting multi-dimensional clinical data of a cancer patient, carrying out the preprocessing, carrying out the enhancement of the preprocessed data, and generating time sequence synthesis data; s2, based on the multi-dimensional clinical data and the time sequence synthesis data, constructing a reinforcement learning environment, including defining a state space, an action space and a reward function; s3, constructing an environment adaptive deep reinforcement learning EA-DRL model as a dose optimization model; performing model training and optimization in the reinforcement learning environment until convergence and obtaining an optimal dose decision strategy; and S4, inputting real-time dynamic clinical data of a patient to be decided into the trained dosage optimization model, and outputting individualized low molecular heparin LMWH administration dosage recommendation. Individualized precise administration is realized, and the treatment effect and the clinical medication safety are improved.

The present disclosure relates to compositions and methods for reducing expression of MYC gene in a cell. In some embodiments, an expression repressor comprises a targeting moiety that binds a MYC promoter, anchor sequence, or super-enhancer. In some embodiments, the expression repressor comprises an effector moiety that represses transcription or methylates DNA. Systems comprising two expression repressors are also disclosed. The compositions can be used, for example, to treat cancers such as HCC.

The application provides a novel DNA methylation marker TAGMe-3 for tumor identification and use thereof. The TAGMe-3 gene sequence region has significant methylation difference between cancer tissues and paracancer tissues. As long as abnormal high methylation state of the TAGMe-3 gene sequence region is detected, the subject is determined to belong to a tumor high-risk population. Moreover, the significant difference of the TAGMe-3 presented between tumor tissues and non-tumor tissues exists in different types of tumors (Pan-cancer) in a wide range.

The invention relates to the technical field of psychosomatic health management, in particular to a psychological immune system evaluation system and intervention method for cancer patients. And the data acquisition module is used for acquiring and fusing the immune biochemical indexes of the patient, the continuous physiological time sequence signals generated by the wearable device, the digital psychological assessment data and the clinical treatment stage marks, and outputting a structured multi-dimensional time sequence data set through time alignment and feature extraction operation. Through multi-modal data fusion and integrated machine learning analysis, the psychosomatic health risk of the patient can be predicted based on the continuous physiological and psychological data change trend of the patient, and corresponding intervention measures can be triggered before the patient has obvious clinical symptoms by outputting the quantized risk coefficient and the multi-stage early warning signal, so that the accuracy of the patient is improved. Therefore, an intervention mode is promoted to be converted from traditional intervention after evaluation to predictive and preventive intervention.

The disclosure relates to radiolabeled aromatic electrophile prosthetic groups, which can be used to prepare bioactive ligands containing PET, SPECT, alpha- or beta-emitting radioisotopes, and their use in treating and / or imaging cancer.

The invention provides an intratumoral bacterium detection and analysis method based on circular DNA enrichment sequencing and related model construction, and belongs to the field of molecular biology. The intratumoral bacterium detection method provided by the invention comprises the following steps: extracting total DNA of cancer tissue or para-carcinoma tissue, carrying out linear digestion, purifying a linear digestion product, and enriching to obtain circular DNA; the method comprises the following steps: amplifying circular DNA, and breaking a DNA amplification product to 300-500bp; purifying DNA fragments, constructing a library, and sequencing; and performing genome comparison according to a sequencing result to obtain information of the intracellular bacteria. According to the method, complete bacterial genome and plasmid genome information can be captured, and the detection sensitivity of the intracellular bacteria and the richness of the bacterial genome information are improved. The invention further provides an intratumoral bacterium analysis method which can be used for screening generic cancer bacterial markers, and provides a cancer risk assessment machine learning model based on the intratumoral bacterium, so that the clinical application possibility of the intratumoral bacterium is improved.

The present disclose provides a method for classifying a sample derived from a subject. The method may comprise obtaining a sample comprising nucleic acid molecules from the subject. The method can comprise assaying the nucleic acid molecules to generate a data set comprising methylation states of one or more genomic regions. The one or more genomic regions can comprise differentially methylation regions (DMRs). The method can comprise processing at least a portion of the data set to generate an output indicative of cancer in the subject. The portion of the data set can pertain to a set of DMRs specific to the subject.

The invention relates to a preparation method of a microwave-assisted synthesized near-infrared electrochemical luminescence gold nanocluster and application of the gold nanocluster in miRNA (micro Ribonucleic Acid) detection. The preparation method comprises the following steps: under a stirring condition, adding a gold source and alkali into a Met solution to obtain a mixed solution, carrying out microwave irradiation reaction, and carrying out solid-liquid separation to obtain a Met-Au NCs solution; the preparation method comprises the following steps: activating a Met-Au NCs solution by using EDC and NHS, adding a DNA solution, mixing, and dialyzing to obtain a Met-Au NCs-DNA compound, namely the near-infrared electrochemical luminescence gold nanocluster. Compared with Au NCs prepared by a common mild method, the Met-stable Au NCs prepared by a microwave-assisted method has the advantage that the fluorescence and electrochemical luminescence efficiency at 835 nm is improved. The invention also provides a'signal closing 'ECL (electron cyclotron ligand) biosensor for high-sensitivity detection of the miRNA-107 (MicroRNA-107), and a method for detecting the miRNA-107 (MicroRNA-107). The sensor is simple to operate and good in repeatability, and has important scientific significance and application value for clinical early diagnosis of cancers.

The invention provides a cross-omics sparse feature selection system and method based on hierarchical causal modeling, and the system comprises a data input and preprocessing module which is used for receiving multi-omics original data of a multivariate sample; the hierarchical causal structure learning module is connected with the data input and adaptive preprocessing module and is used for constructing a cross-omics hierarchical causal topology; the causal-oriented sparse feature selection module is connected with the hierarchical causal structure learning module; and the model retraining and integration module is used for constructing a three-layer weighted integration discrimination model based on the screened markers, optimizing the fusion weight of each layer through a gradient descent algorithm, and outputting a final prediction result. According to the method, the protein-metabolism biological hierarchy relationship and serum-urine complementary information are fully utilized, and the method has good generalization ability and can be widely applied to marker mining and prediction modeling of cancers, metabolic diseases and the like, so that the accuracy and reliability of precise medical treatment are improved.

The invention discloses a rectal cancer medical image lesion segmentation method and device based on deep learning, and aims to solve the problem that in the prior art, only a medical image is used as a single input mode, and potential semantic association among multi-mode data is neglected, so that the segmentation effect is poor. The method comprises the following steps: acquiring a to-be-detected rectal cancer medical image focus image and corresponding clinical text information, and inputting the two images into a segmentation model for processing; the clinical text information is processed through a text multi-scale feature extraction module, and target text multi-scale features are generated; encoding the text features and the medical image by using a feature encoder, and outputting target text image fusion encoding features; inputting the fusion coding feature into a scale attention module, and outputting a target text image fusion attention feature; processing the fusion attention feature and the fusion coding feature through a feature decoder to obtain a target text image decoding feature; and finally, segmenting the decoding features by using a segmentation head, and outputting a final target segmentation result.

The invention discloses a multi-dimensional efficacy evaluation system for colon cancer targeted drug screening, and relates to the technical field of medical assistance. Comprising a data acquisition module, an inference engine module and an output module. The data acquisition module acquires an organ sample response data set (including apoptosis rate A1, activity decline degree A2 and image structure change score B1) and a patient background data set (including gene mutation discrete variable set G and metabolic pathway continuous variable set M). The inference engine module executes dominant condition rules: generating a negative weight factor alpha according to a gene mutation state and a metabolic activation threshold value; generating a deduction item gamma based on a preset drug-resistant mutation subset; performing weighted calculation on the apoptosis rate and the activity decline degree to generate a basic drug effect score beta, and increasing beta through a critical value; and finally generating a comprehensive response score S. And the output module outputs a drug effect judgment result according to the S, and multi-dimensional accurate evaluation is realized.

The invention discloses a multi-omics cancer subtype recognition method, system and device based on density sensing cluster structure guide contrast learning and a medium, and belongs to the technical field of bioinformatics and artificial intelligence crossing. The method comprises the following steps: acquiring and preprocessing multi-omics data; constructing an omics specific auto-encoder and learning potential representation; constructing a density sensing cluster block in the potential space; constructing a cross-omics positive and negative sample pair based on cluster block sample overlapping; difficult negative sample mining; constructing a cluster block level cross-omics contrast learning target, and training and updating; a self-supervised soft refinement mechanism is introduced to dynamically enhance a cluster structure; and carrying out multi-loss joint optimization and model iteration training. According to the method, the robustness and the stability of a cancer subtype recognition result can be improved, high-dimensional, multi-source and multi-noise multi-omics data can be efficiently modeled and analyzed, good generalization ability and application potential are achieved, and reliable technical support can be provided for cancer subtype research, patient stratified analysis and precise medical aid decision making.

The invention belongs to the field of medical image processing and artificial intelligence, and provides a colon cancer CT image segmentation method and system fusing individualized features, and the method comprises the steps: obtaining the abdomen CT images of a historical patient and a target patient; obtaining structured individual feature information related to the patient, wherein the individual feature information comprises age, gender, colon cancer family history and intestinal medical history information; preprocessing the abdomen CT image; and training an image segmentation model by using the preprocessed abdominal CT image of the historical patient, segmenting the preprocessed abdominal CT image of the target patient by using the trained image segmentation model meeting the segmentation precision requirement, and generating a colon cancer focus segmentation image conforming to the individual feature difference of the target patient. According to the method, the structured patient information is utilized to guide the model network to adjust the feature response, so that the segmentation precision and individual adaptability of the model are improved, and the segmentation accuracy is further improved.

The invention relates to combined application of an antibody drug conjugate and an immune checkpoint inhibitor, in particular to application of single drug or combined use of the antibody drug conjugate in preparation of drugs for preventing and / or treating cancers. Specifically, the invention provides an application of the antibody drug conjugate or pharmaceutically acceptable salt, metabolite or solvate single drug thereof or a combined immune checkpoint inhibitor in preparation of drugs for preventing and / or treating cancers.

A tumor classification method, an apparatus, a terminal device and a storage medium. The method comprises: performing feature processing on specific tumor gene data to be classified, so as to obtain a target feature vector; and, by means of a trained biological neural network model, identifying the target feature vector to obtain a classification result of said specific tumor gene data. As the biological neural network model is constructed by introducing biological knowledge, classification results of specific tumor gene data can be predicted on the basis of specific cancer tumor gene attributes combined with hierarchical information in biology, so that the degree of credibility of the classification results is higher, thus improving the accuracy of tumor classification.

The present invention relates to combination therapies employing tumor targeted anti-CEA / CD3 bispecific antibodies and / or agents blocking PD-L1 / PD-1 interaction in combination with 4-1BB (CD137) agonists, in particular 4-1BBL trimer containing antigen binding molecules that also target FAP, the use of these combination therapies for the treatment of cancer and methods of using the combination therapies.

An example computer-implemented method for determining patient-specific tumor dynamics is described herein. The method includes receiving an image of a tissue sample that includes a distribution of tumor cells and non-tumor cells; applying a spatial correlation function to the image; and obtaining a power spectral density of the spatial correlation function of the image. The method also includes fitting the power spectral density of the spatial correlation function of the image to the power spectrum of a reaction-diffusion model; and inferring a patient-specific tumor-dynamic coefficient based on the reaction-diffusion model of cancer.

Various implementations of the invention relate to a silicon-embedded multi-spectral lidar system and method for non-invasive, remote monitoring of pathological conditions of an individual. The system integrates multiple laser sources, photodetectors, and a processing module onto a silicon chip, enabling the capture and analysis of spatial, spectral, scattering and temporal data from a target subject (e.g., individual). By utilizing lidar signals at various wavelengths, various implementations of the invention detect three-dimensional (“3D”) surface and subsurface features such as micro-movements, vascular patterns, pigmentation changes, and tissue differences and / or irregularities. Machine learning algorithms process this information from the lidar to identify and classify abnormalities, enabling applications such as heart rate and respiration monitoring, eye movement tracking for neurological and mental health assessment, and detection of pathological skin conditions like cancer. Various implementations of the invention operate in real-time, adapt to environmental conditions, and support dynamic monitoring over time, thereby providing a comprehensive, non-contact solution for diagnostics and telemedicine, for example. Various implementations of the invention may comprise a compact silicon chip form factor suitable for portable and / or hand-held, scalable health monitoring applications across diverse environments.

The invention discloses a method for screening a Wilson disease serum exosome miRNA biomarker based on a transcriptomics technology, and belongs to the field of bioinformatics analysis of diseases. According to the invention, the effect of miRNA in WD pathogenesis is discussed by identifying serum exosome miRNA, and a potential biomarker is provided for accurate diagnosis and treatment of the disease. According to the invention, 59 DE-miRNAs are identified by analyzing the expression of differential miRNAs of WD and control group patients, and the DE-miRNAs are related to key approaches such as metabolic regulation, cancer progression, signal transduction and the like. Besides, the reliability of the key DE-miRNA, including miR-451a, miR-204-5p and the like, is confirmed through experimental verification, and the potential of the key DE-miRNA as a non-invasive biomarker is indicated. Research results provide important theoretical basis and new insight for accurate diagnosis of WD and development of potential therapeutic targets.

Provided herein is a DNA analysis method for detecting and quantifying immune cell types from which the DNA originated. Provided herein are also methods for determining the likelihood that a subject has a disease or condition, such as cancer.

The invention provides a TF and Her2 targeting bispecific antibody coupling drug as well as a preparation method and application thereof, and belongs to the technical field of biological drug preparation. The bispecific antibody provided by the invention can target TF and / or Her2 antigens in tumor cells, and has the advantages of high stability, easiness in expression, purification and coupling and the like. The bispecific antibody can be specifically combined with a tumor surface antigen and internalized into tumor cells, so that the tumor cells can be specifically killed. The bispecific antibody coupling drug prepared on the basis of the bispecific antibody has a good tumor inhibition effect in a cell model and an animal model, is nontoxic and harmless to animals, and has an excellent cancer treatment potential.

The present disclosure, among other things, provides technologies for predicting immune response (e.g., in response to an antigen) and for utilizing these predictions to create personalized cancer vaccines and viral vaccines. Among other things, systems, methods, and architectures describe a use of large language models (LLMs) and / or multi-task models for immune response predictions. The present disclosure provides models that simultaneously predict multiple immune response tasks and / or benefit from training on multiple immune response tasks. The present disclosure also provides tools for identifying antigen fragments that will, among other things, be presented as ligands for T-cell recognition.

The invention discloses a longitudinal CT image-assisted rectal cancer neoadjuvant radiotherapy and chemotherapy treatment reaction evaluation device, which comprises a focus area segmentation module, a rectum focus area detection module, a rectum focus area detection module, a rectum focus area detection module, a rectum focus area detection module, a rectum focus area detection module, a rectum focus area detection module, a rectum focus area detection module and a rectum focus area detection module, obtaining a standardized three-dimensional tumor area; a feature fusion module extracts deep learning features of a focus area after segmentation at two time points before neoadjuvant radiotherapy and chemotherapy and before an operation from the three-dimensional tumor area, and performs weighted fusion on the deep learning features at the two time points through a dynamic attention weight layer to obtain longitudinal comprehensive features representing tumor treatment response changes; and the prediction module fuses the longitudinal comprehensive characteristics and clinical baseline data to construct a multi-modal prediction model, and outputs a treatment response prediction result of the rectal cancer patient on neoadjuvant chemoradiotherapy, so that the prediction accuracy of pathological complete remission of the rectal cancer patient can be improved, and the prognosis of the patient and the utilization efficiency of medical resources can be improved.

The invention provides a cancer early-stage dynamic risk prediction method and device, equipment and a storage medium, and relates to the technical field of data management and risk assessment. The method comprises the following steps: acquiring health medical data, key gene data and behavioral habit data of a target user; configuring a dynamic risk prediction model based on the key gene data and the behavior habit data to obtain a dynamic risk prediction model corresponding to the target user; and inputting the health medical data into a dynamic risk prediction model corresponding to the target user to obtain predicted health medical data of the target user, and performing cancer early-stage dynamic risk prediction on the target user based on the predicted health medical data. According to the method, the health condition of an individual can be comprehensively analyzed from multiple dimensions, the change of the physical condition of a patient can be better adapted, and a more reliable basis is provided for early diagnosis and treatment of cancers.

The present disclosure provides antibodies that specifically bind to TIGIT. The antibodies have the capacity for substantial activation of T cells and natural killer cells by inhibiting binding of TIGIT to CD155. The antibodies can be used for treatment of cancer and infectious disease, among other applications.

The invention discloses an aza-BODIPY biomedical phototherapy agent taking oxajulolidine as a donor and a preparation method thereof, and relates to a medical phototherapy agent for treating brain glioma and a preparation method thereof, and the prepared compound is prepared by introducing an oxajulolidine fragment with electron donating property into a key position of an aza-BODIPY skeleton, so that the aza-BODIPY biomedical phototherapy agent is obtained. The donor-acceptor type molecular near-infrared phototherapy agent with a new structure is constructed, has good near-infrared absorption and emission performance and excellent stability, and shows a remarkable effect in the field of cancer photodynamic (PDT)-photothermal (PTT) synergistic treatment. The structural categories of the near-infrared aza-BODIPY biomolecules are enriched, and a new molecular platform is provided for expansion and application of the near-infrared aza-BODIPY biomolecules in the fields of biological imaging, tumor diagnosis and treatment, functional materials and the like.