125 results about "Drugs response" patented technology

A computer-implemented system for personalized health optimization constructs a confidence-weighted personal health knowledge graph (PHKG) from heterogeneous data, including wearable sensors, medical devices, lab results, medication logs, and conversational inputs. A multi-stage causal-inference stack identifies modifiable drivers of outcomes using layered methods (e.g., MI, GAM, Neural Granger, DAG-GNN), and simulates candidate interventions. A recommendation engine ranks lifestyle or pharmacologic actions using a benefit-to-friction score, selecting a personalized intervention aligned with user readiness and clinical safety constraints. Interventions may include a minimum effective dose (MED), optimal level, adaptive low-dose, or behavioral challenge. Optional modules include reinforcement learning for timing adaptation and privacy-preserving on-device inference. The system operates across domains including metabolic, cardiovascular, renal, sleep, stress, and medication response, enabling cross-condition synergy evaluation. The architecture is modular, supports runtime plug-in targets, and adapts in real time with or without continuous clinical oversight, depending on deployment.

A federated distributed computational system enables secure drug discovery and resistance tracking through hybrid simulation capabilities. The system implements a hybrid simulation orchestrator that coordinates molecular dynamics simulations with machine learning models for drug discovery analysis, while maintaining secure cross-institutional data exchange. The architecture coordinates multi-scale spatiotemporal synchronization across computational nodes, with each node containing local processing capabilities for molecular dynamics simulation and resistance pattern detection. Through a distributed graph architecture, the system enables real-world clinical data integration, resistance evolution tracking, and multi-scale tensor-based analysis with adaptive dimensionality control. The system implements real-time drug response prediction through multi-modal data analysis, enabling pharmaceutical companies and research institutions to collaborate on complex drug discovery projects while maintaining strict data privacy controls.

The invention provides a drug response prediction method based on a gene relation network and a drug substructure. The drug response prediction method comprises the following steps: performing feature extraction on three multi-modal features of gene expression, copy number variation and mutation of a cell line by adopting an enhanced graph attention network; acquiring a substructure of the medicine by using a gating message passing neural network, and extracting features by enhancing a graph attention network; constructing two complementary graph structures, namely an atom-bond graph and a bond-angle graph, and performing feature extraction and message passing on the two graphs by using a graph convolutional neural network so as to extract 3D features of the medicine; the characteristics of the drug and the cell line are integrated through concat operation, and drug response prediction is carried out through mlp. According to the drug response prediction method provided by the invention, cell line features are extracted by establishing and using three kinds of omics data with different emphasis, and drug feature extraction is performed by using a drug molecular map, a drug 3D structure, a drug molecular fingerprint and a drug substructure relationship.

The invention belongs to the field of bioinformatics, and relates to an anti-cancer drug response prediction method based on an attention mechanism. The method comprises the following steps: firstly, capturing uniform-dimension drug and cancer cell line characteristics through a multi-layer perceptron; secondly, fusing drug characteristics by adopting a Transform encoder, and constructing a cell encoder for cancer cell line characteristic polymerization; then, designing a cross-modal cross fusion module to promote information interaction between the two; and finally, predicting a semi-suppressed concentration value subjected to logarithmic transformation between the two through a multi-layer perceptron. Experimental results show that compared with an existing optimal method, the method has the advantage that the RMSE is reduced by 2.9%. According to the method, accurate prediction of the anti-cancer drug response is achieved by integrating drug and cancer cell line data, screening of potential anti-cancer drugs can be accelerated, personalized treatment schemes can be optimized, the cure rate of cancer patients is further increased, and the method has great significance in cancer treatment.

The invention relates to the technical field of intelligent anesthesia precise regulation and control, and discloses an anesthetic dosage optimization method based on artificial intelligence. According to the method, a dynamic treatment interval is constructed, and the boundary of the dynamic treatment interval is adaptively adjusted according to the real-time sedation depth and the nociceptive stimulation level. And in the interval, performing pattern recognition on the continuous electroencephalogram signals and the hemodynamic parameters, and marking abnormal events deviating from a standard anesthesia state. And establishing a correlation network of the drug effect chamber concentration and the abnormal events, and generating a virtual drug response curve for predicting the trend of the abnormal events under different doses. Whether dose strategy reconstruction is started or not is determined by comparing the goodness of fit between the prediction curve and the actual physiological trajectory. During reconstruction, contribution weights of historical drug infusion points to abnormal events are backtracked and analyzed, and adjustment coefficients are distributed and integrated into a new infusion sequence. According to the invention, individualization and self-adaptive optimization of anesthesia administration are realized, and the accuracy and safety of anesthesia depth control are improved.

The invention provides a drug screening and curative effect evaluation method and system based on a glioma organ-like model, and relates to the technical field of biological material analys.The method includes the steps that a three-dimensional fluorescence image of the glioma organ-like model is collected, signal intensity analysis and compensation processing are carried out, a growth feature mapping model is constructed, and the three-dimensional fluorescence image of the glioma organ-like model is obtained; and phenotypic characteristics for representing the glioma organoid heterogeneity are obtained. Inputting the phenotypic characteristics into a drug response evaluation network, and calculating a drug sensitivity score; the drug molecular feature library and the drug collaborative analysis model are combined, the synergistic interaction index of different drug combinations is calculated, the optimal drug combination is screened, the drug administration dosage and the drug administration time sequence are determined in combination with phenotypic features, and finally an individualized treatment scheme is generated. According to the invention, the curative effect of the drug on the glioma organs can be effectively evaluated, and the optimal drug combination and administration scheme can be screened out, so that the accuracy and effectiveness of glioma treatment are improved.

The invention is applicable to the technical field of clinical medicine, provides a clinical multi-modal cancer drug response prediction method based on feature reconstruction, constructs a clinical multi-modal model for drug response prediction of diffuse large B-cell lymphoma, and aims to predict the drug response of diffuse large B-cell lymphoma by integrating gene sequencing and clinical multi-modal data. And accurate drug reaction prediction is realized. The model adopts an end-to-end multi-stage processing flow: firstly, extracting gene features through TransP-Net, and processing multi-modal clinical data by using a clinical information encoder; then, pseudo-gene features are generated through a clinical-genome filling module to deal with the data missing problem; and finally, multi-modal deep fusion is realized through a clinical information decoder, and a prediction result is output. According to the method, data characteristics and working processes in a real clinical environment are fully considered, two conditions of complete gene data and missing gene data can be processed at the same time, and the method has a good clinical transformation prospect and application value.

The invention relates to the technical field of medical health management, and discloses an endocrine patient health management system based on big data. According to the system, a multi-source data acquisition module is adopted to acquire heterogeneous health data including physiological monitoring indexes, medication record data, medical image reports and the like, and living habit logs can also be included. The physiological feature noise reduction module is used for extracting steady-state physiological features, the multi-modal fusion module is used for generating a focus dynamic map, and the medication feedback analysis module is used for generating a drug response mode evolution sequence. The data are input into a multi-dimensional decision model, and a health management scheme is output by a personalized scheme generation module. And the living habit analysis module analyzes the living habit logs to generate influence factors, and participates in making a health management scheme. The system realizes multi-source data fusion analysis, can provide a personalized health management scheme for an endocrine patient, improves the disease diagnosis accuracy and treatment effect, and improves the life quality of the patient.

The invention provides an organoid drug reaction whole-course monitoring system, and relates to the technical field of data monitoring, and the system comprises an acquisition module which is used for acquiring a three-dimensional image sequence of an organoid at a set time interval, and monitoring the concentration data of metabolites in a culture solution to obtain multi-source monitoring data; the processing module is used for performing voxelization processing on the three-dimensional image sequence to form a time sequence three-dimensional voxel data set; and the calculation module is used for calculating barycentric coordinates of the organ-like structure based on the three-dimensional space distribution characteristics of the organ-like structure in the time sequence three-dimensional voxel data set, and establishing two mutually orthogonal space analysis axes in the maximum cross section of the organ-like structure by taking the barycentric coordinates as the center. According to the method, comprehensive and dynamic monitoring and evaluation of the organoid drug reaction process are realized through multi-source data collaborative acquisition, standardized spatial analysis, accurate form dynamic extraction, form and metabolism time sequence correlation modeling and real-time time sequence registration evaluation.

An ensemble of predictive models that elucidate how cancer mutations impact the response to common replication stress-inducing (RSi) agents. The models implement recent advances in deep learning to facilitate multi-drug prediction and mechanistic interpretation. Initial studies in tumor cells identify 41 molecular assemblies that integrate alterations in hundreds of genes for accurate drug response prediction. These cover roles in transcription, repair, cell-cycle checkpoints, and growth signaling, of which 30 are shown by loss-of-function genetic screens to regulate drug sensitivity or replication restart. The model translates to cisplatin-treated cervical cancer patients, highlighting an RTK (receptor tyrosine kinase)-JAK-STAT assembly governing resistance. This invention defines a compendium of mechanisms by which mutations affect therapeutic responses, with implications for precision medicine.

The invention discloses a dual-channel fusion cancer drug response prediction method, and belongs to the technical field of biological information. The method aims at solving the problems that an existing prediction method is only limited to intra-modal feature extraction, and a complex nonlinear cooperative relation between a drug and cancer cells is difficult to capture. Multi-omics data, drug molecular structure information and cancer cell line drug reaction data are integrated from databases such as CCLE, GDSC and PubChem, and unified input features are formed through standardization and feature construction. Introducing a hierarchical double-attention conversion network into the first channel to carry out characterization learning on the multi-modal features of the drug and the cell line, and constructing a high-order attention neighbor interaction graph convolutional network in the second channel to capture graph structure information of cancer drug response. And carrying out adaptive weighting on output results of the two channels by using a PPO-based fusion module so as to realize a dynamic optimal decision. And finally, generating a drug sensitivity prediction result of the cancer cell line through a classification predictor.

Various methods and systems for efficiently providing pharmacogenetic guidelines is disclosed. A drug prescription and a patient genotype can be analyzed to provide a drug therapy recommendation. The analysis can include comparing the patient genotype and the drug name to a drug profile database, a molecular biomarker database, hospital drug reaction records and omics databases, and calculating the patient response to the drug.

The invention provides a brain disease drug curative effect analysis and prediction system and method, and relates to the technical field of drug analysis. Multi-source heterogeneous data such as genetic variation spectrum, neural image topological characteristics, metabolic trajectory vectors and microbiome dynamic distribution matrix are integrated, and cross-modal dynamic fusion is realized through decomposition. The system constructs a drug prediction coupling network based on dynamic causal inference, analyzes overlapped potential intervention nodes of multiple disease mechanisms, and generates a disease-drug-phenotype multi-dimensional mapping library. A short-term drug response toxicity threshold is predicted through a metabolic entropy change model, a long-term neurological function degeneration trajectory is evaluated in combination with epigenetic drift, and an anti-fact strategy gradient is utilized to dynamically optimize a drug administration scheme. According to the invention, accurate fusion and dynamic analysis of multi-modal data are realized, a balance mechanism of curative effect and risk is established, and accurate drug combination sequence and administration strategy support can be provided for individualized treatment of complex brain diseases.

The invention discloses a drug response prediction model for drug combination based on multi-omics data and transfer learning and application, belongs to the technical field of drug response prediction, and solves the problems that a traditional method is lack of a drug response prediction system based on dosage, is mostly based on single drug response prediction, is lack of modeling ability for drug combination, and cannot predict drug response. Meanwhile, the cost is high, the period is long, and individual differences cannot be reflected. According to the prediction model, digital characteristic data, drug dosage and cell line multi-omics data of drugs are integrated, the prediction model adopts a combined transfer learning algorithm, parameters of a single drug response model are migrated into a drug combination model, a gene function module is introduced to enhance the interpretability of the model, and the prediction model can be applied to drug combination. Four cross validation strategies are adopted for evaluation of the prediction model, so that the drug response of drug combination of different candidate drugs is predicted, the method can be used for predicting the response of the drug combination, and the optimal drug combination and dosage are recommended.

The present disclosure provides an attention-based MIL model for use in extracting and characterising cell features, at both the cell level and the population level. To characterise cells, cells in a well are initially fed into the model. The cells in a well include a points cloud of cells and a point cloud of corresponding cell nuclei. The cells in the well are passed through a pretrained DFN encoder which extrapolates the cell and nuclei features from the cells in the well. These extracted features are then passed through a transformer based encoder to produced transformed versions of the extracted cell and nuclei features. These transformed features are then fed into at least two classifiers. One of the classifiers is a cell-level MLP classifier which is used to compare the cell features with known drug response to attempt to match a phenotype signature with a known drug response. One other classifier is the bag classifier which is used to compare the cell population features with that of known drug responses, again to attempt to match to a phenotype signature. The outputs of the cell classification and the bag classification are used to label the cells in the well with a drug label or a potential drug label / use case.

The invention relates to the technical field of knowledge maps, in particular to a veterinary treatment big data knowledge map construction method, which comprises the following steps of: acquiring animal case symptom characteristics, physical indexes, medical history records and intervention stage data, normalizing the symptom characteristics and encoding medical history to generate a case characteristic vector set; mapping symptoms and medicine nodes to establish a semantic relationship to calculate association strength, embedding physique and medical history to update node confidence to generate a personalized knowledge graph model, dynamically correcting edge weights in combination with feedback and medicine response, and extracting an effective intervention path to construct an association index to generate a veterinary treatment big data knowledge graph. According to the method, through normalization and sequential processing of multi-source case data, feature quantification and tracking are achieved, dynamic association is established based on semantic mapping and graph attention, confidence attenuation and an attribute weighting mechanism are fused, a node relation is optimized and self-adaptive evolution is carried out, individual difference and drug response capture is enhanced, and the updating performance of diagnosis and treatment knowledge is improved; and accurate and intelligent diagnosis and treatment analysis is promoted.

The present disclosure relates to a discovery platform including machine-learning techniques for using medical imaging data to study a phenotype of interest, such as complex diseases with weak or unknown genetic drivers. An exemplary method identifying a covariant of interest with respect to drug response phenotype (DRP) of a treatment is disclosed.

The application discloses a prediction method, system and storage medium for patient drug reactions. The method comprises: constructing a data architecture of a drug reaction prediction model according to pre-input source domain data, target domain data and drug attribute information; based on the data architecture of the drug reaction prediction model, performing training on the drug reaction prediction model according to a target training function to determine execution parameters of the drug reaction prediction model; and determining drug reaction prediction parameters according to the execution parameters, the source domain data and the target domain data to determine a prediction result of the patient drug reaction. The application places the representation alignment process of the patient sample and the cell line sample in the specific drug context fusion information through drug conditionalization alignment, thereby reducing the cross-domain distribution difference. In addition, the drug priority prediction result is generated in units of patients by using the drug reaction prediction parameters, the risk of model degradation into drug identity memory is reduced, and the generalization prediction ability for drugs is enhanced.

Methods for the diagnosis, prognosis, patient stratification and prediction of pharmacological response in patients afflicted by psychiatric disorders based on electroretinography (ERG) parameters are described.

The application relates to a single-cell drug reaction prediction method and device based on dynamic distribution adaptation and multi-source domain feature weighting. The method comprises the following steps: acquiring batch RNA-seq and single-cell RNA-seq; processing to obtain a high-dimensional gene expression profile; mapping the high-dimensional gene expression profile to a low-dimensional potential representation, learning nonlinear features by minimizing the difference between the input and the reconstruction result, and supervising the training of a predictor on a source domain; in the case of a multi-source domain, a multi-source domain feature weighting network is used to generate a weight vector and adjust the source domain features by weighting; a dynamic distribution adaptation method is used for cross-domain knowledge transfer, and a maximum mean difference and an adaptive factor are used for dynamic balance distribution alignment; based on the dynamic distribution adaptation method and the multi-source domain feature weighting, a classifier model is transferred to a target domain for unsupervised drug reaction prediction. The application can improve the prediction performance of the model on the target domain.

The invention belongs to the technical field of bioengineering, particularly relates to the field of tumor animal model research, and particularly provides a primary in-situ hepatocellular carcinoma animal model and a construction method thereof, and the primary in-situ hepatocellular carcinoma animal model is characterized in that primary in-situ hepatocellular carcinoma is formed in an animal liver; the primary in-situ hepatocellular carcinoma is formed in a primary in-situ manner by introducing a gene-edited liver organ into an animal liver tissue. The innovative hepatocellular carcinoma model construction technology promotes the primary in-situ development of long liver organs after gene editing into hepatocellular carcinoma, not only is the preparation period shorter, but also the tumor formation efficiency is higher, the occurrence and development, pathological conditions and clinical drug response of liver cancer patients can be effectively simulated, the full simulation of the tumor microenvironment is realized, and the application prospect is wide. And the development and research of new drugs and new treatment methods can be better guided.

The invention relates to the technical field of bioinformatics, in particular to a drug response prediction method based on knowledge graph and multi-view comparative learning, which comprises the following steps: acquiring drug response information and a target knowledge graph, and further constructing low-order and high-order views according to the drug response information and the target knowledge graph; extracting the embedded representation of each entity in the low-order view and the high-order view by using the knowledge graph attention network, and carrying out iterative updating to generate the embedded representation of the target biological entity; performing comparative learning tasks in a single view and among a plurality of views in the low-order view and the high-order view at the same time to update the embedded representation of the entity; and carrying out nonlinear transformation on the updated embedding representation to obtain a final embedding representation, and further obtaining a reaction prediction result between the drug and the cancer cell line. According to the method, information is captured through an attention mechanism, more high-order knowledge graph information is explored by utilizing a multi-view contrast learning mechanism, and the response of a cell line to a drug can be accurately predicted.

The utility model relates to the technical field of medicine production equipment, and discloses medicine production mixed reaction equipment with a self-cleaning structure, which comprises a tank body, a feed hopper is fixedly arranged at the upper end of the right side wall of the tank body in a penetrating manner, and a discharge pipe with a valve is fixedly arranged at the bottom of the tank body in a penetrating manner; a rotating rod penetrates through a longitudinal bearing in the center of the top of the tank body, and stirring blades are uniformly mounted on the surface of the rotating rod. According to the mixing reaction equipment with the self-cleaning structure for medicine production, the inner wall of the tank body can be scraped and cleaned in the stirring and mixing reaction process of medicines, and the situation that the medicines are adhered and cannot participate in the mixing reaction is avoided, so that the medicine mixing reaction effect is guaranteed, the medicine effect is guaranteed, and after the medicines react and are discharged, the medicine production efficiency is improved. By spraying water and cooperatively scraping the interior of the tank body, the interior of the tank body is cleaned, cleanliness and sanitation are guaranteed, follow-up medicine mixing reaction is facilitated, operation is easy, convenient and flexible, and practicability is high.

Provided herein are methods of determining a molecular response score for use in predictive models. The molecular response score may be used to monitor and guide administration of treatment to a subject.

The present invention relates to the field of precision medicine technology, specifically a system, method, and storage medium for interpreting precise tumor medication, including: a data acquisition module for collecting genetic data, clinical data, and drug response data of tumor patients from multiple data sources; a data standardization processing module for formatting and standardizing the data to ensure a consistent format and enable effective processing and analysis in subsequent modules; a genetic data analysis module for performing variation analysis based on the patient's genetic data, identifying gene mutation sites, and generating drug sensitivity analysis results; and a drug screening module for screening drugs that match the patient's gene mutation sites from a drug database based on the genetic data analysis results, and providing drug dosage recommendations. By adopting a technical solution that combines quantum optimization technology with genetic data analysis, the technical effect of significantly improving the accuracy of drug screening and dosage recommendations is achieved.

The application provides a cross-institutional referral intelligent routing method and system based on a medical intelligent agent middleware, relates to the technical field of medical informatization, and comprises the following steps: establishing a sign data monitoring window, mapping sign index changes and medication record time sequences, constructing a drug reaction sensitivity curve to calculate a treatment effective coefficient; adopting a dynamic time warping algorithm to match a drug-sign correlation graph, and generating a treatment decision tree; and predicting disease development, identifying the best referral opportunity and target institution based on the treatment effective coefficient and specialty characteristics. The application improves cross-institutional referral efficiency, optimizes medical resource allocation, and enhances patient treatment effect.

The invention provides an unbalanced drug response data resampling method and device based on swarm intelligence optimization, a storage medium and equipment, and belongs to the field of unbalanced data classification in data mining. The method comprises the following steps: firstly, generating an initial sampled drug reaction data candidate set; training the classification performance of a classifier according to each drug reaction data candidate set; dynamically adjusting a sample selection strategy, and iteratively updating samples contained in each candidate set through a position updating formula; and finally, outputting to obtain a globally optimal drug reaction resampling data set. The method can be compatible with continuous swarm intelligent optimization algorithms (such as a particle swarm optimization algorithm and a grey wolf optimization algorithm), and is suitable for drug reaction unbalanced data classification tasks of different scales and distribution characteristics.

The invention discloses an intratumor microbial marker group for gastrointestinal tumor prognosis, a prognosis model and application. The biomarker group comprises the following components: Granulicella, Thermodesuftator, Gaetbus, Formosa, Kaistobacter, Candidate Saccharimonas, Dactyloccopsis, Schwartzia, Candidate Kuenia, Sphingosinusus, Microvirgula, Simple, Doria, Halothiobacillus, Rhodobacter, and Oceaniterimus, and is characterized in that the biomarker group comprises the following components: the Granulicella, the Thermodesuftator, the Gaetbus, the Formosa, the Kaistobacter, the Candidate Saccharimonas, the Dactyloccopsis, the Schwartzia, the Candidate Saccharimonas, the The model constructed by the method can accurately predict prognosis, drug response and immunotherapy.

The invention relates to a drug effect evaluation method for fusing target molecules and time-concentration dependent cell phenotypes, which comprises the following steps: S1, preparing samples including a modeling sample and a to-be-detected sample; s2, carrying out FRET imaging and cell fluorescence imaging; s3, carrying out FRET image processing and FRET efficiency calculation; s4, cell fluorescence image processing and feature extraction; s5, calculating a phenotype characterization value; s6, calculating an FRET characterization value; s7, basic drug response value calculation; and S8, comprehensive drug effect evaluation. Target molecule information and time-concentration dependent cell phenotypic response are fused, a comprehensive drug effect evaluation model is constructed, the effect of drugs on whole cells is reflected, and whether the drugs target specified molecules or not is specifically indicated.

The invention discloses a construction method and application of a spontaneous atrial fibrillation mouse model, and belongs to the technical field of atrial fibrillation animal models. According to the construction method, a whole-body DYNLT1 gene knockout mouse is constructed by using technologies such as gene editing and the like, the DYNLT1 gene knockout mouse is systematically evaluated through methods such as body surface electrocardiogram, echocardiography and histopathologic examination, and the DYNLT1 gene knockout mouse shows typical characteristics of atrial fibrillation in the aspects of body surface electrophysiology, atrial structure remodeling and the like. And in the molecular level, atrial muscle cell apoptosis is increased, gap junction protein expression is reduced, and inflammatory factor level is increased, so that the model is confirmed to be a spontaneous atrial fibrillation mouse model. In addition, the model shows a rapid drug reaction to the atrial fibrillation cardioversion drugs, such as amiodarone and propafenone, and has the potential for screening the atrial fibrillation drugs. The animal model provides a new pathological model for atrial fibrillation mechanism research and drug screening, and has important scientific research and clinical application values.