135 results about "Genetic data" patented technology

The invention discloses an interpretable machine learning genome prediction method and device, belongs to the technical field of combination of biological breeding, biological information and machine learning, and utilizes an advanced machine learning algorithm to perform parameter optimization in combination with biological prior information. Through processing of multi-source data (genome, transcriptome and epigenetic data), dynamic feature engineering (PCA and PHATE dimensionality reduction) and organic combination of various machine learning models, and an automatic parameter adjustment framework based on a grid search and sparrow search algorithm, genome prediction precision and calculation efficiency are significantly improved; meanwhile, the interpretability of the model is realized based on the SHAP value, the SNP site contribution is quantified, a reference is provided for precise breeding, and the method is suitable for animal and plant molecular breeding and medical genetic analysis, and can accelerate genetic analysis of high-value characters, assist precise breeding decision and disease risk prediction, and promote leap-forward development from experience breeding to intelligent breeding.

The invention belongs to the technical field of intelligent medical treatment, and provides an active health hierarchical management method based on multi-modal fusion and electronic device.The method comprises the steps that dynamic data and static data of a to-be-assessed person are obtained, physiological time sequence data and behavior time sequence data are input into a spatial-temporal feature extraction module, and the spatial-temporal feature extraction module is used for extracting spatial-temporal features of the to-be-assessed person; extracting a time sequence dependency relationship in the dynamic data, and identifying an abnormal feature sequence based on the time sequence dependency relationship by using a self-attention mechanism to obtain a dynamic risk feature; inputting the genetic data and the environmental exposure data into the static feature extraction module, and extracting static risk features based on a multi-head attention mechanism; fusing the obtained dynamic risk features and the static risk features by using a dynamic gating mechanism to obtain fused features; and transmitting the fusion features to the full connection layer to obtain health risk grade results of different time scales, and outputting a health hierarchical management file based on the health risk grade results.

Processes that determine transcriptional regulation from genetic sequence data are described. Generally, computational models are trained to predict transcriptional regulatory effects, which can be used in several downstream applications. Various methods further develop research tools, develop and perform diagnostics, and treat individuals based on identified variants.

The invention discloses an SNP (Single Nucleotide Polymorphism) marker-based rice disease resistance character whole genome association analysis method, which relates to the technical field of biology, and is characterized by comprising the following steps: selecting a representative genetic recombination population, carrying out high-density SNP genetic typing on the population, and combining recombination event positioning and linkage analysis to obtain the disease resistance character whole genome association analysis of rice. Obtaining genetic parameters reflecting recombination frequencies of different genome segments; on the basis of the obtained original genetic data, parent and offspring genotype information is further integrated, fine positioning and statistics are carried out on recombination breaking points, and a high-resolution genetic map is constructed. By constructing a high-resolution genetic map and combining feature engineering and machine learning, accurate identification and dynamic SNP encryption of a high-recombination region are realized, the marker coverage and associated signal capture capability of the region is enhanced, the functional site leak detection risk is reduced, and the detection efficiency is improved. The positioning accuracy and the molecular breeding application effect of the rice disease resistance character related candidate gene are improved.

A health and wellness system for a non-human subject comprising analyzing genetic data and phenotypic data of the non-human subject with a machine learning algorithm and making a recommendation or recommendation for products or activities for the non-human subject.

The invention relates to the technical field of bioinformatics, in particular to an embryo gene detection and analysis system for data storage. Comprising a signal standardization unit, a data preprocessing unit, a storage optimization unit, a machine learning analysis unit, an intelligent report unit and a safety calculation unit. Through intelligent segmentation, parallel computing and SIMD optimization of the data preprocessing unit, the processing efficiency and quality of original sequencing signals are greatly improved, and meanwhile, the machine learning analysis unit utilizes a generative adversarial network and auto-encoder fusion model, a transfer learning and meta-learning strategy and a multi-modal fusion technology; the deep mining of gene data features, the improvement of model generalization ability and the effective integration of multi-source data are realized, so that the embryo health is accurately evaluated, the disease prediction accuracy is improved, and the accuracy, robustness and clinical application value of the system are remarkably enhanced.

The present invention generally relates to systems (100) and methods for generating, managing, and displaying non-fungible digital representations (102) of living, biological, and / or eukaryotic organisms (104). More specifically, the systems (100) and methods for generating, managing, and displaying non-fungible digital representations (102) include genetic material (106), such as single nucleotide polymorphisms. The systems (100) and methods can record genetic data from the genetic material (106) on a blockchain (114) and can generate and display the non-fungible digital representation (102) of the living, biological, and / or eukaryotic organisms (104) that are based on the genetic data on the blockchain (114).

The invention relates to the technical field of image processing and recognition, and provides an Alzheimer's disease multi-mode classification method based on electroencephalogram, brain image and genetic information, and the method comprises the steps: obtaining electroencephalogram data, brain image data and genetic data of a subject, and carrying out the corresponding preprocessing operation; performing feature extraction on the preprocessed electroencephalogram data, brain image data and gene data to obtain electroencephalogram signal features, brain image features and AD susceptibility features of the subject; respectively carrying out corresponding standardization processing on the features of the three different modes of the subject, then carrying out feature selection, eliminating irrelevant features and redundant features, and finally carrying out feature fusion to obtain fused features; according to the method, binary classification and multi-classification are carried out on the basis of the features of the three different modes after feature fusion and feature selection, and a disease discrimination result of the subject is obtained on the basis of a binary classification result and a multi-classification result, so that the Alzheimer's disease recognition precision is effectively improved.

Systems and methods for generating a likelihood score that is indicative of a likelihood of a pet developing at least one of a disease, a clinical condition or other trait are disclosed. An example method may include: receiving, at a server system, pet data associated with the pet, wherein the pet data includes genetic data and breed data; generating, using a processor of the server system, a likelihood score for the pet associated with the clinical condition by applying the pet data to a trained machine learning model, wherein the trained machine learning model is trained to predict likelihood scores for the clinical condition; and causing, by the processor of the server system, a visual representation of the likelihood score to be displayed on a user device, wherein the visual representation includes an indication of the likelihood of the pet developing the clinical condition. Other aspects are described and claimed.

The invention relates to the technical field of medical instrument quality management, in particular to a medical instrument monitoring method and system, and the method comprises the steps: firstly generating design gene data containing a model code, a physical unclonable fingerprint and a quantum public key at a design freezing node, and writing the design gene data into a Twindow-DNA chip; in the manufacturing stage, process parameters and scattering optical data are synchronously collected, an optical domain super-vector is constructed and spliced with process embedding to form manufacturing embedding characteristic data, and the manufacturing embedding characteristic data are encrypted and then sent to a digital twinborn body; performing twin calculation on a normalized residual error, generating a residual error vector through vector holographic convolution and multi-stage diffusion denoising when the normalized residual error exceeds a threshold value, inputting the residual error vector into a super-vector converter to obtain defect semantic data, and writing the defect semantic data into a three-division hypergraph account book which takes a quantum public key as an index by using zero knowledge commitment; and calling the hypergraph neural network and the neural relationship inference model according to a fixed time interval, outputting correction-prevention data, writing the correction-prevention data back to a manufacturing execution system, and meanwhile, performing hash chain writing on the correction-prevention data to form a quality closed loop and support operation decision and regulation delivery.

The invention provides an Alzheimer's disease diagnosis system based on image gene data fusion, which innovatively introduces a decoupling representation technology, divides features of multi-modal data into global representation and local representation, retains unique information of each data modal by respectively extracting global features and local features, and improves the diagnosis accuracy of the Alzheimer's disease. Efficient fusion of shared information is realized; through the innovative multi-modal feature fusion method, the accuracy and stability of complex disease prediction and diagnosis are remarkably improved, and the problem that cross-modal features and modal internal features cannot be captured at the same time in the prior art is solved.

The invention provides a Kawasaki disease coronary artery disease risk dynamic prediction algorithm and an automatic upgrading system. The Kawasaki disease coronary artery lesion risk dynamic prediction algorithm and the automatic upgrading system comprise the following steps: a, acquiring clinical data of a Kawasaki disease child patient, including data of disease date, sex, month age, serum sodium level, D dimer, erythrocyte distribution width, prothrombin time and C-reactive protein biomarker; according to the Kawasaki disease coronary artery disease risk dynamic prediction algorithm and the automatic upgrading system, through combination of clinical features and gene data of Kawasaki disease children patients, a plurality of machine learning algorithms are used, and an efficient and accurate CAL risk prediction model is constructed. The model combines a plurality of key clinical indexes such as serum sodium level, CRP and D dimer and gene data such as SNP markers such as SIGLEC8-CEACAM18 and PPP1R1C, and the sensitivity and specificity of risk prediction are remarkably improved.

The invention discloses a gene feature extraction method in gene data based on sequence search, and relates to the technical field of biological information. The problems that gene data is wide in source and diversified in format, data processing is extremely complex, data of different formats are difficult to integrate and analyze, and the accuracy and efficiency of feature extraction are affected are solved. According to the method, gene data are comprehensively preprocessed, low-quality and redundant parts are removed, reliable data quality is ensured, data distribution and data conversion are performed at the same time, high-similarity gene feature regions are accurately screened through sequence comparison, importance weights of gene features are determined by using clustering group features, key features are reasonably screened, and the accuracy of gene feature extraction is improved. Data dimensions are effectively reduced, the feature extraction efficiency and accuracy are improved, local and global features are fused to construct a comprehensive feature vector, the feature expression ability is enhanced, a screening result is verified by constructing a test data set, and the accuracy and reliability of the gene feature extraction method are continuously improved.

Methods of predicting a chromatin state metric associated with a genomic region in a sample are provided. The methods comprise: receiving sequence data comprising genetic data and epigenetic data indicative of the presence of one or more epigenetic bases including methylated cytosine and hydroxymethylated cytosine at one or more genomic positions, the one or more epigenetic bases, the genetic data and epigenetic data obtained from a single assay; and predicting for each base or set of bases of the genomic region and using the sequence data associated with the genomic region, a value of the chromatin state metric, wherein the predicting is performed using a machine learning model.

According to an embodiment, disclosed is a system comprising a processor configured to receive an image of a breast of a patient and patient data comprising genetic data; extract features from the image and the patient data, using one or more machine learning models, wherein the features comprise a presence of a calcification and a calcification pattern to generate a breast calcification vector; augment the breast calcification vector with the genetic data; determine, using the machine learning models, a first risk for a breast cancer; a second risk to one or more organs of the patient, wherein the organs comprises one or more of heart, kidney, lungs, pancreas, and brain; predict, a third risk based on one or more of a healing response, a tumor flow and growth, inflammation and degeneration, a disease relapse, an adverse event, and a clinical response; and determine, an overall risk to the patient.

This application, in the field of intelligent medical technology, provides a proactive health stratification management method and electronic device based on multimodal fusion. The method includes: acquiring dynamic and static data of the person to be assessed; inputting the physiological time-series data and the behavioral time-series data into a spatiotemporal feature extraction module to extract the temporal dependencies in the dynamic data, and using a self-attention mechanism to identify abnormal feature sequences based on the temporal dependencies to obtain dynamic risk features; inputting the genetic data and the environmental exposure data into a static feature extraction module to extract static risk features based on a multi-head attention mechanism; fusing the obtained dynamic risk features and the static risk features using a dynamic gating mechanism to obtain fused features; passing the fused features to a fully connected layer to obtain health risk level results at different time scales, and outputting a health stratification management file based on the health risk level results.

Systems and methods for predicting the epidemic rate of loss of heterozygosity (LOH) in a target cell population, where the system includes a memory and a processor configured to receive genetic data of a first reference cell population. The processor is configured to sequence the genetic data of the first reference cell population to obtain first reference data; identifying and removing heterozygous variant positions with unbalanced allele expression in the first reference data to generate second reference data; mapping an identifier of each cell of the target cell population to the second reference data; and applying the mapping identifier for each cell of the target cell population to a supervised machine learning model. The processor is further configured to receive one or more outputs from the model, at least one of the one or more outputs comprising an LOH of the target cell population.

The invention discloses an astragalus sinicus breeding genetic data mining system based on bioinformatics, and particularly relates to the technical field of data mining. The method comprises the following steps: acquiring and synchronizing original sequencing data of an astragalus sinicus host genome and a rhizobium symbiotic microorganism genome to generate a standardized genetic information data set; the method comprises the following steps: identifying sequence cross contamination sites between a host genome and a symbiotic microorganism genome, and eliminating genetic information interference of a microorganism source, so as to obtain purified host genome data without microorganism interference; analyzing the contribution degree of the microbial genome to the target character of the astragalus sinicus to obtain a microbial effect weight; integrating the purified host genome data and the microbial effect weight, constructing an astragalus sinicus character association analysis model, and positioning character association sites; and finally, screening candidate breeding markers based on character associated site information to obtain a precise breeding genetic marker set. According to the method, the accuracy and efficiency of milk vetch breeding are improved.

A system for generating a seed recommendation is disclosed. The system includes a processor, a display, and a memory. The processor may be configured to retrieve genetic data having a first dimensionality; generate embeddings corresponding to the genetic data, the embeddings having a second dimensionality lower than the first dimensionality; categorize the embeddings into one or more clusters, such that genetically similar seed products are assigned to the same cluster based on the embeddings of the genetically similar seed products; using agronomy data, assign additional seed products to the one or more clusters; generate a recommendation to a grower to plant a first seed categorized in a first cluster, when the grower has previously planted a second seed in the first cluster; and cause the display to display the generated recommendation to the grower.

The invention provides a Mendel randomization nonlinear causal inference method based on genome research, and relates to the technical field of biological genetic data analysis, and the method comprises the following steps: obtaining a tool variable, an exposure factor and a result variable, and carrying out data preprocessing to form a structured input matrix; respectively constructing a tool variable nonlinear model and a causal effect nonlinear model; calculating a loss function of the model, and adding a regularization item for joint optimization; optimizing model parameters by using a GBDT kernel method; updating the model based on the optimized model parameters and drawing a nonlinear response curve of the exposure factors and the result variables; replacing the tool variable with a pseudo tool variable to repeat the above steps to verify a causal inference result, and inferring a causal effect according to the verified causal inference result; according to the method, the limitation of assuming a linear relation and processing high-dimensional data in a traditional causal inference method can be overcome, and a more accurate, robust and interpretable causal inference result is provided.

The present invention provides a method and system for encrypted storage and inference of DNA barcodes of rare and endangered species, which relates to the field of encrypted inference technology, including: obtaining a rare and endangered species monitoring data set and a corresponding biological sample set; constructing an encrypted database based on the monitoring data set to obtain an anti-parsing database framework; encrypting the DNA barcodes based on the biological sample set to obtain an encrypted barcode set; generating a single valid sequence based on a verification sequence generated by the DNA sample to be identified; performing collaborative inference verification based on the single valid sequence and the encrypted barcode set to generate a species identification code; performing a comprehensive judgment based on the species identification code and the monitoring data set, and outputting an identification result by correlating morphological feature changes with geographic distribution density. By constructing an anti-parsing encrypted database framework and a functionally limited DNA barcode set, the present invention achieves active protection of rare species genetic data and solves the key hidden danger of sensitive biological information being used for poaching tracing.

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.

A method for practicing precision medicine comprising providing, to a blockchain platform, each of clinical data and genetic data, providing the blockchain platform, the blockchain platform having a first data structure comprising clinical data and a second data structure comprising genetic data, harmonizing the first and second data structures, creating at least one cohort based on the harmonized first and second data structures, and identifying at least one relationship between the clinical data and the genetic data in each of the at least one cohort.

The invention relates to a construction method of an arteriosclerosis risk assessment model, an arteriosclerosis risk assessment method, and application of an arteriosclerosis biomarker and a reagent for detecting the biomarker in preparation of a kit for predicting, preventing and / or treating arteriosclerosis. The construction method of the arteriosclerosis risk assessment model comprises the steps that correlation analysis is conducted based on genetic data and background data of a population to obtain correlation significance values corresponding to SNP loci, and the genetic data comprises the SNP loci and genotypes of the SNP loci; the arteriosclerosis risk assessment model is constructed on the basis of the SNP loci and the associated significance values corresponding to the SNP loci, and the arteriosclerosis risk assessment model comprises one or more of the SNP loci shown in the table 1. The arteriosclerosis risk assessment model obtained according to the construction method provided by the embodiment of the invention considers the specific genetic background, lifestyle, environmental factors and the like of Chinese population, the AUC of the obtained model reaches 0.693, and the arteriosclerosis risk of an individual to be analyzed can be accurately and effectively assessed.

Methods arc provided for making a plant genome having a desired nucleic acid sequence. One example method includes identifying genomic segments of a plant that include at least one desired nucleic acid sequence, using a trained neural network, which is biology-informed through first pre-training connections between a genetic data layer and at least one intermediate layer and second pre-training connection between the at least one intermediate layer and a phenotypic layer. The method also includes recombining the at least one at least one desired nucleic acid sequence with a second nucleic acid sequence to form a target plant genome.

An example embodiment may involve receiving, by way of a user interface of a computing system, an indication of a healthcare patient profile and further input; based on the indication of the healthcare patient profile, obtaining, by the computing system, health records and genetic data of a patient associated with the healthcare patient profile; based on the health records and the genetic data of the patient and the further input, generating, by the computing system, a natural language prompt, wherein the natural language prompt contains instructions to generate a healthcare document for the patient; providing, by the computing system, the natural language prompt to a generative natural language model; receiving, by the computing system, the healthcare document from the generative natural language model; and providing, by way of the user interface, a version of the healthcare document.

This invention discloses an automatic control method for the width of hot-rolled steel coils. First, width data from the slab production process is collected and its average value is calculated. Then, the actual steel pulling amount for finishing rolling and coiling is calculated, and an adaptive genetic table for steel pulling amount is created. After the slab is drawn, the adaptive genetic table for steel pulling amount is queried to obtain genetic data. If retrieval fails, the process returns and a default width allowance value is selected. If retrieval is successful, the predicted coiling width allowance value is calculated for the strip to be rolled. Next, a recommended width allowance correction value is calculated. Then, the width allowance of the electrical equipment is set according to the default width allowance value or the recommended width allowance correction value to control the slab rolling process. Finally, data is stored and the adaptive genetic table for steel pulling amount is updated. This invention improves the finished product width accuracy through staged stable control of steel pulling amount, significantly reduces the proportion of manual intervention, significantly increases the width hit rate at the roughing mill exit, and improves the stability of production line width control.

The invention relates to the technical field of livestock breeding, and discloses a sheep variety breeding method combining phenotype data and gene information, and the method comprises the steps: building a data collection module, a data analysis module, a seed selection and reproduction module, a monitoring module, a genetic stability evaluation module and a feedback adjustment module; the data analysis module is used for analyzing data of the data acquisition module, calculating and evaluating growth, gene conditions and environmental correlation and providing a basis for breeding, a seed selection strategy is formulated in the seed selection and reproduction module, the monitoring module records multi-generation genetic data, and the genetic stability evaluation module is used for evaluating the genetic stability of the sheep flock subjected to multi-generation breeding. And comparing and analyzing the change conditions of gene frequencies and genotype distribution genetic parameters before and after multi-generation breeding, calculating a historical genetic stability coefficient As according to the gene frequencies before and after multi-generation breeding, evaluating a breeding effect and finding a problem improvement direction, and adjusting seed selection by a feedback adjustment module according to an evaluation result of a genetic stability evaluation module.

The present disclosure relates to analyzing genetic data. In one arrangement, a method operates on input data comprising the strength of association between one or more phenotypes, including a target phenotype, and a plurality of genetic variants. A fine-mapping algorithm is applied to all or a subset of the input data to identify one or more independent phenotype-variant associations. For each association, a set of one or more fine-mapped variants is identified. A fine-mapping prediction model is calculated based on the input data and the set of fine-mapped variants. The effect of the set of fine-mapped variants on the target phenotype is subtracted from the input data to obtain residual association data. A machine learning algorithm is applied to the residual association data to identify further predictive correlations between the target phenotype and the plurality of genetic variants.