Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

72 results about "Methylation analysis" patented technology

Methylation analysis method and device for active region of circulating cell-free nucleosome, terminal equipment and storage medium

ActiveCN112735531AAuxiliary early diagnosisAid early screeningProteomicsGenomicsCell freeTerminal equipment
The invention provides a methylation analysis method and device for an active region of circulating cell-free nucleosome, terminal equipment and a storage medium, and the method comprises the steps: obtaining capture sequencing data of a to-be-detected plasma sample, and extracting cfDNA molecular fragments from the capture sequencing data; based on the extracted cfDNA molecular fragments, adopting windows to perform sliding operation in genome intervals of the cfDNA molecular fragments, and calculating the ratio of the number of cfDNA molecules crossing the whole window end to end in each window to the number of all cfDNA molecules in different conditions covered by the window; based on the calculated ratio, screening out an interval having significant difference with a baseline nucleosome activity difference area created according to the healthy person sample through a Kolmonov Schmidov test method to obtain a nucleosome activity area; calculating the methylation phenotypic characteristics of the screened nucleosome active area, completing methylation analysis of the circulating acellular nucleosome active area. The method can effectively assist in distinguishing the source of the plasma sample to be detected.
Owner:臻和(北京)生物科技有限公司 +1

DNA methylation marker for predicting risk of primary breast cancer, and screening method and application of DNA methylation marker

The invention discloses a DNA methylation marker for predicting the risk of primary breast cancer, and a screening method and application of the DNA methylation marker. The method comprises the following steps: (1) performing methylation analysis on sample data to obtain methylation sites related to prediction of primary breast cancer occurrence risks; (2) obtaining methylation Beta values for themethylation sites; (3) constructing a primary breast cancer occurrence risk prediction model based on the methylation Beta values of the methylation sites, and verifying the feasibility of the modelby calculating a ratio; (4) constructing a primary breast cancer occurrence risk prediction model based on the methylation sites by adopting a machine learning method, calculating a ratio ratio, AUC,a recall rate, an accuracy rate and an F1 value, and performing mutual verification with the prediction model in the step (3); and (5) obtaining the methylation sites corresponding to the methylationprobe in the prediction model as the DNA methylation marker. The DNA methylation marker can improve the detection rate of primary breast cancer, and is suitable for large-scale popularization and application.
Owner:武汉百药联科科技有限公司 +1

Plasma sample cancer early screening method based on ensemble learning

The invention discloses a plasma sample cancer early screening method based on ensemble learning, and belongs to the field of cancer early screening. The cancer early screening method comprises the following steps: 1, taking data obtained by performing characteristic value extraction on ctDNA mutation and methylation analysis data in plasma as a training set and a verification set, and then respectively importing the training set into a gradient boosting tree model and a classification model of a support vector machine; 2, fusing the gradient boosting tree model trained in the step 1 and the classification model of the support vector machine trained in the step 1 to obtain an integrated classification model; 3, importing the verification set in the step 1 into the integrated classification model in the step 3, and obtaining a classification result through a voting mechanism, namely, a cancer early screening result. The performance of the model is optimized under different training conditions, the adaptability to sample size, sample feature distribution and the like during model training is enhanced, the stability of the model is effectively improved, the reliability in practical application is ensured, and stable prediction precision is generated.
Owner:哈尔滨智吾康科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products