Invention Grant
US08412466B2 Rapid method of pattern recognition, machine learning, and automated genotype classification through correlation analysis of dynamic signals
有权
通过动态信号的相关分析，模式识别，机器学习和自动化基因型分类的快速方法
- Patent Title: Rapid method of pattern recognition, machine learning, and automated genotype classification through correlation analysis of dynamic signals
- Patent Title (中): 通过动态信号的相关分析，模式识别，机器学习和自动化基因型分类的快速方法
-
Application No.: US12759415Application Date: 2010-04-13
-
Publication No.: US08412466B2Publication Date: 2013-04-02
- Inventor: Sami Kanderian
- Applicant: Sami Kanderian
- Applicant Address: US MD Rockville
- Assignee: Canon U.S. Life Sciences, Inc.
- Current Assignee: Canon U.S. Life Sciences, Inc.
- Current Assignee Address: US MD Rockville
- Agency: Rothwell, Figg, Ernst & Manbeck, P.C.
- Main IPC: G06F19/00
- IPC: G06F19/00 ; G06F15/00 ; C12Q1/68
Abstract:
The present invention relates to methods and systems for the analysis of the dissociation behavior of nucleic acids and the identification of determining whether a genotype is present in a biological sample. This includes methods and systems for determining whether a genotype is present in a biological sample, through generating a dynamic profile an unknown genotype, correlating the dynamic profile to an average profile for a known genotype to generate a correlation value, and determining whether the correlation value falls within an acceptable threshold to determine if the unknown genotype is the known genotype. The present invention also relates to methods and systems for generating a training set to allow a machine to recognize a known genotype from within a class of known genotypes. The training set generated by these methods and systems may be used to assist in identification of unknown genotypes.
Public/Granted literature
Information query
