Automated analysis of analytical gels and blots
AssigneeQuest Diagnostics Investments Incorporated
InventorsNilesh Saratkar, Stanley Naides, Michelle A. Cleveland
Life of this patent
Estimating the term…
Abstract
The present solution describes an automated system for analyzing analytical gels or blots, such as electrophoresis gels. The system can automatically detect the lanes within the gel and convert the lane into a feature vector that can be compared to reference datasets. Based on a comparison of the feature vector to the reference datasets, the system can automatically classify the feature vector (and the test sample in the lane) into a phenotype group.
Claims16
A system to process data from an analytical gel or blot, comprising:
- (i) a lane detector, executed by one or more processors, to identify a plurality of lanes in a first digital image, wherein the first digital image comprises an analytical gel or blot;
- (ii) a feature generator to determine a lane intensity vector for each of the plurality of lanes in the first digital image, wherein the lane intensity vector passes through the length of the plurality of lanes;
- (iii) a classifier to:
- determine a correlation score for each of the plurality of lanes in the first digital image, wherein the correlation score is based on the lane intensity vector for a respective lane of the plurality of lanes and a reference lane intensity vector;
- and
- associate a classification to the each of the plurality of lanes in the first digital image based on the correlation score for the respective lane in the first digital image, wherein the classification is a phenotype;
- and
- (iv) an image preprocessor to convert the digital image into a grayscale image.
A method to process data from an analytical gel or blot, comprising:
- (i) receiving, by an image processor comprising one or more processors, a first digital image comprising an analytical gel or blot;
- (ii) converting, by the image processor, the digital image into a grayscale image;
- (iii) identifying, by the image processor, a plurality of lanes in the first digital image;
- (iv) determining, by the image processor, a lane intensity vector for each of the plurality of lanes in the first digital image, wherein the lane intensity vector passes through the length of the plurality of lanes;
- (v) determining, by the image processor, a correlation score for each of the plurality of lanes in the first digital image, wherein the correlation score is based on the lane intensity vector for a respective lane of the plurality of lanes and a reference lane intensity vector;
- and
- associating, by the image processor, a classification to the each of the plurality of lanes in the first digital image based on the correlation score for the respective lane in the first digital image, wherein the classification is a phenotype.
Dependencies are inferred from the claim text.