Back to results
US 2013/0280712 A1Published application
Method of Detecting Nucleic Acid Targets Using a Statistical Classifier
AssigneeRoche Molecular Systems, Inc.
InventorWei-Min Liu
Life of this patent
Estimating the term…
Abstract
A method of detecting a target nucleic acid in a test sample utilizes a learning statistical classifier system to build a general linear classifier based on an amplification-dependent parameter for the target and the control nucleic acids, in order to classify the test sample as containing or not containing the target nucleic acid.
Claims17
A method of detecting the presence or absence of a target nucleic acid in a test sample comprising:
- (a) inputting into a learning statistical classifier system data from a training set of samples where the amount of the target nucleic acid and a control nucleic acid is known,
- (b) using the learning statistical classifier system, calculating a plurality of weights for a general linear classifier;
- (c) building a general linear classifier with the plurality of weights calculated by the learning statistical classifier system in step (b);
- (d) contacting the test sample with a reaction mixture containing reagents necessary to amplify the target and the control nucleic acids by polymerase chain reaction (PCR) under conditions enabling PCR;
- (e) measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain a test set of data;
- (f) applying the general linear classifier built in step (c) to the data obtained in step (e) to classify the test sample as containing or not containing the target nucleic acid, thereby detecting the presence or absence of the target nucleic acid in the test sample.
3 more elements
A method of detecting the presence or absence of a target nucleic acid in a test sample comprising:
- (a) inputting into a learning statistical classifier system data from a training set of samples where the amount of the target nucleic acid and a control nucleic acid is known;
- (b) using the learning statistical classifier system, calculating a plurality of weights for a general linear classifier;
- (c) building a general linear classifier with the plurality of weights calculated by the learning statistical classifier system in step (b);
- (d) subjecting the sample to polymerase chain reaction (PCR);
- (e) measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain a test set of data;
- (f) applying the general linear classifier built in step (c) to the test set of data obtained in step (e);
- (g) classifying the test sample as containing or not containing the target nucleic acid, thereby detecting the presence or absence of the target nucleic acid in the test sample.
4 more elements
A method of determining whether a target nucleic acid is present in a test sample comprising:
- (a) subjecting a training set of samples wherein the amount of the target nucleic acid and a control nucleic acid is known to polymerase chain reaction (PCR) and measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain a training set of data;
- (b) inputting into a learning statistical classifier system the data obtained in step (a);
- (c) using the learning statistical classifier system, calculating a plurality of weights for a general linear classifier;
- (d) building a general linear classifier with the plurality of weights determined by the learning statistical classifier system in step (c);
- (e) subjecting the test sample to PCR and measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain a test set of data;
- (f) applying the general linear classifier built in step (d) to the data obtained in step (e);
- (g) classifying the test sample as containing or not containing the target nucleic acid.
4 more elements
A method of determining whether a target nucleic acid is present in a test sample comprising:
- (a) subjecting a training set of samples wherein the amount of the target nucleic acid and a control nucleic acid is known to polymerase chain reaction (PCR) and measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain a training set of data;
- (b) inputting into a learning statistical classifier system the data obtained in step (a);
- (c) using the learning statistical classifier system, calculating a plurality of weights for a general linear classifier;
- (d) building a general linear classifier with the plurality of weights determined by the learning statistical classifier system in step (c);
- (e) subjecting the test sample to PCR and measuring at least one amplification-dependent parameter for the target and the control nucleic acids to obtain the test set of data;
- (f) applying the general linear classifier built in step (c) to the data obtained in step (e);
- (g) classifying the test sample as containing or not containing the target nucleic acid.
4 more elements
A computer readable medium including code for controlling one or more processors to classify whether a test sample contains a target nucleic acid, the code including instructions to:
- (a) apply a learning statistical classifier system to a training data set where the amount of the target nucleic acid and a control nucleic acid is known, in order to build a general linear classifier of Formula I;
- (b) apply the general linear classifier built in step (a) to a testing data set comprising the data from the test sample to produce a statistically derived decision classifying the test sample as containing or not containing the target nucleic acid.
A system for detecting a target nucleic acid in a test sample comprising:
- (a) a data acquisition module configured to produce a data set from a training set of samples and one or more test samples, the data set indicating presence and amount of the target nucleic acid and a control nucleic acid;
- (b) a data processing unit configured to process the data acquired by the acquisition module by applying a learning statistical classifier system to the training data set in order to build a general linear classifier of Formula I, and then apply the general linear classifier of Formula I to the test data set comprising the data from the test sample, to produce a statistically derived decision classifying the test sample as containing or not containing the target nucleic acid;
- (c) a display module configured to display the data produced by the data processing unit.
Dependencies are inferred from the claim text.