High-Resolution Melt Curve Classification Using Neural Networks
AssigneeSRC, Inc.
InventorsJonathan David Adelman, William Ryon McKay, Jacquelyn Lillis, Katherine Lawson
Life of this patent
Estimating the term…
Abstract
The present invention relates to a method and system for classifying high-resolution melt (“HRM”) curves, and, more specifically, to a method and system for classifying HRM curves by genotype where the curves are represented by a mathematical function with varying coefficient values.
Claims11
A method for classifying high resolution melt (“HRM”) curve data by genotype, the method comprising:
- obtaining melt curve data from double-stranded DNA from an obtained biological sample of interest;
- determining, by a processor, a corresponding mathematical function of at least one melt curve represented by melt curve data;
- determining, by the processor, the mathematical function's coefficient values;
- using the coefficient values as inputs for classification in a classification tool, wherein said classification tool is configured to classify the melt curve data as either a known genotype or an unknown genotype based on the inputted coefficient values.
The method of claim 2, wherein the step of determining, by a processor, a corresponding mathematical function of at least one melt curve represented by melt curve data further comprising the step of using a Chebyshev polynomial expansion.
The method of claim 4, wherein the step of using a Chebyshev polynomial expansion is pursuant to the following equation:
- T0(x)=1
- T1(x)=x
- tn+1(x)=2xTn(x)−Tn−1(x)
- where T0(x) is the Chebyshev polynomial at order 0, and T1(x) is the Chebyshev polynomial at order 1.
The method of claim 6, wherein said classification tool comprises a neural network.
The method of claim 7, wherein the neural network comprises input neurons, where the number of neurons equals the number of coefficient values.
The method of claim 8, wherein the neural network further comprises one or more hidden layers of neurons.
The method of claim 9, wherein the neural network further comprises a plurality of output neurons, wherein each of said output neurons represents a class comprising a genotype or a group of indistinguishable genotypes that unknown HRM curve data will be assigned to.
The method of claim 10, further comprising the step of interpreting output values of the neural network as the probability that an unknown HRM curve data belongs to a given class, if the coefficient values in the training set are normally distributed.
A non-transitory computer-readable storage medium containing program code comprising:
- program code for obtaining melt curve data from a double-stranded DNA from an obtained biological sample of interest;
- program code for determining a corresponding mathematical function of at least one melt curve represented by melt curve data;
- program code for determining the mathematical function's coefficient values;
- program code for using the coefficient values as inputs for classification in a classification tool, wherein said classification tool is configured to classify the melt curve data as either a known genotype or an unknown genotype based on the inputted coefficient values.
Dependencies are inferred from the claim text.