DNA-based analog neural networks
First Claim
1. A method comprising,providing a set of weight oligomers tethered to one or more solid supports, each weight oligomer comprising one of a plurality of first subunit sequences and one of a plurality of double stranded second subunit sequences, the first subunit sequences represent a pattern of gene expression for a reference cell;
- wherein said first subunit sequence is serially connected to said second subunit sequences, and each weight oligomer being a RNA or DNA oligonucleotide, RNA or DNA oligonucleotide analog or combination thereof; and
wherein the first subunit sequences are configured to hybridize to nucleic acid molecules produced by said reference cell, and the second subunit sequences are configured to not hybridize to nucleic acid molecules produced by said reference cell;
extracting mRNA from a test cell;
mixing an assay of nucleic acid oligomers derived from said mRNA with said set of weight oligomers under conditions where said nucleic acid oligomers are capable of hybridizing to complementary first subunit sequences;
isolating signal oligomers from said second subunit sequences connected to said complementary first subunit sequences; and
determining concentrations of said isolated second subunit sequences.
7 Assignments
0 Petitions
Accused Products
Abstract
This invention is an oligomer-based analog neural network (ANN) comprising weight and saturation oligomers, the concentrations of which are selected such that activation of the ANN by a set of input oligomers generates a set of output oligomers, the sequences and relative concentrations of which are dependent on the sequences and relative concentrations of the input oligomers. The invention further includes methods for using such an ANN for solving any problems amenable to solution by a trained neural network. A preferred embodiment of the claimed invention is a DNA-based ANN that accepts cDNA molecules as inputs and analyzes the gene expression profile of the cells from which the cDNA is derived. The DNA-based ANN is typically trained with a computer to identify the weights giving accurate mapping of the inputs to the outputs; and the concentrations of weight oligomers of the DNA-based ANN are then selected accordingly.
9 Citations
4 Claims
-
1. A method comprising,
providing a set of weight oligomers tethered to one or more solid supports, each weight oligomer comprising one of a plurality of first subunit sequences and one of a plurality of double stranded second subunit sequences, the first subunit sequences represent a pattern of gene expression for a reference cell; -
wherein said first subunit sequence is serially connected to said second subunit sequences, and each weight oligomer being a RNA or DNA oligonucleotide, RNA or DNA oligonucleotide analog or combination thereof; and wherein the first subunit sequences are configured to hybridize to nucleic acid molecules produced by said reference cell, and the second subunit sequences are configured to not hybridize to nucleic acid molecules produced by said reference cell; extracting mRNA from a test cell; mixing an assay of nucleic acid oligomers derived from said mRNA with said set of weight oligomers under conditions where said nucleic acid oligomers are capable of hybridizing to complementary first subunit sequences; isolating signal oligomers from said second subunit sequences connected to said complementary first subunit sequences; and determining concentrations of said isolated second subunit sequences. - View Dependent Claims (2, 3, 4)
-
Specification