System and methods for upsampling of decompressed genomic data after lossy compression using a neural network
AssigneeAtombeam Technologies Inc.
InventorsZhu Li, Paras Maharjan, Brian R. Galvin
Life of this patent
Estimating the term…
Abstract
A system and methods for upsampling of decompressed genomic data after lossy compression using a neural network integrates AI-based techniques to enhance compression quality. It incorporates a novel deep-learning neural network that upsamples decompressed data to restore information lost during lossy compression, taking advantage of cross-correlations between genomic data sets.
Claims13
A system for upsampling of decompressed genomic data after lossy compression using a neural network, comprising:
- a computing system comprising at least a memory and a processor;
- two or more datasets that are substantially correlated and which have been compressed with lossy compression, the two or more datasets comprising genomic data;
- a deep learning neural network configured to recover lost information associated with a compressed bit stream, wherein the deep learning neural network comprises a multi-task learning architecture with shared layers for learning common representations across two or more datasets and task specific layers for adapting the common representations to specific upsampling tasks;
- and
- a decoder comprising a first plurality of programming instructions that, when operating on the processor, cause the computing system to:
- receive a compressed bit stream, the compressed bit stream comprising cross-correlated genomic data;
- decompress each of the compressed bit stream;
- and
- use the decompressed bit stream as an input into the deep learning neural network to recover lost information associated with the genomic data.
A method for upsampling of decompressed genomic data after lossy compression using a neural network, comprising the steps of:
- training a deep learning neural network configured to recover lost information associated with a compressed bit stream, wherein the deep learning neural network comprises a multi-task learning architecture with shared layers for learning common representations across two or more datasets and task specific layers for adapting the common representations to specific upsampling tasks;
- and
- receiving the compressed bit stream, the compressed bit stream comprising cross-correlated genomic data;
- decompressing the compressed bit stream;
- and
- using the decompressed bit stream as an input into the deep learning neural network to recover information lost during lossy compression of the genomic data.
Dependencies are inferred from the claim text.