US 12,224,044 B1
System and methods for upsampling of decompressed genomic data after lossy compression using a neural network
Zhu Li, Overland Park, KS (US); Paras Maharjan, Kansas City, MO (US); and Brian R. Galvin, Silverdale, WA (US)
Assigned to ATOMBEAM TECHNOLOGIES INC, Moraga, CA (US)
Filed by AtomBeam Technologies Inc., Moraga, CA (US)
Filed on Jul. 11, 2024, as Appl. No. 18/769,416.
Application 18/769,416 is a continuation in part of application No. 18/420,771, filed on Jan. 24, 2024, granted, now 12,095,484.
Application 18/420,771 is a continuation in part of application No. 18/410,980, filed on Jan. 11, 2024, granted, now 12,068,761.
Application 18/410,980 is a continuation in part of application No. 18/537,728, filed on Dec. 12, 2023, granted, now 12,058,333.
This patent is subject to a terminal disclaimer.
Int. Cl. H03M 7/00 (2006.01); G16B 40/00 (2019.01); G16B 50/50 (2019.01)
CPC G16B 50/50 (2019.02) [G16B 40/00 (2019.02)] 13 Claims
OG exemplary drawing
 
1. 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.