公开(公告)号：US20230360733A1

公开(公告)日：2023-11-09

申请号：US18312663

申请日：2023-05-05

Applicant: Life Technologies Corporation

Inventor： Cheng-Zong BAI ,  Eugene INGERMAN ,  Alison LAI ,  Werner PUSCHITZ ,  Chao WANG

IPC: G16B40/10 ,  G16B30/00

CPC classification number: G16B40/10 ,  G16B30/00

Abstract: A method for correcting signal measurements comprises an artificial neural network (ANN). The ANN receives a plurality of signal measurements in a channel of an input layer. The ANN is applied to the signal measurements and produces a plurality of signal correction values. The signal correction values may be subtracted from the signal measurements to form corrected signal measurements. The corrected signal measurements may be provided to a base caller to produce a sequence of base calls. The ANN may comprise a convolutional neural network (CNN). The CNN may have a U-NET architecture that includes an encoder and a decoder. The U-NET may include a Convolutional Block Attention Module (CBAM). The CBAM may applied to the outputs of a last pooling layer of the encoder and provides refined feature maps to a first layer of the decoder. The input signal measurements may be generated by a nucleic acid sequencing instrument.

公开(公告)号：US20190237163A1

公开(公告)日：2019-08-01

申请号：US16245343

申请日：2019-01-11

Applicant: LIFE TECHNOLOGIES CORPORATION

Inventor： Chao Wang ,  Eugene INGERMAN

IPC: G16B40/10 ,  G16B30/00 ,  G06N3/08

CPC classification number: G16B40/10 ,  C12Q1/6869 ,  G06N3/0454 ,  G06N3/08 ,  G16B30/00

Abstract: An artificial neural network is applied to a plurality of flow predictor features to generate a flow space probability of error for a base call. A base quality value for the base call is determined based on the flow space probability of error. The base call and flow predictor features are based on the flow space signal measurements generated in response to the nucleotide flow to the reaction confinement region. For an array of reaction confinement regions, a plurality of parallel neural networks is applied to produce a probability of error for each reaction confinement region. A given neural network of the parallel neural networks is applied to the plurality of flow predictor features corresponding to a given reaction confinement region in the array to provide the flow space probability of error for the given reaction confinement region.