公开(公告)号：US20220013193A1

公开(公告)日：2022-01-13

申请号：US17312168

申请日：2019-12-10

Applicant: LIFE TECHNOLOGIES CORPORATION

Inventor： Yong CHU ,  Stephanie SCHNEIDER ,  Rylan SCHAEFFER ,  David WOO

IPC: G16B40/20 ,  G16B30/20 ,  C12Q1/6869 ,  G06N3/08

Abstract: A deep basecaller system for Sanger sequencing and associated methods are provided. The methods use deep machine learning. A Deep Learning Model is used to determine scan labelling probabilities based on an analyzed trace. A Neural Network is trained to learn the optimal mapping function to minimize a Connectionist Temporal Classification (CTC) Loss function. The CTC function is used to calculate loss by matching a target sequence and predicted scan labelling probabilities. A Decoder generates a sequence with the maximum probability. A Basecall position finder using prefix beam search is used to walk through CTC labelling probabilities to find a scan range and then the scan a position of peak labelling probability within the scan range for each called base. Quality Value (QV) is determined using a feature vector calculated from CTC labelling probabilities as an index into a QV look-up table to find a quality score.

公开(公告)号：US20190170684A1

公开(公告)日：2019-06-06

申请号：US16265806

申请日：2019-02-01

Applicant: Life Technologies Corporation

Inventor： David DENNY ,  David WOO ,  Manjula ALIMINATI ,  Siva Kumar SAMSANI ,  Stephanie SCHNEIDER ,  Yoke Peng LIM ,  Sylvia CHANG

IPC: G01N27/447 ,  G16B30/00

CPC classification number: G01N27/44717 ,  G16B30/00

Abstract: In one exemplary embodiment, a method for detecting variants in electropherogram data is provided. The method includes receiving electropherogram data from an instrument and analyzing the electropherogram data to identify mixed bases in the electropherogram data. The method further includes validating the identified mixed bases. Then the method includes determining variants in the electropherogram data based on the validated mixed bases.