Patent · US Active

Training data generation for artificial intelligence-based sequencing

US11908548B2 · kind B2 · utility

1Cited by
54References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 27, 2022
Grant dateFeb 20, 2024
Priority date
Expiry dateMay 27, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V2201/03
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The technology disclosed relates to generating ground truth training data to train a neural network-based template generator for cluster metadata determination task. In particular, it relates to accessing sequencing images, obtaining, from a base caller, a base call classifying each subpixel in the sequencing images as one of four bases (A, C, T, and G), generating a cluster map that identifies clusters as disjointed regions of contiguous subpixels which share a substantially matching base call sequence, determining cluster metadata based on the disjointed regions in the cluster map, and using the cluster metadata to generate the ground truth training data for training the neural network-based template generator for the cluster metadata determination task.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.