US 2021/0264267 A1 · Bus Network for Artificial Intelligence-Based Base Caller

Abstract

The technology disclosed relates to a system that comprises a spatial convolution network and a temporal convolution network. The spatial convolution network is configured to process a window of per-cycle sequencing image sets and generate respective per-cycle spatial feature map sets. Trained coefficients of spatial convolution filters in spatial convolution filter banks of respective sequences of spatial convolution filter banks vary between sequences of spatial convolution layers in respective sequences of spatial convolution layers. The temporal convolution network is configured to process the per-cycle spatial feature map sets on a groupwise basis and generate respective per-group temporal feature map sets. Trained coefficients of temporal convolution filters in respective temporal convolution filter banks vary between temporal convolution filter banks in respective temporal convolution filter banks.

Claims20

Dependent claims

A system, comprising:

a spatial convolution network configured to process a window of per-cycle sequencing image sets for a series of sequencing cycles of a sequencing run on a cycle-by-cycle basis by separately processing respective per-cycle sequencing image sets in the window of per-cycle sequencing image sets through respective spatial processing pipelines;
and
a bus network, connected to the spatial convolution network, and configured to form buses between spatial convolution layers within respective sequences of spatial convolution layers of the respective spatial processing pipelines, the buses configured to cause respective per-cycle spatial feature map sets generated by two or more spatial convolution layers in a particular sequence of spatial convolution layer for a particular sequencing cycle to combine into a combined per-cycle spatial feature map set, and provide the combined per-cycle spatial feature map set as input to another spatial convolution layer in the particular sequence of spatial convolution layer.

An artificial intelligence-based method, including:

processing, through a spatial convolution network, a window of per-cycle sequencing image sets for a series of sequencing cycles of a sequencing run on a cycle-by-cycle basis by separately processing respective per-cycle sequencing image sets in the window of per-cycle sequencing image sets through respective sequences of spatial convolution layers;
and
combining respective per-cycle spatial feature map sets generated by two or more spatial convolution layers in a particular sequence of spatial convolution layer for a particular sequencing cycle into a combined per-cycle spatial feature map set, and providing the combined per-cycle spatial feature map set as input to another spatial convolution layer in the particular sequence of spatial convolution layer.

Dependencies are inferred from the claim text.

Bus Network for Artificial Intelligence-Based Base Caller

Life of this patent

Bus Network for Artificial Intelligence-Based Base Caller

Life of this patent

Abstract

Claims20