Nanopore Base Calling on the Edge
This work addresses the need for energy-efficient, real-time base calling in portable or edge computing scenarios for genomics applications, representing an incremental improvement.
The authors tackled the problem of real-time base calling for nanopore sequencing by developing DeepNano-coral, a base caller optimized for the Coral Edge TPU, achieving slightly better accuracy than Guppy's fast mode while using only 10W of power.
We developed a new base caller DeepNano-coral for nanopore sequencing, which is optimized to run on the Coral Edge Tensor Processing Unit, a small USB-attached hardware accelerator. To achieve this goal, we have designed new versions of two key components used in convolutional neural networks for speech recognition and base calling. In our components, we propose a new way of factorization of a full convolution into smaller operations, which decreases memory access operations, memory access being a bottleneck on this device. DeepNano-coral achieves real-time base calling during sequencing with the accuracy slightly better than the fast mode of the Guppy base caller and is extremely energy efficient, using only 10W of power. Availability: https://github.com/fmfi-compbio/coral-basecaller