论文标题
纳米孔底部呼唤边缘
Nanopore Base Calling on the Edge
论文作者
论文摘要
我们开发了一种用于纳米孔测序的新的基本呼叫者DeepNano-Coral，该纳米孔测序可在珊瑚边缘张量处理单元上运行，这是一个小型USB连接的硬件加速器。为了实现这一目标，我们设计了卷积神经网络中使用的两个关键组件的新版本，以供语音识别和基础呼叫。在我们的组件中，我们提出了一种将全面卷积分解为较小操作的新方法，从而减少了内存访问操作，内存访问是该设备上的瓶颈。 DeepNano-Coral在测序过程中实现了实时基础调用，其准确性比Guppy Base呼叫者的快速模式稍好，并且仅使用10W的功率，并且具有极高的能源效率。可用性：https：//github.com/fmfi-compbio/coral-basecaller
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
