Accelerated Dynamic Time Warping on GPU for Selective Nanopore Sequencing

Abstract

The design and supply of RT-PCR primers for accurate virus testing is a complex process. The MinION is a revolutionary portable nanopore DNA sequencer that may be used to sequence the whole genome of a target virus in a biological sample. Human samples have more than 99% of non-target host DNA and Read Until is a protocol that enables the MinION to selectively eject reads in real-time. However, the MinION does not have any in-built compute power to select non-target reads. SquiggleFilter is a prior work that identified the accuracy and throughput challenges in performing Read Until using the state-of-the-art solution and proposed a hardware-accelerated subsequence Dynamic Time Warping (sDTW) based programmable filter on an ASIC. However, SquiggleFilter does not work for genomes larger than 100Kb. We optimize SquiggleFilter’s sDTW algorithm onto the more commonly available GPUs.DTWaxbetter uses tensor core pipes, 2X-SIMD FP16 computations and efficient data handling strategies using offline pre-processing, coalesced global memory loads, warp shuffles and shared memory buffering among other optimizations.DTWaxenables Read Until and yields 1.92X sequencing speedup and 3.64X compute speedup: costup over a sequencing workflow that does not use Read Until.

Efficient real-time selective genome sequencing on resource-constrained devices

“…This is an emerging and immature field and will inevitably require a substantial period of time to achieve the same level of maturity as base-level selective sequencing. Since the concept of nanopore selective sequencing was introduced, a range of different signal-level selective sequencing methods has been explored, including RUscripts [ 11 ], cwDTW [ 17 ], UNCALLED [ 15 ], sigmap [ 16 ], and, more recently, RawHash [ 21 ], DTWax [ 46 ], and RawMap [ 47 ].…”

MATSA: An MRAM-Based Energy-Efficient Accelerator for Time Series Analysis

“…Accelerating Dynamic Time Warping (DTW). Several works attempt to accelerate the sDTW kernel using GPUs [52], [67] and FPGAs [68]. Section IV demonstrates that MATSA improves upon the performance of GPUs and FPGAs by 6.15× and 65.28× respectively, and supports arbitrary-sized datasets, a key drawback of prior work.…”