Search

Identifying accessible chromatin regions is a fundamental problem in epigenomics with ATAC-seq being a commonly used assay. Exponential rise in single cell ATAC-seq experiments has made it critical to accelerate processing of ATAC-seq data. ATAC-seq data can have a low signal-to-noise ratio for various reasons including low coverage or low cell count. To denoise and identify accessible chromatin regions from noisy ATAC-seq data, use of deep learning on 1D data – using large filter sizes, long tensor widths, and/or dilation - has recently been proposed. Here, we present ways to accelerate the end-to-end training performance of these deep learning based methods using CPUs. We evaluate our approach on the recently released AtacWorks toolkit. Compared to an Nvidia DGX-1 box with 8 V100 GPUs, we get up to 2.27× speedup using just 16 CPU sockets. To achieve this, we build an efficient 1D dilated convolution layer and demonstrate reduced precision (BFloat16) training.

Long read sequencing is now routinely used at scale for genomics and transcriptomics applications. Mapping of long reads or a draft genome assembly to a reference sequence is often one of the most time consuming steps in these applications. Here, we present techniques to accelerate minimap2, a widely used software for mapping. We present multiple optimizations using SIMD parallelization, efficient cache utilization and a learned index data structure to accelerate its three main computational modules, i.e., seeding, chaining and pairwise sequence alignment. These result in reduction of end-to-end mapping time of minimap2 by up to 1.8 × while maintaining identical output.

Over the last decade, advances in high-throughput sequencing and the availability of portable sequencers have enabled fast and cheap access to genetic data. For a given sample, sequencers typically output fragments of the DNA in the sample. Depending on the sequencing technology, the fragments range from a length of 150–250 at high accuracy to lengths in few tens of thousands but at much lower accuracy. Sequencing data is now being produced at a rate that far outpaces Moore's law and poses significant computational challenges on commodity hardware. To meet this demand, software tools have been extensively redesigned and new algorithms and custom hardware have been developed to deal with the diversity in sequencing data. However, a standard set of benchmarks that captures the diverse behaviors of these recent algorithms and can facilitate future architectural exploration is lacking. To that end, we present the GenomicsBench benchmark suite which contains 12 computationally intensive data-parallel kernels drawn from popular bioinformatics software tools. It covers the major steps in short and long-read genome sequence analysis pipelines such as basecalling, sequence mapping, de-novo assembly, variant calling and polishing. We observe that while these genomics kernels have abundant data level parallelism, it is often hard to exploit on commodity processors because of input-dependent irregularities. We also perform a detailed microarchitectural characterization of these kernels and identify their bottlenecks. GenomicsBench includes parallel versions of the source code with CPU and GPU implementations as applicable along with representative input datasets of two sizes - small and large.

© 2020, VLDB Endowment. All rights reserved. Recent advancements in learned index structures propose replacing existing index structures, like B-Trees, with approximate learned models. In this work, we present a unified benchmark that compares well-tuned implementations of three learned index structures against several state-of-the-art "traditional" baselines. Using four real-world datasets, we demonstrate that learned index structures can indeed outperform non-learned indexes in read-only in-memory workloads over a dense array. We investigate the impact of caching, pipelining, dataset size, and key size. We study the performance profile of learned index structures, and build an explanation for why learned models achieve such good performance. Finally, we investigate other important properties of learned index structures, such as their performance in multi-threaded systems and their build times.

BackgroundNext-generation sequencing (NGS) technologies have enabled affordable sequencing of billions of short DNA fragments at high throughput, paving the way for population-scale genomics. Genomics data analytics at this scale requires overcoming performance bottlenecks, such as searching for short DNA sequences over long reference sequences.ResultsIn this paper, we introduce LISA (Learned Indexes for Sequence Analysis), a novel learning-based approach to DNA sequence search. We focus on accelerating two of the most essential flavors of DNA sequence search—exact search and super-maximal exact match (SMEM) search. LISA builds on and extends FM-index, which is the state-of-the-art technique widely deployed in genomics tools. Experiments with human, animal, and plant genome datasets indicate that LISA achieves up to 2.2 and 10.8 speedups over the state-of-the-art FM-index based implementations for exact search and super-maximal exact match (SMEM) search, respectively.Code availabilityhttps://github.com/IntelLabs/Trans-Omics-Acceleration-Library/tree/master/LISA.