GenPIP: In-Memory Acceleration of Genome Analysis via Tight Integration of Basecalling and Read Mapping

Mao, Haiyu; Alser, Mohammed; Sadrosadati, Mohammad; Fırtına, Can; Baranwal, Akanksha; Cali, Damla Senol; Manglik, Aditya; Alserr, Nour Almadhoun; Mutlu, Onur

doi:10.1109/micro56248.2022.00056

Cited by 11 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern basecallers use deep learning-based models to significantly (by at least 10%) improve the accuracy of predicting a nucleotide base from the squiggle compared to traditional non-deep learning-based basecallers [16–18, 31, 33–37]. The success of deep learning in genome basecalling is attributed to the advances in its architecture to model and identify spatial features in raw input data to predict nucleotides.…”

Section: Introductionmentioning

confidence: 99%

A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers

Singh

Alser

Khodamoradi³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Nanopore sequencing is a widely-used high-throughput genome sequencing technology that can sequence long fragments of a genome. Nanopore sequencing generates noisy electrical signals that need to be converted into a standard string of DNA nucleotide bases (i.e., A, C, G, T) using a computational step called basecalling. The accuracy and speed of basecalling have critical implications for every subsequent step in genome analysis. Currently, basecallers are mainly based on deep learning techniques to provide high sequencing accuracy without considering the compute demands of such tools. We observe that state-of-the-art basecallers (i.e., Guppy, Bonito) are slow, inefficient, and memory-hungry as researchers have adapted deep learning models from other domains without specialization to the basecalling purpose. Our goal is to make basecalling highly efficient and fast by building the first framework for specializing and optimizing machine learning-based basecaller. We introduce RUBICON, a framework to develop hardware-optimized basecallers. RUBICON consists of two novel machine-learning techniques that are specifically designed for basecalling. First, we introduce the quantization-aware basecalling neural architecture search (QABAS) framework to specialize the basecalling neural network architecture for a given hardware acceleration platform while jointly exploring and finding the best bit-width precision for each neural network layer. Second, we develop SkipClip, the first technique to remove all the skip connections present in modern basecallers to greatly reduce resource and storage requirements without any loss in basecalling accuracy. We demonstrate the benefits of QABAS and SkipClip by developing RUBICALL, the first hardware-optimized basecaller that performs fast and accurate basecalling. Our experimental results on state-of-the-art computing systems show that RUBICALL is a fast, accurate and hardware-friendly, mixed-precision basecaller. Compared to a highly-accurate state-of-the-art basecaller, RUBICALL provides a 16.56x speedup without losing accuracy, while also achieving a 6.88x and 2.94x reduction in neural network model size and the number of parameters, respectively. Compared to the fastest state-of-the-art basecaller, RUBICALL provides a 3.19x speedup with 2.97% higher accuracy. We show that QABAS and SkipClip can help researchers develop hardware-optimized basecallers that are superior to expert-designed models.

show abstract

Section: Introductionmentioning

confidence: 99%

A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers

Singh

Alser

Khodamoradi³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…One of the immediate steps after generating raw nanopore signals is their translation to their corresponding DNA bases as sequences of characters with a computationallyintensive step, basecalling. Basecalling approaches are usually computationally costly and consume significant energy as they use complex deep learning models [26][27][28][29][30][31][32][33][34][35][36][37][38]. Although we do not evaluate in this work, we expect that RawHash can be used as a low-cost filter to eliminate the reads that are unlikely to be useful in downstream analysis, which can reduce the overall workload of basecallers and further downstream analysis.…”

Section: Discussionmentioning

confidence: 99%

“…Recent works focus on developing methods to speed up the basecalling process. One approach to basecalling acceleration is to use specialized hardware, such as field-programmable gate arrays (FPGAs) [76][77][78][79][80] or processing-in-memory (PIM) [38,81,82], to perform the basecalling computations. These specialized hardware devices can perform many calculations in parallel, allowing for significant speedups in the basecalling process.…”

Section: Related Workmentioning

confidence: 99%

RawHash: Enabling Fast and Accurate Real-Time Analysis of Raw Nanopore Signals for Large Genomes

Fırtına

Ghiasi

Lindegger

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Nanopore sequencers generate electrical raw signals in real-time while sequencing long genomic strands. These raw signals can be analyzed as they are generated, providing an opportunity for real-time genome analysis. An important feature of nanopore sequencing, Read Until, can eject strands from sequencers without fully sequencing them, which provides opportunities to computationally reduce the sequencing time and cost. However, existing works utilizing Read Until either 1) require powerful computational resources that may not be available for portable sequencers or 2) lack scalability for large genomes, rendering them inaccurate or ineffective. We propose RawHash, the first mechanism that can accurately and efficiently perform real-time analysis of nanopore raw signals for large genomes using a hash-based similarity search. To enable this, RawHash ensures the signals corresponding to the same DNA content lead to the same hash value, regardless of the slight variations in these signals. RawHash achieves an accurate hash-based similarity search via an effective quantization of the raw signals such that signals corresponding to the same DNA content have the same quantized value and, subsequently, the same hash value. We evaluate RawHash on three applications: 1) read mapping, 2) relative abundance estimation, and 3) contamination analysis. Our evaluations show that RawHash is the only tool that can provide high accuracy and high throughput for analyzing large genomes in real-time. When compared to the state-of-the-art techniques, UNCALLED and Sigmap, RawHash provides 1) 25.8x and 3.4x better average throughput and 2) an average speedup of 32.1x and 2.1x in the mapping time, respectively. Source code is available at https://github.com/CMU-SAFARI/RawHash.

show abstract

“…Note that the length of the operands at the sub-array level is determined by the minimum sub-problem size, i.e., 2 * T (where T is the segment size in LongGeneGuardian) to account for the 2-bit encoding scheme commonly used in genomics accelerators [65][66][67][68].…”

Section: Crossbarmentioning

confidence: 99%

“…Previous works [49,66,70,[91][92][93] propose various ASIC and CIM architectures for different kernels in genomics pipelines. FilterFuse belongs to the works in this group.…”

Section: B Asic and Cim Accelerators For Genomicsmentioning

confidence: 99%

SieveMem: A Computation-in-Memory Architecture for Fast and Accurate Pre-Alignment

Shahroodi,

Miao,

Zahedi

et al. 2023

2023 IEEE 34th International Conference on Application-Specific Systems, Architectures and Processors (ASAP)

View full text Add to dashboard Cite

With the industry moving towards sequencing of accurate long reads (as they favor accurate and more efficient reconstruction of DNA), finding solutions that support efficient analysis of these reads becomes more necessary. The long execution time required for sequence alignment of long reads negatively affects genomic studies relying on sequence alignment. Although pre-alignment filtering as an extra step before alignment was recently introduced to mitigate sequence alignment for short reads, these filters do not work as efficiently for long reads. Moreover, even with efficient pre-alignment filters, the overall end-to-end (i.e., filtering + original alignment) execution time of alignment for long reads remains high, while the filtering step is now a major portion of the end-to-end execution time.Our paper makes three contributions. First, it identifies data movement of sequences between memory units and computing units as the main source of inefficiency for pre-alignment filters of long reads. This is because although filters reject many of these long sequencing pairs before they get to the alignment stage, they still require a huge cost regarding time and energy consumption for the large data transferred between memory and processor. Second, this paper introduces an adaptation of a short-read pre-alignment filtering algorithm suitable for long reads. We call this LongGeneGuardian. Finally, it presents Filter-Fuse as an architecture that supports LongGeneGuardian inside the memory. FilterFuse exploits the Computation-In-Memory computing paradigm, eliminating the cost of data movement in LongGeneGuardian.Our evaluations show that FilterFuse improves the execution time of filtering by 120.47× for long reads compared to State-ofthe-Art (SoTA) filter, SneakySnake. FilterFuse also improves the end-to-end execution time of sequence alignment by up to 49.14× and 5207.63× compared to SneakySnake with SoTA aligner and only SoTA aligner, respectively.

show abstract

GenPIP: In-Memory Acceleration of Genome Analysis via Tight Integration of Basecalling and Read Mapping

Cited by 11 publications

References 0 publications

A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers

A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers

RawHash: Enabling Fast and Accurate Real-Time Analysis of Raw Nanopore Signals for Large Genomes

SieveMem: A Computation-in-Memory Architecture for Fast and Accurate Pre-Alignment

Contact Info

Product

Resources

About