baseLess: lightweight detection of sequences in raw MinION data

Noordijk, Ben; Nijland, Reindert; Carrión, Víctor J.; Raaijmakers, Jos M.; Ridder, Dick de; Lannoy, Carlos de

doi:10.1101/2022.07.10.499286

Cited by 5 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second group generates noisy sequence representations of the raw signal to compare them with the target reference [28,46]. The third group of works utilize neural network classifiers to label the sequences [29,47]. All these approaches are explained in detail in Section 7.…”

Section: Targeted Sequencingmentioning

confidence: 99%

“…Therefore, unlike TargetCall, SquiggleNet cannot be used as a widely-applicable pre-basecalling filter. BaseLess [47] utilizes an array of small neural networks to detect a small subsequences from raw signals and match these subsequences with a target reference that share the same subsequence. This design choice provides a flexible solution that can define the set of pre-trained neural network models of subsequences to identify a certain target reference instead of retraining the neural network model for each species.…”

Section: Targeted Sequencingmentioning

confidence: 99%

“…The third group of work uses machine learning to label the raw signals in a sample without performing basecalling and costly analyses in the base space [29,47]. SquiggleNet [29] can identify a certain class of species with a high accuracy where the class membership is determined based on the target reference.…”

Section: Targeted Sequencingmentioning

confidence: 99%

See 2 more Smart Citations

TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering

Banu

Singh

Alser

et al. 2022

Preprint

View full text Add to dashboard Cite

Basecalling is an essential step in nanopore sequencing analysis where the raw signals of nanopore sequencers are converted into nucleotide sequences, i.e., reads. State-of-the-art basecallers employ complex deep learning models to achieve high basecalling accuracy. This makes basecalling computationally-inefficient and memory-hungry; bottlenecking the entire genome analysis pipeline. However, for many applications, the majority of reads do no match the reference genome of interest (i.e., target reference) and thus are discarded in later steps in the genomics pipeline, wasting the basecalling computation. To overcome this issue, we propose TargetCall, the first fast and widely-applicable pre-basecalling filter to eliminate the wasted computation in basecalling. TargetCall's key idea is to discard reads that will not match the target reference (i.e., off-target reads) prior to basecalling. TargetCall consists of two main components: (1) LightCall, a lightweight neural network basecaller that produces noisy reads; and (2) Similarity Check, which labels each of these noisy reads as on-target or off-target by matching them to the target reference. TargetCall filters out all off-target reads before basecalling; and the highly-accurate but slow basecalling is performed only on the raw signals whose noisy reads are labeled as on-target. Our thorough experimental evaluations using both real and simulated data show that TargetCall 1) improves the end-to-end basecalling performance of the state-of-the-art basecaller by 3.31x while maintaining high (98.88%) sensitivity in keeping on-target reads, 2) maintains high accuracy in downstream analysis, 3) precisely filters out up to 94.71% of off-target reads, and 4) achieves better performance, sensitivity, and generality compared to prior works. We freely open-source TargetCall to aid future research in pre-basecalling filtering at https://github.com/CMU-SAFARI/TargetCall.

show abstract

Section: Targeted Sequencingmentioning

confidence: 99%

Section: Targeted Sequencingmentioning

confidence: 99%

See 1 more Smart Citation

TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering

Banu

Singh

Alser

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the applicability of the mentioned method for complex inter-species classification is yet to be explored. The most recent work named baseLess is also a deep learning approach that relies on features of salient k-mers rather than reads as a whole, explicitly designed to work with MinION [17]. The authors have reported a performance similar to SquiggleNet, which does not surpass the performance of Guppy+Minimap2.…”

Section: Related Workmentioning

confidence: 99%

DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing

Senanayake

Gamaarachchi

Herath

et al. 2022

Preprint

View full text Add to dashboard Cite

Nanopore sequencing allows selective sequencing, the ability to programmatically reject unwanted reads in a sample. Selective sequencing has many present and future applications in genomics research and the classification of species from a pool of species is an example. Existing methods for selective sequencing for species classification are still immature and the accuracy highly varies depending on the datasets. For the five datasets we tested, the accuracy of existing methods varied in the range of ~77%-97% (average accuracy <89%). Here we present DeepSelectNet, an accurate deep-learning-based method that can directly classify nanopore current signals belonging to a particular species. DeepSelectNet utilizes novel data preprocessing techniques and improved neural network architecture for regularization. For the five datasets tested, DeepSelectNet's accuracy varied between ~91%-99% (average accuracy ~95%). At its best performance, DeepSelectNet achieved a nearly 12% accuracy increase compared to its deep learning-based predecessor SquiggleNet. Furthermore, precision and recall evaluated for DeepSelectNet on average were always >89% (average ~95%). In terms of execution performance, DeepSelectNet outperformed SquiggleNet by ~13% on average. Thus, DeepSelectNet is a practically viable method to improve the effectiveness of selective sequencing. Compared to base alignment and deep learning predecessors, DeepSelectNet can significantly improve the accuracy to enable real-time species classification using selective sequencing. The source code of DeepSelectNet is available at https://github.com/AnjanaSenanayake/DeepSelectNet.

show abstract

“…This renders many current methods [3, 6] inaccurate or useless for large genomes as they cannot either provide accurate results or match the throughput of nanopores for these genomes. Third, machine learning models used in past works [5, 8, 9] to analyze raw nanopore signals often require retraining or reconfiguring the model to improve accuracy for a certain experiment [11, 12], which can be a barrier to flexibly and easily performing realtime analysis without retraining or reconfiguring these models. To our knowledge, there is no work that can efficiently and accurately perform real-time analysis of raw nanopore signals on a large scale (e.g., whole-genome analysis for human) without requiring powerful computational resources, which can easily and flexibly be applied to a wide range of applications that could benefit from real-time nanopore raw signal analysis.…”

Section: Introductionmentioning

confidence: 99%

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

Fırtına

Ghiasi

Lindegger

et al. 2023

Preprint

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

baseLess: lightweight detection of sequences in raw MinION data

Cited by 5 publications

References 25 publications

TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering

TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering

DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing

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

Contact Info

Product

Resources

About