Nucl2Vec : Local alignment of DNA sequences using Distributed Vector Representation

Ganesh, Prakhar; Gupta, Gaurav; Saini, Shubhi; Paul, Kolin

doi:10.1101/401851

Cited by 2 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aoki and Sakakibara [12] have used Word2Vec encoding to do alignment and generate motif of non-coding regions of RNA. Nucl2Vec [13] also uses encoding similar to word2Vec and uses KNN algorithm to do alignment of sequencer data.…”

Section: Current Methodologymentioning

confidence: 99%

“…Due to their computational demands, heuristic-based methods are less commonly used than probabilistic methods [4]. Some studies have been conducted which use machine learning techniques for indel identification using random forests [14]. But still GATK is the de facto industry standard for identification of SNVs in Illumina datasets.…”

Section: Current Methodologymentioning

confidence: 99%

See 1 more Smart Citation

DAVI: Deep learning-based tool for alignment and single nucleotide variant identification

Gupta¹,

Saini²

2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Next-generation sequencing (NGS) technologies have provided affordable but errorful ways to generate raw genetic data. To extract variant information from billions of NGS reads is still a daunting task which involves various hand-crafted and parameterized statistical tools. Here we propose a deep neural networks (DNN) based alignment and single nucleotide variant (SNV) identifier tool known as DAVI: deep alignment and variant identification. DAVI consists of models for both global and local alignment and for variant calling. We have evaluated the performance of DAVI against existing state-of-the-art tool sets and found that its accuracy and performance is comparable to existing tools used for bench-marking. We further demonstrate that while existing tools are based on data generated from a specific sequencing technology, the models proposed in DAVI are generic and can be used across different NGS technologies as well as across different species. The use of DAVI will therefore help non-human sequencing projects to benefit from the wealth of human ground truth data. Moreover, this approach is a migration from expert-driven statistical models to generic, automated, self-learning models.

show abstract

Section: Current Methodologymentioning

confidence: 99%

Section: Current Methodologymentioning

confidence: 99%

DAVI: Deep learning-based tool for alignment and single nucleotide variant identification

Gupta¹,

Saini²

2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Nucl2vec. Another similar approach, Nucl2vec [10] trains word2vec on k-mers with the goal of aligning a small query sequence to a long reference genome. Due to the fact that the query might not match exactly with the reference due to natural divergence and sequencing errors, Ganesh et al modify word2vec to accommodate for insertions and substitutions.…”

Section: Distributed Representationsmentioning

confidence: 99%

“…Genomic Signatures are an effective method of discriminating between sequences from different organisms. [42] 20-mers 108 dna2vec [31] k-mers, k ∈ [3, 8] 100 Genomic Signatures [35] 5-mers 16 N-gram graph [22,35] 5-mers, 3-mers 2,6 Nucl2vec [10] 4-mers 1…”

Section: Genomic Signatures (Gs)mentioning

confidence: 99%

Evaluation of distributed DNA representations on the classification of conserved non-coding elements

Gialitsis

Giannakopoulos

Athanasouli

2020

11th Hellenic Conference on Artificial Intelligence

View full text Add to dashboard Cite

The representation of DNA sequences has been an interesting topic of discussion for many years. Presently, given the usefulness of representations built upon embeddings for Natural Language Processing (NLP), there have been efforts to transfer such paradigms to the DNA world and related problems. In this paper, we study different DNA representations on the well-studied problem of Conserved Non-coding Elements (CNEs), trying to understand how well existing representations utilize the value of context, both in terms of local, near context, but also of long-distance interactions in genomic sequences. To this end, we apply a number of methods, including probabilistic models (LDA) and hybrid probabilistic-neural models (lda2vec) on appropriate datasets, compare the results to pre-existing methods and discuss the findings to better understand the value and challenges of different representations in the given domain.

show abstract

Nucl2Vec : Local alignment of DNA sequences using Distributed Vector Representation

Cited by 2 publications

References 7 publications

DAVI: Deep learning-based tool for alignment and single nucleotide variant identification

DAVI: Deep learning-based tool for alignment and single nucleotide variant identification

Evaluation of distributed DNA representations on the classification of conserved non-coding elements

Contact Info

Product

Resources

About