Literature DB >> 33179040

Efficient DNA sequence compression with neural networks.

Milton Silva1,2, Diogo Pratas1,2,3, Armando J Pinho1,2.   

Abstract

BACKGROUND: The increasing production of genomic data has led to an intensified need for models that can cope efficiently with the lossless compression of DNA sequences. Important applications include long-term storage and compression-based data analysis. In the literature, only a few recent articles propose the use of neural networks for DNA sequence compression. However, they fall short when compared with specific DNA compression tools, such as GeCo2. This limitation is due to the absence of models specifically designed for DNA sequences. In this work, we combine the power of neural networks with specific DNA models. For this purpose, we created GeCo3, a new genomic sequence compressor that uses neural networks for mixing multiple context and substitution-tolerant context models.
FINDINGS: We benchmark GeCo3 as a reference-free DNA compressor in 5 datasets, including a balanced and comprehensive dataset of DNA sequences, the Y-chromosome and human mitogenome, 2 compilations of archaeal and virus genomes, 4 whole genomes, and 2 collections of FASTQ data of a human virome and ancient DNA. GeCo3 achieves a solid improvement in compression over the previous version (GeCo2) of $2.4\%$, $7.1\%$, $6.1\%$, $5.8\%$, and $6.0\%$, respectively. To test its performance as a reference-based DNA compressor, we benchmark GeCo3 in 4 datasets constituted by the pairwise compression of the chromosomes of the genomes of several primates. GeCo3 improves the compression in $12.4\%$, $11.7\%$, $10.8\%$, and $10.1\%$ over the state of the art. The cost of this compression improvement is some additional computational time (1.7-3 times slower than GeCo2). The RAM use is constant, and the tool scales efficiently, independently of the sequence size. Overall, these values outperform the state of the art.
CONCLUSIONS: GeCo3 is a genomic sequence compressor with a neural network mixing approach that provides additional gains over top specific genomic compressors. The proposed mixing method is portable, requiring only the probabilities of the models as inputs, providing easy adaptation to other data compressors or compression-based data analysis tools. GeCo3 is released under GPLv3 and is available for free download at https://github.com/cobilab/geco3.
© The Author(s) 2020. Published by Oxford University Press GigaScience.

Entities:  

Keywords:  DNA sequence compression; context mixing; lossless data compression; mixture of experts; neural networks

Year:  2020        PMID: 33179040      PMCID: PMC7657843          DOI: 10.1093/gigascience/giaa119

Source DB:  PubMed          Journal:  Gigascience        ISSN: 2047-217X            Impact factor:   6.524


  48 in total

1.  CoGI: Towards Compressing Genomes as an Image.

Authors:  Xiaojing Xie; Shuigeng Zhou; Jihong Guan
Journal:  IEEE/ACM Trans Comput Biol Bioinform       Date:  2015 Nov-Dec       Impact factor: 3.710

2.  Efficient storage of high throughput DNA sequencing data using reference-based compression.

Authors:  Markus Hsi-Yang Fritz; Rasko Leinonen; Guy Cochrane; Ewan Birney
Journal:  Genome Res       Date:  2011-01-18       Impact factor: 9.043

3.  A high-coverage genome sequence from an archaic Denisovan individual.

Authors:  Matthias Meyer; Martin Kircher; Marie-Theres Gansauge; Heng Li; Fernando Racimo; Swapan Mallick; Joshua G Schraiber; Flora Jay; Kay Prüfer; Cesare de Filippo; Peter H Sudmant; Can Alkan; Qiaomei Fu; Ron Do; Nadin Rohland; Arti Tandon; Michael Siebauer; Richard E Green; Katarzyna Bryc; Adrian W Briggs; Udo Stenzel; Jesse Dabney; Jay Shendure; Jacob Kitzman; Michael F Hammer; Michael V Shunkov; Anatoli P Derevianko; Nick Patterson; Aida M Andrés; Evan E Eichler; Montgomery Slatkin; David Reich; Janet Kelso; Svante Pääbo
Journal:  Science       Date:  2012-08-30       Impact factor: 47.728

4.  DELIMINATE--a fast and efficient method for loss-less compression of genomic sequences: sequence analysis.

Authors:  Monzoorul Haque Mohammed; Anirban Dutta; Tungadri Bose; Sudha Chadaram; Sharmila S Mande
Journal:  Bioinformatics       Date:  2012-07-25       Impact factor: 6.937

5.  SeqCompress: an algorithm for biological sequence compression.

Authors:  Muhammad Sardaraz; Muhammad Tahir; Ataul Aziz Ikram; Hassan Bajwa
Journal:  Genomics       Date:  2014-08-27       Impact factor: 5.736

6.  iDoComp: a compression scheme for assembled genomes.

Authors:  Idoia Ochoa; Mikel Hernaez; Tsachy Weissman
Journal:  Bioinformatics       Date:  2014-10-24       Impact factor: 6.937

7.  Smash++: an alignment-free and memory-efficient tool to find genomic rearrangements.

Authors:  Morteza Hosseini; Diogo Pratas; Burkhard Morgenstern; Armando J Pinho
Journal:  Gigascience       Date:  2020-05-01       Impact factor: 6.524

8.  Big Data: Astronomical or Genomical?

Authors:  Zachary D Stephens; Skylar Y Lee; Faraz Faghri; Roy H Campbell; Chengxiang Zhai; Miles J Efron; Ravishankar Iyer; Michael C Schatz; Saurabh Sinha; Gene E Robinson
Journal:  PLoS Biol       Date:  2015-07-07       Impact factor: 8.029

9.  Nucleotide Archival Format (NAF) enables efficient lossless reference-free compression of DNA sequences.

Authors:  Kirill Kryukov; Mahoko Takahashi Ueda; So Nakagawa; Tadashi Imanishi
Journal:  Bioinformatics       Date:  2019-10-01       Impact factor: 6.937

10.  Evolutionary determinants of genome-wide nucleotide composition.

Authors:  Hongan Long; Way Sung; Sibel Kucukyildirim; Emily Williams; Samuel F Miller; Wanfeng Guo; Caitlyn Patterson; Colin Gregory; Chloe Strauss; Casey Stone; Cécile Berne; David Kysela; William R Shoemaker; Mario E Muscarella; Haiwei Luo; Jay T Lennon; Yves V Brun; Michael Lynch
Journal:  Nat Ecol Evol       Date:  2018-01-01       Impact factor: 15.460

View more
  4 in total

1.  The complexity landscape of viral genomes.

Authors:  Jorge Miguel Silva; Diogo Pratas; Tânia Caetano; Sérgio Matos
Journal:  Gigascience       Date:  2022-08-11       Impact factor: 7.658

Review 2.  Efficient compression of SARS-CoV-2 genome data using Nucleotide Archival Format.

Authors:  Kirill Kryukov; Lihua Jin; So Nakagawa
Journal:  Patterns (N Y)       Date:  2022-07-07

3.  AC2: An Efficient Protein Sequence Compression Tool Using Artificial Neural Networks and Cache-Hash Models.

Authors:  Milton Silva; Diogo Pratas; Armando J Pinho
Journal:  Entropy (Basel)       Date:  2021-04-26       Impact factor: 2.524

4.  MBGC: Multiple Bacteria Genome Compressor.

Authors:  Szymon Grabowski; Tomasz M Kowalski
Journal:  Gigascience       Date:  2022-01-27       Impact factor: 6.524

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.