A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences

Salvatore Gaglio, Giosue' Lo Bosco, Riccardo Rizzo, Giosué Lo Bosco, Riccardo Rizzo, Mattia Antonino Di Gangi

Risultato della ricerca: Chapter

5 Citazioni (Scopus)

Abstract

A nucleosome is a DNA-histone complex, wrapping about 150 pairs of double-stranded DNA. The role of nucleosomes is to pack the DNA into the nucleus of the Eukaryote cells to form the Chromatin. Nucleosome positioning genome wide play an important role in the regulation of cell type-specific gene activities. Several biological studies have shown sequence specificity of nucleosome presence, clearly underlined by the organization of precise nucleotides substrings. Taking into consideration such advances, the identification of nucleosomes on a genomic scale has been successfully performed by DNA sequence features representation and classical supervised classification methods such as Support Vector Machines and Logistic regression. The goal of this work is to propose a classification method for nucleosome positioning that, differently from the proposed method so far, does not make any use of a sequence feature extraction step. Deep neural networks (DNN) or deep learning models, were proved to be able to extract automatically useful features from input patterns. Under this framework, Long Short-Term Memory (LSTM) is a recurrent unit that reads a sequence one step at a time and can exploit long range relations. In this work, we propose a DNN model for nucleosome identification on sequences from three different species. Our experiments show that it outperforms classical methods in two of the three data sets and give promising results also for the other
Lingua originaleEnglish
Titolo della pubblicazione ospiteBioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II
Pagine524-533
Numero di pagine10
Volume10209
Stato di pubblicazionePublished - 2017

Serie di pubblicazioni

NomeLECTURE NOTES IN COMPUTER SCIENCE

Fingerprint

DNA
Genes
DNA sequences
Nucleotides
Logistics
Deep learning
Experiments
Deep neural networks
Long short-term memory

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cita questo

Gaglio, S., Lo Bosco, G., Rizzo, R., Lo Bosco, G., Rizzo, R., & Di Gangi, M. A. (2017). A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences. In Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II (Vol. 10209, pagg. 524-533). (LECTURE NOTES IN COMPUTER SCIENCE).

A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences. / Gaglio, Salvatore; Lo Bosco, Giosue'; Rizzo, Riccardo; Lo Bosco, Giosué; Rizzo, Riccardo; Di Gangi, Mattia Antonino.

Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II. Vol. 10209 2017. pag. 524-533 (LECTURE NOTES IN COMPUTER SCIENCE).

Risultato della ricerca: Chapter

Gaglio, S, Lo Bosco, G, Rizzo, R, Lo Bosco, G, Rizzo, R & Di Gangi, MA 2017, A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences. in Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II. vol. 10209, LECTURE NOTES IN COMPUTER SCIENCE, pagg. 524-533.
Gaglio S, Lo Bosco G, Rizzo R, Lo Bosco G, Rizzo R, Di Gangi MA. A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences. In Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II. Vol. 10209. 2017. pag. 524-533. (LECTURE NOTES IN COMPUTER SCIENCE).
Gaglio, Salvatore ; Lo Bosco, Giosue' ; Rizzo, Riccardo ; Lo Bosco, Giosué ; Rizzo, Riccardo ; Di Gangi, Mattia Antonino. / A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences. Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II. Vol. 10209 2017. pagg. 524-533 (LECTURE NOTES IN COMPUTER SCIENCE).
@inbook{daebfa76aa7443d6bf9cb45156969427,
title = "A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences",
abstract = "A nucleosome is a DNA-histone complex, wrapping about 150 pairs of double-stranded DNA. The role of nucleosomes is to pack the DNA into the nucleus of the Eukaryote cells to form the Chromatin. Nucleosome positioning genome wide play an important role in the regulation of cell type-specific gene activities. Several biological studies have shown sequence specificity of nucleosome presence, clearly underlined by the organization of precise nucleotides substrings. Taking into consideration such advances, the identification of nucleosomes on a genomic scale has been successfully performed by DNA sequence features representation and classical supervised classification methods such as Support Vector Machines and Logistic regression. The goal of this work is to propose a classification method for nucleosome positioning that, differently from the proposed method so far, does not make any use of a sequence feature extraction step. Deep neural networks (DNN) or deep learning models, were proved to be able to extract automatically useful features from input patterns. Under this framework, Long Short-Term Memory (LSTM) is a recurrent unit that reads a sequence one step at a time and can exploit long range relations. In this work, we propose a DNN model for nucleosome identification on sequences from three different species. Our experiments show that it outperforms classical methods in two of the three data sets and give promising results also for the other",
keywords = "Nucleosome classification, Epigenetic, Deep learning networks, Recurrent Neural Networks",
author = "Salvatore Gaglio and {Lo Bosco}, Giosue' and Riccardo Rizzo and {Lo Bosco}, Giosu{\'e} and Riccardo Rizzo and {Di Gangi}, {Mattia Antonino}",
year = "2017",
language = "English",
isbn = "978-3-319-56153-0",
volume = "10209",
series = "LECTURE NOTES IN COMPUTER SCIENCE",
pages = "524--533",
booktitle = "Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II",

}

TY - CHAP

T1 - A Deep Learning Network for Exploiting Positional Information in Nucleosome Related Sequences

AU - Gaglio, Salvatore

AU - Lo Bosco, Giosue'

AU - Rizzo, Riccardo

AU - Lo Bosco, Giosué

AU - Rizzo, Riccardo

AU - Di Gangi, Mattia Antonino

PY - 2017

Y1 - 2017

N2 - A nucleosome is a DNA-histone complex, wrapping about 150 pairs of double-stranded DNA. The role of nucleosomes is to pack the DNA into the nucleus of the Eukaryote cells to form the Chromatin. Nucleosome positioning genome wide play an important role in the regulation of cell type-specific gene activities. Several biological studies have shown sequence specificity of nucleosome presence, clearly underlined by the organization of precise nucleotides substrings. Taking into consideration such advances, the identification of nucleosomes on a genomic scale has been successfully performed by DNA sequence features representation and classical supervised classification methods such as Support Vector Machines and Logistic regression. The goal of this work is to propose a classification method for nucleosome positioning that, differently from the proposed method so far, does not make any use of a sequence feature extraction step. Deep neural networks (DNN) or deep learning models, were proved to be able to extract automatically useful features from input patterns. Under this framework, Long Short-Term Memory (LSTM) is a recurrent unit that reads a sequence one step at a time and can exploit long range relations. In this work, we propose a DNN model for nucleosome identification on sequences from three different species. Our experiments show that it outperforms classical methods in two of the three data sets and give promising results also for the other

AB - A nucleosome is a DNA-histone complex, wrapping about 150 pairs of double-stranded DNA. The role of nucleosomes is to pack the DNA into the nucleus of the Eukaryote cells to form the Chromatin. Nucleosome positioning genome wide play an important role in the regulation of cell type-specific gene activities. Several biological studies have shown sequence specificity of nucleosome presence, clearly underlined by the organization of precise nucleotides substrings. Taking into consideration such advances, the identification of nucleosomes on a genomic scale has been successfully performed by DNA sequence features representation and classical supervised classification methods such as Support Vector Machines and Logistic regression. The goal of this work is to propose a classification method for nucleosome positioning that, differently from the proposed method so far, does not make any use of a sequence feature extraction step. Deep neural networks (DNN) or deep learning models, were proved to be able to extract automatically useful features from input patterns. Under this framework, Long Short-Term Memory (LSTM) is a recurrent unit that reads a sequence one step at a time and can exploit long range relations. In this work, we propose a DNN model for nucleosome identification on sequences from three different species. Our experiments show that it outperforms classical methods in two of the three data sets and give promising results also for the other

KW - Nucleosome classification, Epigenetic, Deep learning networks, Recurrent Neural Networks

UR - http://hdl.handle.net/10447/225306

M3 - Chapter

SN - 978-3-319-56153-0

VL - 10209

T3 - LECTURE NOTES IN COMPUTER SCIENCE

SP - 524

EP - 533

BT - Bioinformatics and Biomedical Engineering, 5th International Work-Conference, IWBBIO 2017, Granada, Spain, April 26–28, 2017, Proceedings, Part II

ER -