coolneng
/
bachelor-thesis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Adapt babathesis to the TFG

This commit is contained in:
coolneng 2021-06-28 00:48:32 +02:00
parent fed667561e
commit 707b2adadc
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
6 changed files with 1177 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/Dissertation.org
View File

@ -1,19 +1,13 @@
#+TITLE: Machine Learning para corrección de errores en datos de secuenciación de ADN #+TITLE: Machine Learning para corrección de errores en datos de secuenciación de ADN
#+SUBTITLE: Trabajo de Fin de Grado
#+AUTHOR: Amin Kasrou Aouam #+AUTHOR: Amin Kasrou Aouam
#+DATE: 26-06-2021 #+DATE: 26 de Junio de 2021
#+PANDOC_OPTIONS: template:~/.pandoc/templates/eisvogel.latex #+PANDOC_OPTIONS: template:assets/babathesis.latex
#+PANDOC_OPTIONS: toc:t #+PANDOC_OPTIONS: toc:t
#+PANDOC_OPTIONS: bibliography:assets/bibliography.bib #+PANDOC_OPTIONS: bibliography:assets/bibliography.bib
#+PANDOC_OPTIONS: citeproc:t #+PANDOC_OPTIONS: citeproc:t
#+PANDOC_OPTIONS: csl:assets/ieee.csl #+PANDOC_OPTIONS: csl:assets/ieee.csl
#+PANDOC_OPTIONS: pdf-engine:xelatex
#+PANDOC_METADATA: link-citations:t #+PANDOC_METADATA: link-citations:t
#+PANDOC_METADATA: lang=es
#+PANDOC_METADATA: titlepage:t
#+PANDOC_METADATA: toc-own-page:t
#+PANDOC_METADATA: table-use-row-colors:t
#+PANDOC_METADATA: colorlinks:t
#+PANDOC_METADATA: logo:/home/coolneng/Photos/Logos/UGR.png
* Resumen * Resumen
Las nuevas técnicas de secuenciación de ADN (NGS) han revolucionado la investigación en genómica. Estas tecnologías se basan en la secuenciación de millones de fragmentos de ADN en paralelo, cuya reconstrucción se basa en técnicas de bioinformática. Aunque estas técnicas se apliquen de forma habitual, presentan tasas de error significantes que son detrimentales para el análisis de regiones con alto grado de polimorfismo. En este estudio se implementa un nuevo método computacional, locimend, basado en /Deep Learning/ para la corrección de errores de secuenciación de ADN. Se aplica al análisis de la región determinante de complementariedad 3 (CDR3) del receptor de linfocitos T (TCR), generada /in silico/ y posteriorimente sometida a un simulador de secuenciación con el fin de producir errores de secuenciación. Empleando estos datos, entrenamos una red neuronal convolucional (CNN) con el objetivo de generar un modelo computacional que permita la detección y corrección de los errores de secuenciación. Las nuevas técnicas de secuenciación de ADN (NGS) han revolucionado la investigación en genómica. Estas tecnologías se basan en la secuenciación de millones de fragmentos de ADN en paralelo, cuya reconstrucción se basa en técnicas de bioinformática. Aunque estas técnicas se apliquen de forma habitual, presentan tasas de error significantes que son detrimentales para el análisis de regiones con alto grado de polimorfismo. En este estudio se implementa un nuevo método computacional, locimend, basado en /Deep Learning/ para la corrección de errores de secuenciación de ADN. Se aplica al análisis de la región determinante de complementariedad 3 (CDR3) del receptor de linfocitos T (TCR), generada /in silico/ y posteriorimente sometida a un simulador de secuenciación con el fin de producir errores de secuenciación. Empleando estos datos, entrenamos una red neuronal convolucional (CNN) con el objetivo de generar un modelo computacional que permita la detección y corrección de los errores de secuenciación.
@ -30,8 +24,7 @@ Next generation sequencing (NGS) have revolutionised genomic research. These tec
* Introducción * Introducción
** Técnicas de secuenciación de alto rendimiento En los últimos años se ha
** Sistema inmunitario
La capacidad del sistema inmunitario adaptativo para responder a cualquiera de los numerosos antígenos extraños potenciales a los que puede estar expuesta una persona depende de los receptores altamente polimórficos expresados por las células B (inmunoglobulinas) y las células T (receptores de células T [TCR]). La especificidad de las células T viene determinada principalmente por la secuencia de aminoácidos codificada en los bucles de la tercera región determinante de la complementariedad (CDR3). cite:pmid19706884 La capacidad del sistema inmunitario adaptativo para responder a cualquiera de los numerosos antígenos extraños potenciales a los que puede estar expuesta una persona depende de los receptores altamente polimórficos expresados por las células B (inmunoglobulinas) y las células T (receptores de células T [TCR]). La especificidad de las células T viene determinada principalmente por la secuencia de aminoácidos codificada en los bucles de la tercera región determinante de la complementariedad (CDR3). cite:pmid19706884

BIN
docs/Dissertation.pdf
View File

Binary file not shown.

96
docs/assets/babathesis.latex
View File

@ -7,6 +7,9 @@
% Use 'KOMA-Script Book' as the document class % Use 'KOMA-Script Book' as the document class
\documentclass[toc=bibliography,toc=indentunnumbered,listof=totoc]{scrbook} \documentclass[toc=bibliography,toc=indentunnumbered,listof=totoc]{scrbook}
% Use Spanish as language
\usepackage[spanish]{babel}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@ -62,7 +65,7 @@
%\KOMAoptions{parskip=half+} %\KOMAoptions{parskip=half+}
% Don't stretch the content to fill entire pages % Don't stretch the content to fill entire pages
\raggedbottom \raggedbottom{}
% Don't break paragraphs because of a single line % Don't break paragraphs because of a single line
\PassOptionsToPackage{defaultlines=2,all}{nowidow} \PassOptionsToPackage{defaultlines=2,all}{nowidow}
@ -120,7 +123,7 @@
\setsansfont{URW Classico}% \setsansfont{URW Classico}%
[ [
UprightFont = {*-Regular}, UprightFont = {*-Regular},
ItalicFont = {*-Italic}, ItalicFont = {*-Italic Italic},
BoldFont = {*-Bold}, BoldFont = {*-Bold},
Numbers = {Proportional,Lining}, Numbers = {Proportional,Lining},
Scale = MatchUppercase Scale = MatchUppercase
@ -221,7 +224,6 @@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Make sure footnote marks are separated by commas and kerned properly % Make sure footnote marks are separated by commas and kerned properly
\usepackage[multiple=true,mult-fn-sep=${}^{,\kern-0.07em}$]{fnpct}
% Change the font used for footnotes % Change the font used for footnotes
%\addtokomafont{footnote}{\sffamily} %\addtokomafont{footnote}{\sffamily}
@ -265,8 +267,8 @@
% Fix kerning problems for backslashes and redefine underscores in hyperlinks % Fix kerning problems for backslashes and redefine underscores in hyperlinks
\makeatletter \makeatletter
\let\UrlSpecialsOld\UrlSpecials \let\UrlSpecialsOld\UrlSpecials{}
\def\UrlSpecials{\UrlSpecialsOld\do\/{\Url@slash}\do\_{\Url@underscore}}% \def\UrlSpecials{\UrlSpecialsOld\do/{\Url@slash}\do\_{\Url@underscore}}%
\def\Url@slash{\@ifnextchar/{\kern+0.05em\mathchar47\kern-0.10em}% \def\Url@slash{\@ifnextchar/{\kern+0.05em\mathchar47\kern-0.10em}%
{\kern0.08em\mathchar47\penalty\UrlBigBreakPenalty}} {\kern0.08em\mathchar47\penalty\UrlBigBreakPenalty}}
\def\Url@underscore{\nfss@text{\leavevmode \kern.06em\vbox{\hrule height 0.12ex width 0.4em}}} \def\Url@underscore{\nfss@text{\leavevmode \kern.06em\vbox{\hrule height 0.12ex width 0.4em}}}
@ -284,7 +286,7 @@
\PassOptionsToPackage{backend=biber}{biblatex} \PassOptionsToPackage{backend=biber}{biblatex}
% Bibliography style (e.g. 'phys' or 'nature') % Bibliography style (e.g. 'phys' or 'nature')
\PassOptionsToPackage{style=bababib}{biblatex} \PassOptionsToPackage{style=phys}{biblatex}
% Citation style (e.g. 'plain' or 'superscript') % Citation style (e.g. 'plain' or 'superscript')
\PassOptionsToPackage{autocite=plain}{biblatex} \PassOptionsToPackage{autocite=plain}{biblatex}
@ -292,10 +294,32 @@
% Enable multiple bibliographies with separate numbering % Enable multiple bibliographies with separate numbering
\PassOptionsToPackage{defernumbers=true}{biblatex} \PassOptionsToPackage{defernumbers=true}{biblatex}
% Pandoc references
% Format for cross-references with \cref % Format for cross-references with \cref
\PassOptionsToPackage{noabbrev}{cleveref} \PassOptionsToPackage{noabbrev}{cleveref}
\newcommand{\crefrangeconjunction}{--} \newcommand{\crefrangeconjunction}{--}
\newlength{\cslhangindent}
\setlength{\cslhangindent}{1.5em}
\newlength{\csllabelwidth}
\setlength{\csllabelwidth}{3em}
\newenvironment{CSLReferences}[2] % #1 hanging-ident, #2 entry spacing
{% don't indent paragraphs
\setlength{\parindent}{0pt}
% turn on hanging indent if param 1 is 1
\ifodd #1 \everypar{\setlength{\hangindent}{\cslhangindent}}\ignorespaces\fi
% set entry spacing
\ifnum #2 > 0
\setlength{\parskip}{#2\baselineskip}
\fi
}%
{}
\usepackage{calc}
\newcommand{\CSLBlock}[1]{#1\hfill\break}
\newcommand{\CSLLeftMargin}[1]{\parbox[t]{\csllabelwidth}{#1}}
\newcommand{\CSLRightInline}[1]{\parbox[t]{\linewidth - \csllabelwidth}{#1}\break}
\newcommand{\CSLIndent}[1]{\hspace{\cslhangindent}#1}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@ -328,8 +352,8 @@
%\AtBeginDocument{\let\nabla=𝛁} %\AtBeginDocument{\let\nabla=𝛁}
\AtBeginDocument% \AtBeginDocument%
{ {
\let\epsilon=\varepsilon \let\epsilon=\varepsilon{}
\let\phi=\varphi \let\phi=\varphi{}
} }
% Change the font used for tables % Change the font used for tables
@ -351,7 +375,7 @@
\makeatother \makeatother
% Replace \cite with the more flexible \autocite % Replace \cite with the more flexible \autocite
\let\cite=\autocite \let\cite=\autocite{}
% Define a custom color palette % Define a custom color palette
\definecolor{whiteish}{rgb}{1.000, 0.964, 0.859} \definecolor{whiteish}{rgb}{1.000, 0.964, 0.859}
@ -403,17 +427,53 @@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Import bibliographies % Import bibliographies
\addbibresource{references.bib} \addbibresource{bibliography.bib}
\begin{document} \begin{document}
% UGR titlepage
\begin{titlepage}
\newlength{\centeroffset}
\setlength{\centeroffset}{-0.5\oddsidemargin}
\addtolength{\centeroffset}{0.5\evensidemargin}
\thispagestyle{empty}
\noindent\hspace*{\centeroffset}
\begin{minipage}{\textwidth}
\centering
\includegraphics[width=0.9\textwidth]{assets/logo_ugr}\\[1cm]
\textsc{ \Large TRABAJO FIN DE GRADO\\[0.2cm]}
\textsc{ GRADO DE INGENIERÍA EN INFORMÁTICA}\\[1cm]
% Upper part of the page
%
% Title
{\huge\bfseries $title$\\}
\noindent\rule[-1ex]{\textwidth}{3pt}\\[3.5ex]
{\large\bfseries }
\end{minipage}
\vspace{0.3cm}
\noindent\hspace*{\centeroffset}\begin{minipage}{\textwidth}
\centering
\textbf{Autor}\\ {$author$}\\[2.5ex]
\textbf{Directores}\\
{Carlos Cano Gutiérrez}\\
{María Soledad Benítez Cantos}\\[2cm]
\includegraphics[width=0.3\textwidth]{assets/logo-ceuta.jpg}\\[0.1cm]
\textsc{Facultad de Educación, Tecnología y Economía de Ceuta}\\
\textsc{---}\\
Granada, $date$
\end{minipage}
\end{titlepage}
\frontmatter \frontmatter
\include{chapters/abstract} \listoftables
\include{chapters/preface} \listoffigures
\tableofcontents \tableofcontents
\mainmatter \mainmatter{}
\include{chapters/introduction} $body$
\include{chapters/test} \backmatter{}
\include{chapters/conclusion} \printbibliography{}
\backmatter
\printbibliography
\end{document} \end{document}

257
docs/assets/bibliography.bib
View File

@ -1,13 +1,43 @@
@article{10.1093/molbev/msy224, @article{10.1093/molbev/msy224,
author = {Flagel, Lex and Brandvain, Yaniv and Schrider, Daniel R}, author = {Flagel, Lex and Brandvain, Yaniv and Schrider, Daniel R},
title = "{The Unreasonable Effectiveness of Convolutional Neural Networks in Population Genetic Inference}", title = "{The Unreasonable Effectiveness of Convolutional Neural
Networks in Population Genetic Inference}",
journal = {Molecular Biology and Evolution}, journal = {Molecular Biology and Evolution},
volume = {36}, volume = 36,
number = {2}, number = 2,
pages = {220-238}, pages = {220-238},
year = {2018}, year = 2018,
month = {12}, month = 12,
abstract = "{Population-scale genomic data sets have given researchers incredible amounts of information from which to infer evolutionary histories. Concomitant with this flood of data, theoretical and methodological advances have sought to extract information from genomic sequences to infer demographic events such as population size changes and gene flow among closely related populations/species, construct recombination maps, and uncover loci underlying recent adaptation. To date, most methods make use of only one or a few summaries of the input sequences and therefore ignore potentially useful information encoded in the data. The most sophisticated of these approaches involve likelihood calculations, which require theoretical advances for each new problem, and often focus on a single aspect of the data (e.g., only allele frequency information) in the interest of mathematical and computational tractability. Directly interrogating the entirety of the input sequence data in a likelihood-free manner would thus offer a fruitful alternative. Here, we accomplish this by representing DNA sequence alignments as images and using a class of deep learning methods called convolutional neural networks (CNNs) to make population genetic inferences from these images. We apply CNNs to a number of evolutionary questions and find that they frequently match or exceed the accuracy of current methods. Importantly, we show that CNNs perform accurate evolutionary model selection and parameter estimation, even on problems that have not received detailed theoretical treatments. Thus, when applied to population genetic alignments, CNNs are capable of outperforming expert-derived statistical methods and offer a new path forward in cases where no likelihood approach exists.}", abstract = "{Population-scale genomic data sets have given researchers
incredible amounts of information from which to infer
evolutionary histories. Concomitant with this flood of data,
theoretical and methodological advances have sought to extract
information from genomic sequences to infer demographic events
such as population size changes and gene flow among closely
related populations/species, construct recombination maps, and
uncover loci underlying recent adaptation. To date, most
methods make use of only one or a few summaries of the input
sequences and therefore ignore potentially useful information
encoded in the data. The most sophisticated of these
approaches involve likelihood calculations, which require
theoretical advances for each new problem, and often focus on
a single aspect of the data (e.g., only allele frequency
information) in the interest of mathematical and computational
tractability. Directly interrogating the entirety of the input
sequence data in a likelihood-free manner would thus offer a
fruitful alternative. Here, we accomplish this by representing
DNA sequence alignments as images and using a class of deep
learning methods called convolutional neural networks (CNNs)
to make population genetic inferences from these images. We
apply CNNs to a number of evolutionary questions and find that
they frequently match or exceed the accuracy of current
methods. Importantly, we show that CNNs perform accurate
evolutionary model selection and parameter estimation, even on
problems that have not received detailed theoretical
treatments. Thus, when applied to population genetic
alignments, CNNs are capable of outperforming expert-derived
statistical methods and offer a new path forward in cases
where no likelihood approach exists.}",
issn = {0737-4038}, issn = {0737-4038},
doi = {10.1093/molbev/msy224}, doi = {10.1093/molbev/msy224},
url = {https://doi.org/10.1093/molbev/msy224}, url = {https://doi.org/10.1093/molbev/msy224},
@ -15,12 +45,217 @@
} }
@Article{pmid19706884, @Article{pmid19706884,
Author="Robins, H. S. and Campregher, P. V. and Srivastava, S. K. and Wacher, A. and Turtle, C. J. and Kahsai, O. and Riddell, S. R. and Warren, E. H. and Carlson, C. S. ", Author = "Robins, H. S. and Campregher, P. V. and Srivastava, S. K.
Title="{{C}omprehensive assessment of {T}-cell receptor beta-chain diversity in alphabeta {T} cells}", and Wacher, A. and Turtle, C. J. and Kahsai, O. and Riddell,
S. R. and Warren, E. H. and Carlson, C. S. ",
Title = "{{C}omprehensive assessment of {T}-cell receptor beta-chain
diversity in alphabeta {T} cells}",
Journal = "Blood", Journal = "Blood",
Year="2009", Year = 2009,
Volume="114", Volume = 114,
Number="19", Number = 19,
Pages = "4099--4107", Pages = "4099--4107",
Month = "Nov" Month = "Nov"
} }
@article {Nurk2021.05.26.445798,
author = {Nurk, Sergey and Koren, Sergey and Rhie, Arang and
Rautiainen, Mikko and Bzikadze, Andrey V. and Mikheenko, Alla
and Vollger, Mitchell R. and Altemose, Nicolas and Uralsky,
Lev and Gershman, Ariel and Aganezov, Sergey and Hoyt,
Savannah J. and Diekhans, Mark and Logsdon, Glennis A. and
Alonge, Michael and Antonarakis, Stylianos E. and Borchers,
Matthew and Bouffard, Gerard G. and Brooks, Shelise Y. and
Caldas, Gina V. and Cheng, Haoyu and Chin, Chen-Shan and Chow,
William and de Lima, Leonardo G. and Dishuck, Philip C. and
Durbin, Richard and Dvorkina, Tatiana and Fiddes, Ian T. and
Formenti, Giulio and Fulton, Robert S. and Fungtammasan,
Arkarachai and Garrison, Erik and Grady, Patrick G.S. and
Graves-Lindsay, Tina A. and Hall, Ira M. and Hansen, Nancy F.
and Hartley, Gabrielle A. and Haukness, Marina and Howe,
Kerstin and Hunkapiller, Michael W. and Jain, Chirag and Jain,
Miten and Jarvis, Erich D. and Kerpedjiev, Peter and Kirsche,
Melanie and Kolmogorov, Mikhail and Korlach, Jonas and
Kremitzki, Milinn and Li, Heng and Maduro, Valerie V. and
Marschall, Tobias and McCartney, Ann M. and McDaniel, Jennifer
and Miller, Danny E. and Mullikin, James C. and Myers, Eugene
W. and Olson, Nathan D. and Paten, Benedict and Peluso, Paul
and Pevzner, Pavel A. and Porubsky, David and Potapova, Tamara
and Rogaev, Evgeny I. and Rosenfeld, Jeffrey A. and Salzberg,
Steven L. and Schneider, Valerie A. and Sedlazeck, Fritz J.
and Shafin, Kishwar and Shew, Colin J. and Shumate, Alaina and
Sims, Yumi and Smit, Arian F. A. and Soto, Daniela C. and
Sovi{\'c}, Ivan and Storer, Jessica M. and Streets, Aaron and
Sullivan, Beth A. and Thibaud-Nissen, Fran{\c c}oise and
Torrance, James and Wagner, Justin and Walenz, Brian P. and
Wenger, Aaron and Wood, Jonathan M. D. and Xiao, Chunlin and
Yan, Stephanie M. and Young, Alice C. and Zarate, Samantha and
Surti, Urvashi and McCoy, Rajiv C. and Dennis, Megan Y. and
Alexandrov, Ivan A. and Gerton, Jennifer L. and
O{\textquoteright}Neill, Rachel J. and Timp, Winston and Zook,
Justin M. and Schatz, Michael C. and Eichler, Evan E. and
Miga, Karen H. and Phillippy, Adam M.},
title = {The complete sequence of a human genome},
elocation-id = {2021.05.26.445798},
year = 2021,
doi = {10.1101/2021.05.26.445798},
publisher = {Cold Spring Harbor Laboratory},
abstract = {In 2001, Celera Genomics and the International Human Genome
Sequencing Consortium published their initial drafts of the
human genome, which revolutionized the field of genomics.
While these drafts and the updates that followed effectively
covered the euchromatic fraction of the genome, the
heterochromatin and many other complex regions were left
unfinished or erroneous. Addressing this remaining 8\% of the
genome, the Telomere-to-Telomere (T2T) Consortium has finished
the first truly complete 3.055 billion base pair (bp) sequence
of a human genome, representing the largest improvement to the
human reference genome since its initial release. The new
T2T-CHM13 reference includes gapless assemblies for all 22
autosomes plus Chromosome X, corrects numerous errors, and
introduces nearly 200 million bp of novel sequence containing
2,226 paralogous gene copies, 115 of which are predicted to be
protein coding. The newly completed regions include all
centromeric satellite arrays and the short arms of all five
acrocentric chromosomes, unlocking these complex regions of
the genome to variational and functional studies for the first
time.Competing Interest StatementAF and CSC are employees of
DNAnexus; IS, JK, MWH, PP, and AW are employees of Pacific
Biosciences; FJS has received travel funds to speak at events
hosted by Pacific Biosciences; SK and FJS have received travel
funds to speak at events hosted by Oxford Nanopore
Technologies. WT has licensed two patents to Oxford Nanopore
Technologies (US 8748091 and 8394584).},
URL = {https://www.biorxiv.org/content/early/2021/05/27/2021.05.26.445798},
eprint = {https://www.biorxiv.org/content/early/2021/05/27/2021.05.26.445798.full.pdf},
journal = {bioRxiv}
}
@ARTICLE{10.3389/fgene.2020.00900,
AUTHOR = {Wang, Luotong and Qu, Li and Yang, Longshu and Wang, Yiying
and Zhu, Huaiqiu},
TITLE = {NanoReviser: An Error-Correction Tool for Nanopore
Sequencing Based on a Deep Learning Algorithm},
JOURNAL = {Frontiers in Genetics},
VOLUME = 11,
PAGES = 900,
YEAR = 2020,
URL = {https://www.frontiersin.org/article/10.3389/fgene.2020.00900},
DOI = {10.3389/fgene.2020.00900},
ISSN = {1664-8021},
ABSTRACT = {Nanopore sequencing is regarded as one of the most
promising third-generation sequencing (TGS) technologies.
Since 2014, Oxford Nanopore Technologies (ONT) has developed a
series of devices based on nanopore sequencing to produce very
long reads, with an expected impact on genomics. However, the
nanopore sequencing reads are susceptible to a fairly high
error rate owing to the difficulty in identifying the DNA
bases from the complex electrical signals. Although several
basecalling tools have been developed for nanopore sequencing
over the past years, it is still challenging to correct the
sequences after applying the basecalling procedure. In this
study, we developed an open-source DNA basecalling reviser,
NanoReviser, based on a deep learning algorithm to correct the
basecalling errors introduced by current basecallers provided
by default. In our module, we re-segmented the raw electrical
signals based on the basecalled sequences provided by the
default basecallers. By employing convolution neural networks
(CNNs) and bidirectional long short-term memory (Bi-LSTM)
networks, we took advantage of the information from the raw
electrical signals and the basecalled sequences from the
basecallers. Our results showed NanoReviser, as a
post-basecalling reviser, significantly improving the
basecalling quality. After being trained on standard ONT
sequencing reads from public E. coli and human NA12878
datasets, NanoReviser reduced the sequencing error rate by
over 5% for both the E. coli dataset and the human dataset.
The performance of NanoReviser was found to be better than
those of all current basecalling tools. Furthermore, we
analyzed the modified bases of the E. coli dataset and added
the methylation information to train our module. With the
methylation annotation, NanoReviser reduced the error rate by
7% for the E. coli dataset and specifically reduced the error
rate by over 10% for the regions of the sequence rich in
methylated bases. To the best of our knowledge, NanoReviser is
the first post-processing tool after basecalling to accurately
correct the nanopore sequences without the time-consuming
procedure of building the consensus sequence. The NanoReviser
package is freely available at <ext-link ext-link-type="uri"
xlink:href="https://github.com/pkubioinformatics/NanoReviser"
xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/pkubioinformatics/NanoReviser</ext-link>.}
}

@Article{Davis2021,
author = {Davis, Eric M. and Sun, Yu and Liu, Yanling and Kolekar,
Pandurang and Shao, Ying and Szlachta, Karol and Mulder,
Heather L. and Ren, Dongren and Rice, Stephen V. and Wang,
Zhaoming and Nakitandwe, Joy and Gout, Alexander M. and
Shaner, Bridget and Hall, Salina and Robison, Leslie L. and
Pounds, Stanley and Klco, Jeffery M. and Easton, John and Ma,
Xiaotu},
title = {SequencErr: measuring and suppressing sequencer errors in
next-generation sequencing data},
journal = {Genome Biology},
year = 2021,
month = {Jan},
day = 25,
volume = 22,
number = 1,
pages = 37,
abstract = {There is currently no method to precisely measure the
errors that occur in the sequencing instrument/sequencer,
which is critical for next-generation sequencing applications
aimed at discovering the genetic makeup of heterogeneous
cellular populations.},
issn = {1474-760X},
doi = {10.1186/s13059-020-02254-2},
url = {https://doi.org/10.1186/s13059-020-02254-2}
}
@article{HEATHER20161,
title = {The sequence of sequencers: The history of sequencing DNA},
journal = {Genomics},
volume = 107,
number = 1,
pages = {1-8},
year = 2016,
issn = {0888-7543},
doi = {https://doi.org/10.1016/j.ygeno.2015.11.003},
url = {https://www.sciencedirect.com/science/article/pii/S0888754315300410},
author = {James M. Heather and Benjamin Chain},
keywords = {DNA, RNA, Sequencing, Sequencer, History},
abstract = {Determining the order of nucleic acid residues in
biological samples is an integral component of a wide variety
of research applications. Over the last fifty years large
numbers of researchers have applied themselves to the
production of techniques and technologies to facilitate this
feat, sequencing DNA and RNA molecules. This time-scale has
witnessed tremendous changes, moving from sequencing short
oligonucleotides to millions of bases, from struggling towards
the deduction of the coding sequence of a single gene to rapid
and widely available whole genome sequencing. This article
traverses those years, iterating through the different
generations of sequencing technology, highlighting some of the
key discoveries, researchers, and sequences along the way.}
}

@Article{vanDijk2014,
author = {van Dijk, Erwin L. and Auger, H{\'e}l{\`e}ne and
Jaszczyszyn, Yan and Thermes, Claude},
title = {Ten years of next-generation sequencing technology},
journal = {Trends in Genetics},
year = 2014,
month = {Sep},
day = 01,
publisher = {Elsevier},
volume = 30,
number = 9,
pages = {418-426},
issn = {0168-9525},
doi = {10.1016/j.tig.2014.07.001},
url = {https://doi.org/10.1016/j.tig.2014.07.001}
}

BIN
docs/assets/logo-ceuta.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 24 KiB

838
docs/assets/logo_ugr.pdf Normal file
View File

File diff suppressed because one or more lines are too long