Proposal for student project: MoBiLe 2013

git-svn-id: https://humgenprojects.lumc.nl/svn/mutalyzer/trunk@688 eb6bd6ab-9ccd-42b9-aceb-e2899b4a52f1

doc/Proposal_MoBiLe_2013/Makefile

+# Generate PDF from LaTeX and BibTeX source.
+#
+# There are some hacks in here to work with LaTeX compilation, I'll try
+# to document them with comments :)
+#
+# Martijn Vermaat, martijn@vermaat.name
+
+# Configuration
+DOCUMENT = mutalyzer-mobile-2013
+PDFLATEX = /usr/bin/pdflatex
+PDFLATEXFLAGS = -halt-on-error -interaction errorstopmode
+BIBTEX = /usr/bin/bibtex
+
+# Just create the PDF!
+all: pdf
+
+# Compile BibTeX source file (run this when citations or .bib file change)
+bibtex: $(DOCUMENT).bbl
+
+# Create the files
+pdf: $(DOCUMENT).pdf
+
+# For the PDF, we need a .tex LaTeX source. Actually, we also need a .bbl
+# BibTeX database, but we don't want to regenerate that on every .tex change.
+# We compile the file twice to make sure all references are okay.
+%.pdf: %.tex %.bbl
+	$(PDFLATEX) $(PDFLATEXFLAGS) $<
+	while egrep -q -s 'Rerun (LaTeX|to get cross-references right)' $*.log ;\
+	    do \
+	        $(PDFLATEX) $(PDFLATEXFLAGS) $< ;\
+	    done
+	$(PDFLATEX) $(PDFLATEXFLAGS) $< # With ntheorem, another run is needed
+
+# For the .bbl BibTeX database we need the .bib BibTeX source and .tex LaTeX
+# source.
+# Afterwards, we remove the resulting PDF, because we require some additional
+# compilation passes that are done by the %.pdf rule.
+%.bbl: %.bib %.tex
+	$(PDFLATEX) $(PDFLATEXFLAGS) $*
+	$(BIBTEX) $*
+	$(PDFLATEX) $(PDFLATEXFLAGS) $*
+	while egrep -q -s 'Rerun (LaTeX|to get cross-references right)' $*.log ;\
+	    do \
+	        $(PDFLATEX) $(PDFLATEXFLAGS) $* ;\
+	    done
+	/bin/rm $*.pdf
+
+# Please make sure we don't kill any sources...
+clean:
+	rm -f $(DOCUMENT).aux $(DOCUMENT).pdf $(DOCUMENT).log $(DOCUMENT).toc $(DOCUMENT).out $(DOCUMENT).bbl $(DOCUMENT).blg $(DOCUMENT).nav $(DOCUMENT).snm $(DOCUMENT).vrb

doc/Proposal_MoBiLe_2013/mutalyzer-mobile-2013.bib

+@unpublished{elzanowski-2010,
+    title = {{T}he {G}enetic {C}odes},
+    author = {Andrzej (Anjay) Elzanowski and Jim Ostell},
+    month = jul # "~07,",
+    year = {2010},
+    note = {\url{http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c}}
+}
+
+@article{slavoff-2013,
+author = {Slavoff SA and Mitchell AJ and Schwaid AG and Cabili MN and Ma J and Levin JZ and Karger AD and Budnik BA and Rinn JL and Saghatelian A},
+title = {Peptidomic discovery of short open reading frame-encoded peptides in human cells},
+volume = {9},
+number = {1},
+pages = {59-64},
+year = {2013},
+journal = {Nature chemical biology}
+}

doc/Proposal_MoBiLe_2013/mutalyzer-mobile-2013.tex

+\documentclass[a4paper,11pt]{article}
+\usepackage{a4,fullpage}
+\usepackage[latin1]{inputenc}
+\usepackage[english]{babel}
+\usepackage{amsmath,amsfonts,amssymb}
+\usepackage{qpxmath}
+\usepackage{tgpagella}
+\renewcommand{\ttdefault}{txtt}
+\usepackage[scaled=0.95]{helvet}
+\usepackage[T1]{fontenc}
+\usepackage[numbers]{natbib}
+\bibliographystyle{plainnat}
+\addto\captionsenglish{\renewcommand{\bibname}{References}}
+%\shortcites{green-2010}
+\usepackage{url}
+%% Define a new 'leo' style for the package that will use a smaller
+%% font.
+\makeatletter
+\def\url@leostyle{%
+  \@ifundefined{selectfont}{\def\UrlFont{\sf}}{\def\UrlFont{\small\ttfamily}}}
+\makeatother
+%% Now actually use the newly defined style.
+\urlstyle{leo}
+\usepackage{hyperref}
+\hypersetup{
+  final,
+  colorlinks=true,
+  citecolor=black,
+  filecolor=black,
+  linkcolor=red,
+  urlcolor=red,
+  anchorcolor=black,
+  pdfauthor={Martijn Vermaat},
+  pdftitle={Quality control of full-genome alignments for 756 individuals in the
+    Genome of the NetherlandsInfinitary Rewriting in Coq},
+}
+\setlength\parskip{\medskipamount}
+\setlength{\parindent}{0pt}
+\pagestyle{plain}
+
+
+\title{Research project proposal: Extending the Mutalyzer reference sequence
+  parser for the analysis of mysterious genes}
+\date{April 8, 2013}
+\author{Martijn Vermaat \and Jeroen F. J. Laros \and Peter
+  E. M. Taschner\\[1.5em]
+\normalsize{Department of Human Genetics, Leiden University Medical Center}}
+
+
+\begin{document}
+
+
+\maketitle
+\thispagestyle{empty}
+
+
+\section*{Background}
+
+The application of molecular genetic techniques to elucidate the molecular
+basis of hereditary disease in both research and diagnostic settings has led
+to the identification of many sequence variations in human genes.
+The department of Human Genetics maintains several databases containing
+sequence variations (see \href{http://www.lovd.nl}{lovd.nl}), which need to be
+curated to assure use of appropriate sequence variation nomenclature.
+The current Mutalyzer 2 (\href{https://mutalyzer.nl}{mutalyzer.nl}) enables
+extended checks of sequence variation nomenclature provided by the user, but
+also provides mutation descriptions for all transcripts and proteins affected
+by a genomic sequence change when a properly annotated reference sequence is
+provided. The latter information already provides the basis for an extended
+analysis of genotype-phenotype correlations.
+
+
+\section*{Project description}
+
+The students will work on the reference sequence record parser of Mutalyzer to
+capture and use additional annotation in
+\href{http://www.ncbi.nlm.nih.gov/refseq/}{RefSeq},
+\href{http://www.lrg-sequence.org/}{LRG}, and
+\href{http://www.ensembl.org/index.html}{Ensembl} records which will help
+extending Mutalyzer's functionality to ``exotic'' human genes
+\begin{enumerate}
+  \itemsep0em
+  \item with alternative use of termination codons (UGA for selenocystein and
+    UAG for pyrrolysine incorporation) \citep{elzanowski-2010},
+  \item having mismatches between RefSeq genomic and transcript or protein
+    coding sequences, or
+  \item using alternative start codons \citep{slavoff-2013}.
+\end{enumerate}
+Each extension of the improved parser will be implemented by the Mutalyzer
+development team on a publicly reachable server, so progress can be followed
+during the project.
+In addition, a solution has to be developed for bacterial translation,
+including the automatic generation of mutated sequences, automatic submission
+of these sequences and their reference counterparts for analysis and
+comparison with web-based analysis tools and prediction of mutation effects.
+
+
+\section*{Implementation details}
+
+The Mutalyzer sequence variation nomenclature checker is implemented in Python
+and uses \href{http://biopython.org/}{BioPython} and Python's XML libraries
+for parsing reference sequence records.
+To generalize specific formats such as GenBank and LRG, an abstract reference
+sequence representation is used internally (``GenRecord'').
+Students are expected to extend this representation with additional attributes
+and write the code to implement them from data in the specific formats.
+Some experience with programming in Python is required to take on this
+project.
+
+
+\bibliography{mutalyzer-mobile-2013}
+
+
+\end{document}