From 354c1fd1ca1213063fc41ec4166e6cb917044344 Mon Sep 17 00:00:00 2001
From: Samuel Ortion <samuel+git@ortion.fr>
Date: Fri, 29 Mar 2024 21:05:53 +0100
Subject: [PATCH] Amend text and switch figure extension based on HTML or LaTeX
 export

---
 figures/lallemand2020-fig1_copy.pdf |  4 +-
 figures/lallemand2020-fig1_copy.svg | 58 +++++++++++-----------
 report.org                          | 74 +++++++++++++++++++----------
 report.pdf                          |  4 +-
 4 files changed, 83 insertions(+), 57 deletions(-)

diff --git a/figures/lallemand2020-fig1_copy.pdf b/figures/lallemand2020-fig1_copy.pdf
index a61621a..87c1d85 100644
--- a/figures/lallemand2020-fig1_copy.pdf
+++ b/figures/lallemand2020-fig1_copy.pdf
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6305072bc71c3503b369c829494f9ae578b57da8a66b4c66c02e2ca447b4474e
-size 12354
+oid sha256:d18594e5de423fe3150a46b6b4c2d93fe7eba124102dff9b1f4b48bad1f775d9
+size 12301
diff --git a/figures/lallemand2020-fig1_copy.svg b/figures/lallemand2020-fig1_copy.svg
index fff7c65..d0d0e19 100644
--- a/figures/lallemand2020-fig1_copy.svg
+++ b/figures/lallemand2020-fig1_copy.svg
@@ -2,9 +2,9 @@
 <!-- Created with Inkscape (http://www.inkscape.org/) -->
 
 <svg
-   width="210mm"
-   height="297mm"
-   viewBox="0 0 210 297"
+   width="200mm"
+   height="230mm"
+   viewBox="0 0 200 230"
    version="1.1"
    id="svg1"
    inkscape:version="1.3.2 (091e20ef0f, 2023-11-25)"
@@ -28,8 +28,8 @@
      inkscape:document-units="mm"
      showgrid="true"
      inkscape:zoom="0.74398314"
-     inkscape:cx="401.89083"
-     inkscape:cy="616.94947"
+     inkscape:cx="51.076426"
+     inkscape:cy="404.57906"
      inkscape:window-width="1920"
      inkscape:window-height="1008"
      inkscape:window-x="0"
@@ -39,8 +39,8 @@
     <inkscape:grid
        id="grid2"
        units="mm"
-       originx="0"
-       originy="0"
+       originx="-5.0000023"
+       originy="-5.0000001"
        spacingx="0.99999998"
        spacingy="1"
        empcolor="#0099e5"
@@ -173,7 +173,8 @@
   <g
      inkscape:label="Layer 1"
      inkscape:groupmode="layer"
-     id="layer1">
+     id="layer1"
+     transform="translate(-5.0000024,-5)">
     <g
        id="g64">
       <g
@@ -379,7 +380,7 @@
     </g>
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#ArrowTriangleStylized)"
-       d="m 90.456771,34.997399 25.032419,0.0026"
+       d="m 89.999994,34.997399 25.032416,0.0026"
        id="path23" />
     <text
        xml:space="preserve"
@@ -403,19 +404,19 @@
        sodipodi:nodetypes="cc" />
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#ArrowTriangleStylized)"
-       d="m 90.456777,68.997621 25.032413,0.003"
+       d="m 90.000002,68.997621 25.032418,0.003"
        id="path24" />
     <text
        xml:space="preserve"
        style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:0.913725;stroke-width:1"
-       x="86.394516"
-       y="61.889977"
+       x="87.620811"
+       y="61.320938"
        id="text3"><tspan
          sodipodi:role="line"
          id="tspan3"
          style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;stroke-width:1"
-         x="86.394516"
-         y="61.889977">unequal crossing-over</tspan></text>
+         x="87.620811"
+         y="61.320938">unequal crossing-over</tspan></text>
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#ffaaaa;stroke-width:1"
        d="m 43.015474,82.180432 0.03973,8.74277"
@@ -505,41 +506,41 @@
     </g>
     <text
        xml:space="preserve"
-       style="font-size:4.2333298px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;font-weight:normal;font-style:normal;font-stretch:normal;font-variant:normal;font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal"
+       style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1"
        x="75.085213"
        y="151.30989"
        id="text4"><tspan
          sodipodi:role="line"
          id="tspan4"
-         style="fill:#000000;stroke:none;stroke-width:1;-inkscape-font-specification:'TeX Gyre Termes, Normal';font-family:'TeX Gyre Termes';font-weight:normal;font-style:normal;font-stretch:normal;font-variant:normal;font-size:4.2333298px;font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal"
+         style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;stroke:none;stroke-width:1"
          x="75.085213"
          y="151.30989" /></text>
     <text
        xml:space="preserve"
        style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:0.913725;stroke:none;stroke-width:1;stroke-dasharray:1, 1"
-       x="92.428703"
-       y="163.95569"
+       x="90.094139"
+       y="163.34464"
        id="text6"><tspan
          sodipodi:role="line"
          id="tspan6"
          style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;stroke-width:1"
-         x="92.428703"
-         y="163.95569">transduplication</tspan></text>
+         x="90.094139"
+         y="163.34464">transduplication</tspan></text>
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#ArrowTriangleStylized)"
-       d="m 89.186472,102.99821 25.032418,0.003"
+       d="m 90.000002,102.99821 25.032418,0.003"
        id="path1" />
     <text
        xml:space="preserve"
        style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:0.913725;stroke:#ffaaaa;stroke-width:1;stroke-dasharray:1, 1"
-       x="88.718613"
-       y="95.573738"
+       x="89.944908"
+       y="96.640633"
        id="text5"><tspan
          sodipodi:role="line"
          id="tspan5"
          style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;stroke:none;stroke-width:1"
-         x="88.718613"
-         y="95.573738">tandem duplication</tspan></text>
+         x="89.944908"
+         y="96.640633">tandem duplication</tspan></text>
     <g
        id="g54"
        transform="matrix(0.75018563,0,0,0.75018563,30.108223,22.451333)">
@@ -730,7 +731,7 @@
          y="129.25327">retroduplication</tspan></text>
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#ArrowTriangleStylized-0)"
-       d="m 90.456779,136.99881 25.032411,0.003"
+       d="m 89.622314,134.99671 25.032406,0.003"
        id="path1-7" />
     <path
        style="fill:#000000;fill-opacity:1;stroke:#000000;stroke-width:0.25;stroke-dasharray:none;stroke-opacity:1"
@@ -914,7 +915,7 @@
          y="157.28877">retrocopy</tspan></text>
     <path
        style="fill:none;fill-opacity:0.913725;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#ArrowTriangleStylized-0)"
-       d="m 92.483797,170.9994 25.032413,0.003"
+       d="m 90.000002,170.9994 25.032418,0.003"
        id="path69" />
     <path
        style="fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.25;stroke-dasharray:none;stroke-opacity:1"
@@ -1028,7 +1029,8 @@
   <g
      inkscape:groupmode="layer"
      id="layer2"
-     inkscape:label="Caption">
+     inkscape:label="Caption"
+     transform="translate(-5.0000024,-5)">
     <text
        xml:space="preserve"
        style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:4.23333px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:none;fill-opacity:0.913725;stroke:#cccccc;stroke-width:1"
diff --git a/report.org b/report.org
index 45d54d7..13b8b4d 100644
--- a/report.org
+++ b/report.org
@@ -1,4 +1,4 @@
-#+title: Further development on FTAG Finder, a pipeline to identify Tandemly Arrayed Genes
+#+title: Further development on FTAG Finder, a pipeline to identify Gene Families and Tandemly Arrayed Genes
 #+author: Samuel Ortion
 #+date: 2023-2024
 #+LATEX_CLASS: scientific-project
@@ -16,13 +16,14 @@
 | TAG  | TAG          | Tandemly Arrayed Gene              |
 | FTAG | FTAG         | Families and Tandemly Arrayed Gene |
 | WGD  | WGD          | Whole Genome Duplication           |
+| MCL  | MCL          | Markov Clustering                  |
 
 #+begin_export latex
+\makeatletter
 \hypersetup{
-	pdfauthor={Samuel Ortion},
-	pdftitle={},
 	pdfkeywords={duplicate genes, workflow management systems, pipeline},
 }
+\makeatother
 \pagenumbering{roman}
 #+end_export
 #+begin_myabstract
@@ -38,7 +39,7 @@ TODO:
 #+begin_export latex
 \tableofcontents
 \listoffigures
-\listoftables
+%\listoftables
 #+end_export
 
 [[printglossaries:]]
@@ -48,9 +49,24 @@ TODO:
 #+end_export
 
 * Context
+It is estimated that between 46% and 65.5% of human genes could be considered as duplicate genes [cite:@correaTransposableElementEnvironment2021].
+Duplicate genes offers a pool of genetic material available for further experimentation during species evolution.
+
 ** Duplication mechanisms
 #+name: fig:gene-duplication-mechanisms
-[[./figures/lallemand2020-fig1_copy.pdf]]
+#+begin_src emacs-lisp :exports results :results raw
+(cond
+  ((org-export-derived-backend-p org-export-current-backend 'html)
+   "[[./figures/lallemand2020-fig1_copy.svg]]")
+  ((org-export-derived-backend-p org-export-current-backend 'latex)
+   "[[./figures/lallemand2020-fig1_copy.pdf]]")
+  (t "[[./figures/lallemand2020-fig1_copy.svg]]"))
+#+end_src
+#+caption[Different types of duplications]: Different types of duplications. (A) Whole genome duplication. (B) An unequal crossing-over leads to a duplication of a fragment of a chromosome. (C) In tandem duplication, two (set of) genes are duplicated one after the other. (D) Retrotransposon enables retroduplication: a RNA transcript is reverse transcribed and inserted back without introns and with a polyA tail in the genome. (E) A DNA transposon can acquire a fragment of a gene. (F) Segmental duplication corresponds to long stretches of duplicated sequences with high identity. *Source* Adapted from [cite:@lallemandOverviewDuplicatedGene2020].
+#+RESULTS: fig:gene-duplication-mechanisms
+[[./figures/lallemand2020-fig1_copy.svg]]
+
+# https://stackoverflow.com/questions/13611837/how-can-i-use-different-image-formats-for-different-exports-in-org-mode
 
 Multiple mechanisms may lead to gene duplication. We review them in this section.
 
@@ -58,48 +74,51 @@ Multiple mechanisms may lead to gene duplication. We review them in this section
 *** Retroduplication
 Retrotransposons, or RNA transposons are one type of transposable elements. Retrotransposons share similar structure and mechanism with retroviruses.
 They may replicate in the genome through a mechanism known as "copy-and-paste".
-These transposons are typically composed of a reverse transcriptase gene. This enzyme gene may proceed in the reverse transcription of an mRNA transcript into DNA sequence which can then be inserted elsewhere in the genome.
-More generally, retroduplication refers to the duplication of a region in a chromosome through reverse transcription or a transcript.
+These transposons are typically composed of a reverse transcriptase gene. This enzyme may proceed in the reverse transcription of an mRNA transcript into DNA sequence which can then be inserted elsewhere in the genome.
+More generally, retroduplication refers to the duplication of a region of a chromosome through reverse transcription or a RNA transcript.
 *** Transduplication
 DNA transposons are another type of transposable element whose transposition mechanism can also lead to gene duplication.
 This type of transposable element moves in the genome through a mechanisms known as "cut-and-paste".
 A typical DNA transposon contains a transposase gene. This enzyme recognize two sites surrounding the donnor transposon sequence in the chromosome resulting in a DNA cleavage and excision of the transposon. The transposase can then insert the transposon in a new place of the genome.
 Similarly to retrotransposon, if a gene was present between the two cleavage sites of the donnor transposon, it may move with the transposed sequence.
 *** Tandem Duplication
-*** Polyploidisation
-**** Alloployploidisation
-**** Autopolyploidisation
-**** Polyploidisation mechanisms
-***** Polyspermy
-***** Non-reduced gametes
+*** Polyploidisation and Whole Genome Duplication
+In an event of whole genome duplication, the entire set of genes present on the chromosomes is duplicated.
+Whole genome duplication is more frequent in plants.
+A striking example is probably the /Triticum/ genus (wheat) in which some species (such as /T. aestivum/) are hexaploid, due to hybridisation events [cite:@golovninaMolecularPhylogenyGenus2007].
+
+We distinguish two kinds of polyploidisation, based on the origin of the duplicate genome:
+- Allopolyploidisation occurs when the supplementary chromosomes comes from an other species. This is the case for /Triticum aestivum/ hybridisation.
+- Autopolyploidisation consist in the hybridisation of the genome within the same species.
+
+Whole genome duplication can occur thanks to polyspermy or in case of a non-reduced gamete, for instance.
 *** Unequal crossing-over
 A crossing-over may occur during cell division. A fragment of chromosome is exchanged between two chromatids of a pair of chromosome. If the cleavage of the two chromatids occured at different positions on both chromosomes, the shared fragments may have different lengths. When the repair of missing fragment is performed, the resulting chromosome will incorporate a duplicate region of the chromosome, leading to a potential duplication for genes present in this region, as represented in figure [[fig:gene-duplication-mechanisms]].
-This mechanism leads to the duplication of the whole set of genes present in the inserted fragment. These genes are duplicated one after the other in second array of genes placed after the original one and are thus called Tandemly Arrayed Genes.
+This mechanism leads to the duplication of the whole set of genes present in the inserted fragment. An array of genes is duplicated after the original array and are thus called Tandemly Arrayed Genes.
 ** Role of duplicate genes in genome evolution
-In his book /Evolution by Gene Duplication/, Susumu \textsc{Ohno} proposed that gene duplication plays a major role in species evolution [cite:@ohnoEvolutionGeneDuplication1970].
+In his book /Evolution by Gene Duplication/, Susumu [[latex:textsc][Ohno]] proposed that gene duplication plays a major role in species evolution [cite:@ohnoEvolutionGeneDuplication1970].
 
 ** Methods to identify duplicate genes
-\textsc{Lallemand} et al. review the different methods used to detect duplicate genes. These methods are dependant on the type of duplicate genes they target [cite:@lallemandOverviewDuplicatedGene2020].
+[[latex:textsc][Lallemand]] et al. review the different methods used to detect duplicate genes. These methods are dependant on the type of duplicate genes they target [cite:@lallemandOverviewDuplicatedGene2020].
 
 *** FTAG Finder
-Developped in the LaMME laboratory, this pipeline targets the detection of gene family and tandemly arrayed genes from a given species' proteome [cite:@bouillonFTAGFinderOutil].
+Developped in the LaMME laboratory, this pipeline targets the detection of gene families and tandemly arrayed genes from a given species' proteome [cite:@bouillonFTAGFinderOutil].
 
 **** Estimation of homology links between genes
 This steps consists in establishing a relation between each genes in a genome.
 In this step, the typical tool involved is =BLAST= (Basic Local Alignment Search Tool) [cite:@altschulBasicLocalAlignment1990] run on the whole proteome.
 
-Several =BLAST= metrics can be used as an homology measure, such as bitscore, identity percentage, E-value or modifications of thoses. The choice of the metrics used may have an impact on the results of graph clustering step [cite:@gibbonsEvaluationBLASTbasedEdgeweighting2015].
+Several =BLAST= metrics can be used as an homology measure, such as bitscore, identity percentage, E-value or variations on those. The metrics choice may have an impact on the results of graph clustering in the following step [cite:@gibbonsEvaluationBLASTbasedEdgeweighting2015].
 **** Identification of gene families
 Based on the homology links between each pair of genes, we construct a weighted undirected graph whose vertices corresponds to genes and edges to homology links.
 Then, a graph clustering algorithm is applied on this graph in order to infer the gene families.
 
-The team choosed to propose three clustering algorithms: Single linkage, Markov Clustering or Walktrap.
-
+The team chosed to propose three clustering algorithms: Single linkage, Markov Clustering  or Walktrap.
 * Objectives
 ** Extend the existing Galaxy pipeline
-Galaxy is a web-based platform for performing accessible data analysis pipeline, mostly used for genomic data analysis [cite:@goecksGalaxyComprehensiveApproach2010].
+Galaxy is a web-based platform for performing accessible data analysis pipeline, first designed for use in genomic data analysis [cite:@goecksGalaxyComprehensiveApproach2010].
 
-Last year, Séanna \textsc{Charles}, worked on the Galaxy's version of the gls:FTAG Finder pipeline [cite:@charlesFinalisationPipelineFTAG2023] during her M1 intenship. I will continue this work.
+Last year, Séanna [[latex:textsc][Charles]], worked on the Galaxy's version of the gls:FTAG Finder pipeline during her M1 internship  [cite:@charlesFinalisationPipelineFTAG2023]. I will continue this work.
 
 ** Port FTAG Finder pipeline on a workflow manager
 Another objective of my internship will be to port FTAG Finder on a workflow manager better suited to larger and more reproducible analysis.
@@ -109,10 +128,15 @@ The two main options are Snakemake and Nextflow. Snakemake is a python powered w
 
 These tools ease the deployment of large scale data analysis workflow with reproducible output.
 
-#+begin_export latex
-\printbibliography
+#+begin_export html
+<h3>Bibliography</h3>
 #+end_export
 
+#+print_bibliography:
+
+#+begin_export latex
+\clearpage
+#+end_export
 ** Summary
 :PROPERTIES:
 :UNNUMBERED: t
@@ -120,7 +144,7 @@ These tools ease the deployment of large scale data analysis workflow with repro
 
 
 * Bean :noexport:
-
+** MCL
 MCL uses two operations on a stochastic matrix representation $M$ of the graph first derived from the adjacency matrix, namely /expansion/ and /inflation/. Expansion consists in elevating the matrix to a power $r$, and subsequently scaling its columns so that they sum to 1 again. The image of the inflation operator $\Gamma_r$ is defined as
 \[
 (\Gamma_r M)_{pq} = (M_{pq})^r / \sum_{i=1}^m (M_{iq})^r
diff --git a/report.pdf b/report.pdf
index 5cffc35..75e1105 100644
--- a/report.pdf
+++ b/report.pdf
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9779f1b25b31b9f98d5be5440943ef5f3999fd078a6e99c5eb1c379b1618da27
-size 132373
+oid sha256:b570ea851097f0ad59e4783bc83432d1218c65ceec7896453f3457cf6513c81d
+size 130136