add discussion file

[chloroplast13.git] / annotated.tex

diff --git a/annotated.tex b/annotated.tex
index 819cc33ba537a959ec6d35317e2a90a058dfcfe8..46619ab9a42a64153ccd0cd2133a800e3363d40c 100644 (file)
--- a/annotated.tex
+++ b/annotated.tex
@@ -47,11 +47,11 @@ that stores annotated and/or unannotated chloroplast genomes.  We have
 considered the GenBank-NCBI \cite{Sayers01012011} database as sequence
 database:  99~genomes of chloroplasts  were retrieved.   These genomes
 lie in  the eleven type  of chloroplast families and  Table \ref{Tab2}
 considered the GenBank-NCBI \cite{Sayers01012011} database as sequence
 database:  99~genomes of chloroplasts  were retrieved.   These genomes
 lie in  the eleven type  of chloroplast families and  Table \ref{Tab2}

-summarizes their distribution in our dataset.\\
+summarizes their distribution in our dataset.

 
 \begin{figure}[h]  
   \centering
 
 \begin{figure}[h]  
   \centering

-    \includegraphics[width=0.8\textwidth]{generalView}
+    \includegraphics[width=0.75\textwidth]{generalView}

 \caption{A general overview of the annotation-based approach}\label{Fig1}
 \end{figure}
 
 \caption{A general overview of the annotation-based approach}\label{Fig1}
 \end{figure}
 


@@ -190,9 +190,9 @@ to extract core genes, as explained in Algorithm \ref{Alg3:thirdM}.
 \STATE $geneList=\text{empty list}$
 \STATE $common=set(dir(NCBI\_Genes)) \cap set(dir(Dogma\_Genes))$
 \FOR{$\text{gene in common}$}
 \STATE $geneList=\text{empty list}$
 \STATE $common=set(dir(NCBI\_Genes)) \cap set(dir(Dogma\_Genes))$
 \FOR{$\text{gene in common}$}

-       \STATE $gen1 \leftarrow open(NCBI\_Genes(gene)).read()$         
-       \STATE $gen2 \leftarrow open(Dogma\_Genes(gene)).read()$
-       \STATE $score \leftarrow geneChk(gen1,gen2)$
+       \STATE $g1 \leftarrow open(NCBI\_Genes(gene)).read()$   
+       \STATE $g2 \leftarrow open(Dogma\_Genes(gene)).read()$
+       \STATE $score \leftarrow geneChk(g1,g2)$

        \IF {$score > Threshold$}
                \STATE $geneList \leftarrow gene$
        \ENDIF 
        \IF {$score > Threshold$}
                \STATE $geneList \leftarrow gene$
        \ENDIF 


@@ -210,18 +210,16 @@ geneChk subroutine.
 \caption{Find the Maximum Similarity Score between two sequences}
 \label{Alg3:genechk}
 \begin{algorithmic} 
 \caption{Find the Maximum Similarity Score between two sequences}
 \label{Alg3:genechk}
 \begin{algorithmic} 

-\REQUIRE $gen1,gen2 \leftarrow \text{NCBI gene sequence, Dogma gene sequence}$
+\REQUIRE $g1,g2 \leftarrow \text{NCBI gene sequence, Dogma gene sequence}$

 \ENSURE $\text{Maximum similarity score}$
 \ENSURE $\text{Maximum similarity score}$

-\STATE $Score1 \leftarrow needle(gen1,gen2)$
-\STATE $Score2 \leftarrow needle(gen1,Reverse(gen2))$
-\STATE $Score3 \leftarrow needle(gen1,Complement(gen2))$
-\STATE $Score4 \leftarrow needle(gen1,Reverse(Complement(gen2)))$
-\RETURN $max(Score1, Score2, Score3, Score4)$
+\STATE $score1 \leftarrow needle(g1,g2)$
+\STATE $score2 \leftarrow needle(g1,Reverse(g2))$
+\STATE $score3 \leftarrow needle(g1,Complement(g2))$
+\STATE $score4 \leftarrow needle(g1,Reverse(Complement(g2)))$
+\RETURN $max(score1,score2,score3,score4)$

 \end{algorithmic}
 \end{algorithm}  
 
 \end{algorithmic}
 \end{algorithm}  
 

-% THIS SUBSECTION MUST BE IMPROVED 
-

 \subsubsection{Intersection Core Matrix (\textit{ICM})}
 
 To extract  core genes, we  iteratively collect the maximum  number of
 \subsubsection{Intersection Core Matrix (\textit{ICM})}
 
 To extract  core genes, we  iteratively collect the maximum  number of


@@ -266,8 +264,8 @@ core genes with its two genomes parents.
 \caption{Extract Maximum Intersection Score}
 \label{Alg1:ICM}
 \begin{algorithmic} 
 \caption{Extract Maximum Intersection Score}
 \label{Alg1:ICM}
 \begin{algorithmic} 

-\REQUIRE $L \leftarrow \text{genomes vectors}$
-\ENSURE $B1 \leftarrow Max Core Vector$ 
+\REQUIRE $L \leftarrow \text{genomes sets}$
+\ENSURE $B1 \leftarrow \text{Max Core set}$ 

 \FOR{$i \leftarrow 0:len(L)-1$}
         \STATE $score \leftarrow 0$
        \STATE $core1 \leftarrow set(GenomeList[L[i]])$
 \FOR{$i \leftarrow 0:len(L)-1$}
         \STATE $score \leftarrow 0$
        \STATE $core1 \leftarrow set(GenomeList[L[i]])$


@@ -297,7 +295,7 @@ names\_Accession number)}, while an edge is labeled with the number of
 lost  genes from  a leaf  genome or  an intermediate  core  gene. Such
 numbers are  very interesting because  they give an  information about
 the evolution:  how many genes  were lost between two  species whether
 lost  genes from  a leaf  genome or  an intermediate  core  gene. Such
 numbers are  very interesting because  they give an  information about
 the evolution:  how many genes  were lost between two  species whether

-they  belong  to  the  same  familie  or not.   By  the  principle  of
+they  belong  to  the  same  family  or not.   By  the  principle  of

 classification, a  small number of genes lost  among species indicates
 that those species are close to  each other and belong to same family,
 while a  large lost  means that we  have an  evolutionary relationship
 classification, a  small number of genes lost  among species indicates
 that those species are close to  each other and belong to same family,
 while a  large lost  means that we  have an  evolutionary relationship


@@ -321,7 +319,7 @@ to align these sequences with each others.
 \end{enumerate} 
 
 \begin{figure}[H]
 \end{enumerate} 
 
 \begin{figure}[H]

-  \centering \includegraphics[width=0.8\textwidth]{Whole_system}
+  \centering \includegraphics[width=0.75\textwidth]{Whole_system}

   \caption{Overview of the pipeline}\label{wholesystem}
 \end{figure}
 
   \caption{Overview of the pipeline}\label{wholesystem}
 \end{figure}