still on update section 4

[chloroplast13.git] / annotated.tex

diff --git a/annotated.tex b/annotated.tex
index c9e00bd2a9dbe5831c00020b3d590b92e590271c..fb04c9bca230c989814da9b3e311a212e1d4b93a 100644 (file)
--- a/annotated.tex
+++ b/annotated.tex
@@ -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


@@ -240,36 +238,25 @@ score_{ij}=\vert g_i \cap g_j\vert
 \label{Eq1}
 \end{equation}
 \noindent where $1 \leq i \leq n$, $1 \leq j \leq n$, and $g_i, g_j$ are 
 \label{Eq1}
 \end{equation}
 \noindent where $1 \leq i \leq n$, $1 \leq j \leq n$, and $g_i, g_j$ are 

-genomes. The  generation of a new  core gene depends obviously on the
-value of intersection scores $score_{ij}$:
-
-% TO BE CONTINUED
-
-$$
-\text{new Core} = 
-\begin{cases}
-\text{Ignored} & \text{if $\textit{score}=0$;} \\
-\text{new Core id} & \text{if $\textit{Score}>0$.}
-\end{cases}
-$$
-
-if     $\textit{Score}=0$     then     we    have     \textit{disjoint
-relation} \emph{i.e.},  no common genes between two  genomes.  In this
-case  the  system  ignores  the   genome  that  annul  the  core  gene
-size. Otherwise, The system removes these two genomes from ICM and add
-new  core  genome  with a  \textit{coreID}  of  them  to ICM  for  the
-calculation in  next iteration. This  process reduces the size  of ICM
-and repeats until all genomes  are treated \emph{i.e.} ICM has no more
-genomes.  We observe  that ICM is very large because  of the amount of
-data that it stores. This results  to be time and memory consuming for
-calculating  the  intersection  scores.   To  increase  the  speed  of
-calculations, it  is sufficient to  only calculate the  upper triangle
-scores. The time complexity for this process after enhancement is thus
-$O(\frac{n.(n-1)}{2})$.   Algorithm   \ref{Alg1:ICM}  illustrates  the
-construction of  the ICM matrix and  the extraction of  the core genes
-where \textit{GenomeList},  represents the database  where all genomes
-data are stored. At each iteration, it computes the maximum core genes
-with its two genomes parents.
+genomes. The  generation of a new  core gene depends  obviously on the
+value  of the  intersection scores  $score_{ij}$. More  precisely, the
+idea is  to consider a  pair of genomes  such that their score  is the
+largest element in ICM. These two genomes are then removed from matrix
+and the  resulting new  core genome is  added for the  next iteration.
+The ICM is then updated to take into account the new core gene: new IS
+values are computed for it. This process is repeated until no new core
+gene can be obtained.
+
+We  can observe  that  the ICM  is very  large  due to  the amount  of
+data. As a consequence, the  computation of the intersection scores is
+both  time and  memory consuming.  However,  since ICM  is a  symetric
+matrix we can reduce the  computation overhead by considering only its
+triangular  upper part.  The  time complexity  for this  process after
+enhancement is thus $O(\frac{n.(n-1)}{2})$.  Algorithm ~\ref{Alg1:ICM}
+illustrates the construction  of the ICM matrix and  the extraction of
+the  core  genes, where  \textit{GenomeList}  represents the  database
+storing all genomes  data. At each iteration, it  computes the maximum
+core genes with its two genomes parents.

 
 % ALGORITHM HAS BEEN REWRITTEN
 
 
 % ALGORITHM HAS BEEN REWRITTEN
 


@@ -277,8 +264,8 @@ 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 $core1 \leftarrow set(GenomeList[L[i]])$


@@ -300,15 +287,15 @@ with its two genomes parents.
 \subsection{Features visualization}
 
 The goal is to visualize results  by building a tree of evolution. All
 \subsection{Features visualization}
 
 The goal is to visualize results  by building a tree of evolution. All

-core  genes generated  represent  important information  in the  tree,
-because they  provide information about  the ancestors of two  or more
+core  genes generated  represent  an important information  in the  tree,
+because they  provide ancestor information of two  or more

 genomes. Each  node in the  tree represents one chloroplast  genome or
 genomes. Each  node in the  tree represents one chloroplast  genome or

-one predicted core called \textit{(Genes count:Family name\_Scientific
-names\_Accession number)}, while an edge is labeled with the number of
+one predicted core and labelled as \textit{(Genes count:Family name\_Scientific
+names\_Accession number)}. While an edge is labelled 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


@@ -328,6 +315,7 @@ The procedure used to built a phylogenetic tree is as follows:
 \item For each gene in a core gene, extract its sequence and store it in the database.
 \item Use multiple alignment tools such as (****to be write after see christophe****) 
 to align these sequences with each others.
 \item For each gene in a core gene, extract its sequence and store it in the database.
 \item Use multiple alignment tools such as (****to be write after see christophe****) 
 to align these sequences with each others.

+\item we use an outer-group genome from cyanobacteria to calculate distances.

 \item Submit the resulting aligned sequences to RAxML program to compute the distances and finally draw the phylogenetic tree.
 \end{enumerate} 
 
 \item Submit the resulting aligned sequences to RAxML program to compute the distances and finally draw the phylogenetic tree.
 \end{enumerate} 
 


@@ -337,7 +325,47 @@ to align these sequences with each others.
 \end{figure}
 
 \section{Implementation}
 \end{figure}
 
 \section{Implementation}

-We implemented four algorithms to extract maximum core genes from large amount of chloroplast genomes. Two algorithms used to extract core genes based on NCBI annotation, and the others based on dogma annotation tool. Evolutionary tree generated as a result from each method implementation. In this section, we will present the four methods, and how they can extract maximum core genes?, and how the developed code will generate the evolutionary tree.
+We implemented the three algorithms to extract maximum core genes from large amount of chloroplast genomes. Table \ref{Etime}, show the annotation, execution time, and the number of core genes for each method:
+
+\begin{center}
+\begin{tiny}
+\begin{table}[H]
+\caption{Annotation, Execution Time, and core genes for each methodology. Annotation means the type of annotation algorithm used to annotate chloroplast genome, Features means the gene features which it is in two types: either gene name, gene sequence, or using the both. The execution time is represented in minute. The number of core genes in the super core is represented with NCBI and DOGMA. Bad genomes: are the number of genomes that can destroy core genes by low number of gene intersection}\label{Etime}
+\begin{tabular}{ccccccccccc}
+\hline\hline
+ & \multicolumn{2}{c}{Annotation} & \multicolumn{2}{c}{Features} & \multicolumn{2}{c}{Exec Time} & \multicolumn{2}{c}{Core genes} & \multicolumn{2}{c}{Bad genomes} \\
+~ & NCBI & DOGMA & Name & Seq & NCBI & DOGMA & NCBI & DOGMA & NCBI & \multicolumn{1}{c}{DOGMA} \\
+\hline
+Gene prediction & $\surd$ & - & - & $\surd$ & ? & - & ? & - & 0 & -\\
+Gene Features & $\surd$ & $\surd$ & $\surd$ & - & 4.98 & 1.52 & 28 & 10 & 1 & 0\\
+Gene Quality & $\surd$ & $\surd$ & $\surd$ & $\surd$ & \multicolumn{2}{c}{1.29} & \multicolumn{2}{c}{4} & \multicolumn{2}{c}{1}
+
+\end{tabular}
+\end{table}
+\end{tiny}
+\end{center} 
+
+
+The second important factor is the amount of memory usage in each methodology. Table \ref{mem} show the amounts of memory consumption by each method.
+
+\begin{center}
+\begin{tiny}
+\begin{table}[H]
+\caption{Annotation, Execution Time, and core genes for each methodology. Annotation means the type of annotation algorithm used to annotate chloroplast genome, Features means the gene features which it is in two types: either gene name, gene sequence, or using the both. The execution time is represented in minute. The number of core genes in the super core is represented with NCBI and DOGMA. Bad genomes: are the number of genomes that can destroy core genes by low number of gene intersection}\label{Etime}
+\begin{tabular}{cccccccc}
+\hline\hline
+& & Load Genomes & T. genevision & Read genevision & ICM & Draw tree & Core Seq. \\
+\hline
+Gene prediction & ~ & ~ & ~ & ~ & ~ & ~ & ~\\
+\multirow{2}{*}{Gene Features} & NCBI & 15.4 & 18.9 & 17.5 & 18 & 18 & 28.1\\
+              & DOGMA& 15.3 & 15.3 & 16.8 & 17.8 & 17.9 & 31.2\\
+Gene Quality  & ~    & 15.3 & >134 & 16.1 & 17 & 17.1 & 24.4 
+\end{tabular}
+\end{table}
+\end{tiny}
+\end{center}  
+
+one algorithm used to extract core genes based on NCBI annotation, and the others based on NCBI and DOGMA annotation tool. Evolutionary tree generated as a result from each method implementation. 

 
 \subsection{Extract Core Genes based on Gene Contents}
 
 
 \subsection{Extract Core Genes based on Gene Contents}
 


@@ -364,10 +392,8 @@ extracting core genes based on genes names and counts summarized in the followin
 \item Analysing genomes to store lists of code genes names (\textit{i.e. exons}). solve gene fragments is done by using first method in solve gene fragments. The output from annotation process with dogma is genomes files in GenVision file format. Sets of genes were stored in the database.
 \item Generate ICM matrix to calculate maximum core genes.
 \item Draw the evolutionary tree by extracted all genes sequences from each core. Then applying multiple alignment process on the sequences to calculate the distance among cores to draw a phylogenetic tree.
 \item Analysing genomes to store lists of code genes names (\textit{i.e. exons}). solve gene fragments is done by using first method in solve gene fragments. The output from annotation process with dogma is genomes files in GenVision file format. Sets of genes were stored in the database.
 \item Generate ICM matrix to calculate maximum core genes.
 \item Draw the evolutionary tree by extracted all genes sequences from each core. Then applying multiple alignment process on the sequences to calculate the distance among cores to draw a phylogenetic tree.

-

 \end{enumerate}
 
 \end{enumerate}
 

-

 The main drawback from the method of extracting core genes based on gene names and counts is that we can not depending only on genes names because of three causes: first, the genome may have not totally named (This can be found in early versions of NCBI genomes), so we will have some lost sequences. Second, we may have two genes sharing the same name, while their sequences are different. Third, we need to annotate all the genomes.               
 
 \subsection{Extract Core Genes based on Gene Quality Control}
 The main drawback from the method of extracting core genes based on gene names and counts is that we can not depending only on genes names because of three causes: first, the genome may have not totally named (This can be found in early versions of NCBI genomes), so we will have some lost sequences. Second, we may have two genes sharing the same name, while their sequences are different. Third, we need to annotate all the genomes.               
 
 \subsection{Extract Core Genes based on Gene Quality Control}