ReadStructures

 [run_structures,maxgen,nruns] = ReadStructures(namefile,n)
 ReadStructures:  Reads all structures stored in the file 'namefile' which correspond to 
                  structures of the probabilistic models learned in nruns of an EDA with
                  a maximum of maxgen generations.
 INPUTS
 namefile: file that contains the structures
           The file contains two columns of numerical values
           where negative values -g -r  mean that the precedent positive
           values were the edges learned at generation g or run r.
           (In the file, vertices are numbered from 0 to n-1)
           EXAMPLE: 
             2 0 
             8 0 
             14 3 
             -1 -1
             13 8 
             0 10 
             3 5
             9 10 
            -1 -2
          The structure learned at run 1, generation 1 contains edges
          (3,1), (9,1) and (15,4).  The structure learned at run 2,
          generation 1 contains edges  (14,9), (1,11), (4,6) and (10,11).
 n: Number of variables
 mangen: maximum number of generations
 nruns: number of runs of the algorithm
 OUTPUTS
 run_structures{1} = indexmatrix(n,n): Associates an index to each possible edge in the network.
 e.g. indexmatrix(1,2) = 1, number of edges m = n*(n+1)/2;
 run_structures{2} = AllBigMatrices{nruns}(m,maxgen}: For each run contains whether the edge i appeared in generation j
 run_structures{3} = AllSumMatrices(m,maxgen): = \sum_i^nruns AllBigMatrices{i},
 i.e. the number of runs that each edge i appeared in generation j 
 run_structures{4} = AllContactMatrix{maxgen}(n,n): The number of runs in which edge i,j
 was present in generation k.
 run_structures{5} = SumAllContactMatrix(n,n): = \sum_k^maxgen AllContactMatrix{k}. 
 i.e. Total number of times edge i,j was present in all the structures
 learned in all generations of all runs.
 EXAMPLE
[] = ReadStructures('ProteinStructsExR.txt',20,43,50)

 Last version 8/26/2008. Roberto Santana (roberto.santana@ehu.es)

0001 function[run_structures,maxgen,nruns] = ReadStructures(namefile,n)
0002 % [run_structures,maxgen,nruns] = ReadStructures(namefile,n)
0003 % ReadStructures:  Reads all structures stored in the file 'namefile' which correspond to
0004 %                  structures of the probabilistic models learned in nruns of an EDA with
0005 %                  a maximum of maxgen generations.
0006 % INPUTS
0007 % namefile: file that contains the structures
0008 %           The file contains two columns of numerical values
0009 %           where negative values -g -r  mean that the precedent positive
0010 %           values were the edges learned at generation g or run r.
0011 %           (In the file, vertices are numbered from 0 to n-1)
0012 %           EXAMPLE:
0013 %             2 0
0014 %             8 0
0015 %             14 3
0016 %             -1 -1
0017 %             13 8
0018 %             0 10
0019 %             3 5
0020 %             9 10
0021 %            -1 -2
0022 %          The structure learned at run 1, generation 1 contains edges
0023 %          (3,1), (9,1) and (15,4).  The structure learned at run 2,
0024 %          generation 1 contains edges  (14,9), (1,11), (4,6) and (10,11).
0025 % n: Number of variables
0026 % mangen: maximum number of generations
0027 % nruns: number of runs of the algorithm
0028 % OUTPUTS
0029 % run_structures{1} = indexmatrix(n,n): Associates an index to each possible edge in the network.
0030 % e.g. indexmatrix(1,2) = 1, number of edges m = n*(n+1)/2;
0031 % run_structures{2} = AllBigMatrices{nruns}(m,maxgen}: For each run contains whether the edge i appeared in generation j
0032 % run_structures{3} = AllSumMatrices(m,maxgen): = \sum_i^nruns AllBigMatrices{i},
0033 % i.e. the number of runs that each edge i appeared in generation j
0034 % run_structures{4} = AllContactMatrix{maxgen}(n,n): The number of runs in which edge i,j
0035 % was present in generation k.
0036 % run_structures{5} = SumAllContactMatrix(n,n): = \sum_k^maxgen AllContactMatrix{k}.
0037 % i.e. Total number of times edge i,j was present in all the structures
0038 % learned in all generations of all runs.
0039 % EXAMPLE
0040 %[] = ReadStructures('ProteinStructsExR.txt',20,43,50)
0041 %
0042 % Last version 8/26/2008. Roberto Santana (roberto.santana@ehu.es)
0043 
0044 
0045 
0046 [m,indexmatrix] = Find_indexmatrix(n);
0047 
0048 AuxFile = load (namefile);  % The file is read
0049 Cycle = size(AuxFile,1);  % Its length is calculated
0050 
0051 nruns = -1*min(AuxFile(:,1));
0052 maxgen = -1*min(AuxFile(:,2));
0053 
0054 
0055 a = 1;
0056 
0057  for i=1:Cycle,
0058   if(AuxFile(i,1)<0)
0059     run = -1*AuxFile(i,1);
0060     gen = -1*AuxFile(i,2);   
0061     AllStruct{run,gen} = AuxStruct;
0062     a = 1;
0063     AuxStruct = [];    
0064   else
0065     AuxStruct(a,:) = AuxFile(i,:);
0066     a = a+1;
0067   end 
0068 end
0069 
0070 % The matrices containing the occurrence of edges at each generation are constructed
0071 AllSumMatrices = zeros(m,maxgen);
0072  
0073  for j=1:maxgen  
0074   AllContactMatrix{j}= zeros(n,n);
0075  end
0076  
0077 for i=1:nruns,
0078  BigMatrix = zeros(m,maxgen);
0079   for j=1:size(AllStruct,2)  
0080      if ~isempty(AllStruct{i,j})
0081      edges = AllStruct{i,j};
0082      for k=1:size(edges,1),
0083       AllContactMatrix{j}(edges(k,1)+1,edges(k,2)+1) =  AllContactMatrix{j}(edges(k,1)+1,edges(k,2)+1) + 1;
0084       AllContactMatrix{j}(edges(k,2)+1,edges(k,1)+1) =  AllContactMatrix{j}(edges(k,2)+1,edges(k,1)+1) + 1;
0085       edgeindex = indexmatrix(edges(k,1)+1,edges(k,2)+1);
0086       BigMatrix(edgeindex,j) = 1;       
0087      end
0088    end
0089   end
0090   AllBigMatrices{i} = BigMatrix;
0091   AllSumMatrices = AllSumMatrices + BigMatrix;
0092 end
0093 
0094 SumAllContactMatrix = zeros(n,n);
0095 for j=1:maxgen  
0096   SumAllContactMatrix  =  SumAllContactMatrix  + AllContactMatrix{j};
0097 end
0098 
0099 run_structures{1} = indexmatrix;
0100 run_structures{2} = AllBigMatrices;
0101 run_structures{3} = AllSumMatrices;
0102 run_structures{4} = AllContactMatrix;
0103 run_structures{5} = SumAllContactMatrix;
0104 
0105 
0106 
0107