[Bio] / Sprout / ModelSaplingLoader.pm Repository:
ViewVC logotype

Diff of /Sprout/ModelSaplingLoader.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.12, Mon Jan 24 03:52:18 2011 UTC revision 1.15, Mon Feb 28 20:27:17 2011 UTC
# Line 16  Line 16 
16  # Genomes at veronika@thefig.info or download a copy from  # Genomes at veronika@thefig.info or download a copy from
17  # http://www.theseed.org/LICENSE.TXT.  # http://www.theseed.org/LICENSE.TXT.
18  #  #
19  use FIGMODEL;  #use FIGMODEL;
20    
21  package ModelSaplingLoader;  package ModelSaplingLoader;
22      use strict;      use strict;
23      use Tracer;      use Tracer;
24      use ERDB;      use ERDB;
     use HTTP::Date;  
25      use base 'BaseSaplingLoader';      use base 'BaseSaplingLoader';
26    
27  =head1 Sapling ModelLoader Load Group Class  =head1 Sapling Model Load Group Class
28    
29  =head2 Introduction  =head2 Introduction
30    
31  The ModelLoader Load Group includes all of the major mdl tables.  The Model Load Group includes a small set of tables that describe reactions and compounds
32    and how they relate to the models in the main model database.
33    
34  =head3 new  =head3 new
35    
36      my $sl = ModelLoaderSaplingLoader->new($erdb, $options, @tables);      my $sl = ModelSaplingLoader->new($erdb, $options, @tables);
37    
38  Construct a new ModelLoaderSaplingLoader object.  Construct a new ModelSaplingLoader object.
39    
40  =over 4  =over 4
41    
# Line 59  Line 59 
59      # Get the parameters.      # Get the parameters.
60      my ($class, $erdb, $options) = @_;      my ($class, $erdb, $options) = @_;
61      # Create the table list.      # Create the table list.
62      my @tables = sort qw(StructuralCue IsFoundIn Compound HasAliasOf AliasType      my @tables = qw(Compound Reaction EcNumber Model Media IsTriggeredBy
63                           HasReactionAliasOf Reaction Involves IsTriggeredBy                      IsCategorizedInto IsConsistentWith IsModeledBy Involves
64                           RoleSet IsCombinationOf IsCategorizedInto EcNumber                      IsRequiredBy);
                          IsConsistentWith IsStimulatedBy  FeatureSet IsSetOf  
                          IsRequiredBy Model IsModeledBy ModelUser); # Encompasses);  
65      # Create the BaseSaplingLoader object.      # Create the BaseSaplingLoader object.
66      my $retVal = BaseSaplingLoader::new($class, $erdb, $options, @tables);      my $retVal = BaseSaplingLoader::new($class, $erdb, $options, @tables);
67        # Create the reaction tracking hash.
68        $retVal->{reactions} = {};
69      # Return it.      # Return it.
70      return $retVal;      return $retVal;
71  }  }
# Line 76  Line 76 
76    
77      $sl->Generate();      $sl->Generate();
78    
79  Generate the data for the mdl files.  Generate the data for the model files.
80    
81  =cut  =cut
82    
# Line 85  Line 85 
85      my ($self) = @_;      my ($self) = @_;
86      # Get the database object.      # Get the database object.
87      my $erdb = $self->db();      my $erdb = $self->db();
     # Get the source object.  
     my $fig = $self->source();  
88      # Is this the global section?      # Is this the global section?
     my $model = new FIGMODEL;  
89      if ($self->global()) {      if ($self->global()) {
90          #Loading the compound entities and relationships          # Load the tables from the model dump files.
91          $self->LoadCompounds($model);          $self->LoadModelFiles();
         #Loading the reaction, and EC number entities and relationships  
         $self->LoadReactions($model);  
92      } else {      } else {
93          # Get the section ID.          # Get the section ID.
94          my $genomeID = $self->section();          my $genomeID = $self->section();
# Line 101  Line 96 
96      }      }
97  }  }
98    
99  sub LoadCompounds {  =head3 LoadModelFiles
     my ($self,$model) = @_;  
100    
101      #First getting the compound table which has a list of all compounds in the database as well as alot of compound information      $sl->LoadModelFiles();
     my $CompoundTable = $model->database()->GetDBTable("COMPOUNDS");  
102    
103      #Adding the universal AliasType that will always exist  Load the data from the six model dump files.
     $self->PutE(AliasType => "NAME", source => "NONE");  
     $self->PutE(AliasType => "SEARCHNAME", source => "NONE");  
     $self->PutE(AliasType => "KEGG", source => "http://www.kegg.com/");  
     $self->PutE(AliasType => "ARGONNE", source => "OBSOLETE IDs");  
104    
105      #Cycling through the compound list and adding each individual compound entity  =cut
     for (my $i=0; $i < $CompoundTable->size(); $i++) {  
         my $Row = $CompoundTable->get_row($i);  
         if (defined($Row) && defined($Row->{"DATABASE"}->[0]) && $Row->{"DATABASE"}->[0] =~ m/cpd\d\d\d\d\d/) {  
             my $Object = FIGMODELObject->load($model->{"compound directory"}->[0].$Row->{"DATABASE"}->[0],"\t");  
             my @LoadingArray = ($Row->{"DATABASE"}->[0],$Row->{"DATABASE"}->[0],0,"",0,"",0,10000000,10000000,"");  
             $self->Track(compoundRow => $LoadingArray[0], 1000);  
             if (defined($Row->{"NAME"}->[0])) {  
                 $LoadingArray[1] = $Row->{"NAME"}->[0];  
             }  
             if (defined($Object->{"MASS"}->[0])) {  
                 $LoadingArray[2] = $Object->{"MASS"}->[0];  
             }  
             if (defined($Object->{"FORMULA"}->[0])) {  
                 $LoadingArray[3] = $Object->{"FORMULA"}->[0];  
             }  
             if (defined($Object->{"CHARGE"}->[0])) {  
                 $LoadingArray[4] = $Object->{"CHARGE"}->[0];  
             }  
             if (defined($Object->{"CHARGE"}->[0]) && defined($Object->{"FORMULA"}->[0])) {  
                 $LoadingArray[5] = FIGMODEL::ConvertToNeutralFormula($Object->{"FORMULA"}->[0],$Object->{"CHARGE"}->[0]);  
             }  
             if (-e $model->{"Argonne molfile directory"}->[0].$Row->{"DATABASE"}->[0].".mol" || -e $model->{"Argonne molfile directory"}->[0]."pH7/".$Row->{"DATABASE"}->[0].".mol") {  
                 $LoadingArray[6] = 1;  
             }  
             if (defined($Object->{"DELTAG"}->[0])) {  
                 $LoadingArray[7] = $Object->{"DELTAG"}->[0];  
             }  
             if (defined($Object->{"DELTAGERR"}->[0])) {  
                 $LoadingArray[8] = $Object->{"DELTAGERR"}->[0];  
             }  
             if (defined($Row->{"STRINGCODE"}->[0])) {  
                 $LoadingArray[9] = $Row->{"STRINGCODE"}->[0];  
             }  
             $self->PutE(Compound => $LoadingArray[0], label => $LoadingArray[1], mass => $LoadingArray[2], chargedFormula => $LoadingArray[3], charge => $LoadingArray[4],neutralFormula => $LoadingArray[5], hasMolfile => $LoadingArray[6], deltaG => $LoadingArray[7], deltaGerr => $LoadingArray[8], stringcode => $LoadingArray[9]);  
             #Adding the relationship between compound and structural cue  
             if (defined($Object->{"STRUCTURAL_CUES"})) {  
                 foreach my $Cue (@{$Object->{"STRUCTURAL_CUES"}}) {  
                     my @TempArray = split(/:/,$Cue);  
                     if (@TempArray == 2) {  
                         $self->PutR(IsFoundIn => $TempArray[0],$LoadingArray[0],count => $TempArray[1]);  
                     }  
                 }  
             }  
             #Adding the relationship between compound and alias type  
             if (defined($Object->{"NAME"})) {  
                 foreach my $Name (@{$Object->{"NAME"}}) {  
                     $self->PutR(HasAliasOf => $LoadingArray[0],"NAME",alias => $Name);  
                     my @SearchNames = FIGMODEL::ConvertToSearchNames($Name);  
                     foreach my $SearchName (@SearchNames) {  
                         $self->PutR(HasAliasOf => $LoadingArray[0],"SEARCHNAME",alias => $SearchName);  
                     }  
                 }  
             }  
             if (defined($Object->{"DBLINKS"})) {  
                 foreach my $Link (@{$Object->{"DBLINKS"}}) {  
                     my @TempArray = split(/:/,$Link);  
                     if (@TempArray >= 2) {  
                         if ($TempArray[0] ne "KEGG" && $TempArray[0] ne "ARGONNE") {  
                             $self->PutE(AliasType => $TempArray[0], source => "PUBLISHED MODEL");  
                         }  
                         if ($TempArray[0] eq "ARGONNE") {  
                             splice(@TempArray,1,1);  
                         }  
                         for (my $j=1; $j < @TempArray; $j++) {  
                             $self->PutR(HasAliasOf => $LoadingArray[0],$TempArray[0],alias => $TempArray[$j]);  
                         }  
                     }  
                 }  
             }  
         }  
     }  
 }  
106    
107  sub LoadReactions {  # hash of ubiquitous compounds.
108      my ($self,$model) = @_;  use constant UBIQUITOUS => {
109      #First getting the reaction table which has a list of all reactions in the database as well as alot of reaction information      cpd00002 => 'ATP',
110      my $ReactionTable = $model->database()->GetDBTable("REACTIONS");      cpd00008 => 'ADP',
111        cpd00007 => 'Oxygen',
112        cpd00010 => 'CoenzymeA',
113        cpd00012 => 'PPi',
114        cpd15560 => 'Ubiquinone-8',
115        cpd15561 => 'Ubiquinol-8',
116        cpd15500 => 'Menaquinone',
117        cpd15499 => 'Menaquinol',
118        cpd00022 => 'Acetyl-CoA',
119        cpd00018 => 'AMP',
120        cpd00971 => 'Sodium',
121        cpd15352 => '2-Demethylmenaquinone',
122        cpd15353 => '2-Demethylmenaquinol'
123    
124      #Cycling through the compound list and adding each individual compound entity  };
125      my $Count = 0;  
126      for (my $i=0; $i < $ReactionTable->size(); $i++) {  sub LoadModelFiles {
127          my $Row = $ReactionTable->get_row($i);      # Get the parameters.
128          if (defined($Row) && defined($Row->{"DATABASE"}->[0]) && $Row->{"DATABASE"}->[0] =~ m/rxn\d\d\d\d\d/) {      my ($self) = @_;
129              my $Object = FIGMODELObject->load($model->{"reaction directory"}->[0].$Row->{"DATABASE"}->[0],"\t");      # Get the model dump file directory.
130              my @LoadingArray = ($Row->{"DATABASE"}->[0],"","","","","",10000000,10000000,10000000,"R");      my $dir = $self->db()->LoadDirectory() . "/models";
131              $self->Track(reactionRow => $LoadingArray[0], 1000);      # First we read the compounds.
132              if (defined($Object->{"DEFINITION"}->[0])) {      my $ih = $self->CheckFile("$dir/CompoundName.txt", qw(CompoundID Name));
133                  $LoadingArray[1] = $Object->{"DEFINITION"}->[0];      while (! eof $ih) {
134              }          # Get the next compound.
135              if (defined($Object->{"EQUATION"}->[0])) {          my ($id, $label) = $self->ReadLine($ih);
136                  my ($Direction,$Equation,$ReverseEquation,$FullEquation,$EquationCompartment,$Error) = $model->ConvertEquationToCode($Object->{"EQUATION"}->[0],{"Test" => "Test"});          # Create a compound record for it.
137                  $LoadingArray[2] = $Equation;          $self->PutE(Compound => $id, label => $label, ubiquitous => (UBIQUITOUS->{$id} ? 1 : 0));
138              }      }
139              if (defined($Object->{"OPERATOR"}->[0])) {      # Next, the compound-reactions relationship. We create the reactions here, too.
140                  $LoadingArray[3] = $Object->{"OPERATOR"}->[0];      $ih = $self->CheckFile("$dir/CompoundReaction.txt", qw(CompoundID ReactionID
141              }                             Stoichiometry Cofactor));
142              if (defined($Object->{"PATHWAY"}->[0])) {      while (! eof $ih) {
143                  $LoadingArray[4] = join(";",@{$Object->{"PATHWAY"}});          # Get the next link.
144              }          my ($compound, $reaction, $stoich, $cofactor) = $self->ReadLine($ih);
145              if (defined($Row->{"KEGG MAPS"}->[0])) {          # Insure the reaction exists.
146                  $LoadingArray[5] = join(";",@{$Row->{"KEGG MAPS"}});          $self->CreateReaction($reaction);
147              }          # Check for product or substrate.
148              if (defined($Object->{"DELTAG"}->[0])) {          my $product;
149                  $LoadingArray[6] = $Object->{"DELTAG"}->[0];          if ($stoich < 0) {
150              }              $product = 0;
151              if (defined($Object->{"MMDELTAG"}->[0])) {              $stoich = -$stoich;
                 $LoadingArray[7] = $Object->{"MMDELTAG"}->[0];  
             }  
             if (defined($Object->{"DELTAGERR"}->[0])) {  
                 $LoadingArray[8] = $Object->{"DELTAGERR"}->[0];  
             }  
             if (defined($Object->{"THERMODYNAMIC REVERSIBILITY"}->[0])) {  
                 my $code = $Object->{"THERMODYNAMIC REVERSIBILITY"}->[0];  
                 if ($code eq '<=>') {  
                     $LoadingArray[9] = "R";  
                 } elsif ($code eq '<=') {  
                     $LoadingArray[9] = "B";  
                 } elsif ($code eq '=>') {  
                     $LoadingArray[9] = "F";  
                 }  
             }  
             $self->PutE(Reaction => $LoadingArray[0], definition => $LoadingArray[1], code => $LoadingArray[2], operator => $LoadingArray[3], pathway => $LoadingArray[4],keggMap => $LoadingArray[5], deltaG => $LoadingArray[6], MMdeltaG => $LoadingArray[7], deltaGerr => $LoadingArray[8], predictedReversibility => $LoadingArray[9]);  
             #Adding relationship between compounds and reactions  
             my ($Reactants,$Products) = $model->GetReactionSubstrateData($LoadingArray[0]);  
             if (! defined $Reactants) {  
                 $self->Add(missingReactants => 1);  
152              } else {              } else {
153                  for (my $j=0; $j < @{$Reactants}; $j++) {              $product = 1;
                     $self->PutR(Involves => $LoadingArray[0],$Reactants->[$j]->{"DATABASE"}->[0],product => 0,stoichiometry => $Reactants->[$j]->{"COEFFICIENT"}->[0],main => 1,compartment => $Reactants->[$j]->{"COMPARTMENT"}->[0],discriminator => $Count);  
                     #TODO:Properly identify main reactants in reactions  
                     $Count++;  
154                  }                  }
155            # Connect the reaction to the compound.
156            $self->PutR(Involves => $reaction, $compound, product => $product,
157                        stoichiometry => $stoich, cofactor => $cofactor);
158        }
159        # Now we connect the reactions to roles.
160        $ih = $self->CheckFile("$dir/ReactionRole.txt", qw(ReactionID Role));
161        while (! eof $ih) {
162            # Get the next reaction/role pair. We don't need to create roles here because
163            # they are built in the Feature module.
164            my ($reaction, $role) = $self->ReadLine($ih);
165            # Insure the reaction exists.
166            $self->CreateReaction($reaction);
167            # Connect the reaction to the role.
168            $self->PutR(IsTriggeredBy => $reaction, $role);
169        }
170        # Now we create the models.
171        $ih = $self->CheckFile("$dir/ModelGenome.txt", qw(ModelID GenomeID));
172        while (! eof $ih) {
173            # Get the next model.
174            my ($model, $genome) = $self->ReadLine($ih);
175            # Create the model.
176            $self->PutE(Model => $model);
177            # Connect it to the genome. Again, the genomes are created elsewhere.
178            $self->PutR(IsModeledBy => $genome, $model);
179        }
180        # Next we connect the reactions to models.
181        $ih = $self->CheckFile("$dir/ModelReaction.txt", qw(ModelID ReactionID));
182        while (! eof $ih) {
183            # Get the next line.
184            my ($model, $reaction) = $self->ReadLine($ih);
185            # Only proceed if a reaction is present.
186            if ($reaction) {
187                # Insure the reaction exists.
188                $self->CreateReaction($reaction);
189                # Connect the reaction to the model.
190                $self->PutR(IsRequiredBy => $reaction, $model);
191              }              }
             if (! defined $Products) {  
                 $self->Add(missingProducts => 1);  
             } else {  
                 for (my $j=0; $j < @{$Products}; $j++) {  
                     $self->PutR(Involves => $LoadingArray[0],$Products->[$j]->{"DATABASE"}->[0],product => 1,stoichiometry => $Products->[$j]->{"COEFFICIENT"}->[0],main => 1,compartment => $Products->[$j]->{"COMPARTMENT"}->[0],discriminator => $Count);  
                     #TODO:Properly identify main reactants in reactions  
                     $Count++;  
192                  }                  }
193              }              }
194              #Adding relationship between EC number and reactions  
195              if (defined($Object->{"ENZYME"})) {  =head3 StartFile
196                  foreach my $Enzyme (@{$Object->{"ENZYME"}}) {  
197                     if ($Enzyme =~ /,/) {      my $ih = $sl->CheckFile($fileName, @fieldNames);
198                      #TODO:Invalid enzyme  
199    Read the header record of the specified file and verify that the field names match
200    the names in the input list. If they do not, an error will be thrown; if they do, an
201    open file handle will be returned, positioned on the first data record.
202    
203    =over 4
204    
205    =item fileName
206    
207    Name for the input file. The file is in standard tab-delimited format. The first record
208    contains the field names and the remaining records contain the data.
209    
210    =item fieldNames
211    
212    List of the field names expected, in order.
213    
214    =item RETURN
215    
216    Returns the open file handle if successful. If there is a mismatch, throws an error.
217    
218    =back
219    
220    =cut
221    
222    sub CheckFile {
223        # Get the parameters.
224        my ($self, $fileName, @fieldNames) = @_;
225        # Open the file.
226        my $retVal = Open(undef, "<$fileName");
227        $self->Add(files => 1);
228        # Read in the file header.
229        my @actualFields = Tracer::GetLine($retVal);
230        # This will be set to TRUE if there's a mismatch.
231        my $error = 0;
232        for (my $i = 0; $i <= $#fieldNames; $i++) {
233            if ($fieldNames[$i] ne $actualFields[$i]) {
234                Trace("Field match error: expected $fieldNames[$i], found $actualFields[$i].") if T(0);
235                $error = 1;
236            }
237        }
238        # Was there an error?
239        if ($error) {
240            # Yes, so abort.
241            Confess("Invalid field name header in $fileName.");
242                     } else {                     } else {
243                      $Enzyme =~ s/\s//g;          # No, so trace the open.
244                      $self->PutE(EcNumber => $Enzyme, obsolete => 0, replacedby => "NONE");          Trace("Processing $fileName.") if T(ERDBLoadGroup => 2);
                     $self->PutR(IsCategorizedInto => $LoadingArray[0],$Enzyme,source => "KEGG");  
                    }  
                 }  
             }  
             #Adding the relationship between reaction and alias type  
             if (defined($Object->{"NAME"})) {  
                 foreach my $Name (@{$Object->{"NAME"}}) {  
                     $self->PutR(HasReactionAliasOf => $LoadingArray[0],"NAME",alias => $Name);  
                 }  
             }  
             if (defined($Object->{"DBLINKS"})) {  
                 foreach my $Link (@{$Object->{"DBLINKS"}}) {  
                     my @TempArray = split(/:/,$Link);  
                     if (@TempArray >= 2) {  
                         if ($TempArray[0] ne "KEGG" && $TempArray[0] ne "ARGONNE") {  
                             $self->PutE(AliasType => $TempArray[0], source => "PUBLISHED MODEL");  
                         }  
                         if ($TempArray[0] eq "ARGONNE") {  
                             splice(@TempArray,1,1);  
                         }  
                         for (my $j=1; $j < @TempArray; $j++) {  
                             $self->PutR(HasReactionAliasOf => $LoadingArray[0],$TempArray[0],alias => $TempArray[$j]);  
                         }  
                     }  
                 }  
             }  
245          }          }
246        # Return the file handle.
247        return $retVal;
248      }      }
249    
250    =head3 ReadLine
251    
252        my @fields = $sl->ReadLine($ih);
253    
254    Read a line of data from an input file.
255    
256    =over 4
257    
258    =item ih
259    
260    Open file handle for the input file.
261    
262    =item RETURN
263    
264    Returns a list of the field values for the next record in the file.
265    
266    =back
267    
268    =cut
269    
270    sub ReadLine {
271        # Get the parameters.
272        my ($self, $ih) = @_;
273        # Read the line.
274        my @retVal = Tracer::GetLine($ih);
275        # Count this record.
276        $self->Track(records => $retVal[0], 1000);
277        # Return the data.
278        return @retVal;
279  }  }
280    
281    
282  sub FixDate {  =head3 CheckReaction
283      my ($date) = @_;  
284      my $retVal = ($date eq 'NA' ? 0 : $date);      $sl->CheckReaction($reaction);
285      return $retVal;  
286    Insure we have created a rectord for the specified reaction.
287    
288    =over 4
289    
290    =item reaction
291    
292    ID of the reaction in question.
293    
294    =back
295    
296    =cut
297    
298    sub CreateReaction {
299        # Get the parameters.
300        my ($self, $reaction) = @_;
301        # Get the reaction hash.
302        my $reactionH = $self->{reactions};
303        # See if this reaction is new.
304        if (! $reactionH->{$reaction}) {
305            # It is, so create it.
306            $self->PutE(Reaction => $reaction);
307            # Insure we don't create it again.
308            $reactionH->{$reaction} = 1;
309        }
310  }  }
311    
312  1;  1;

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.15

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3