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

Diff of /Sprout/Sprout.pm

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

revision 1.12, Wed May 4 03:24:43 2005 UTC revision 1.47, Thu Oct 20 12:02:43 2005 UTC
# Line 70  Line 70 
70    
71  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72    
73    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74    
75  =back  =back
76    
77  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
# Line 86  Line 88 
88          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
89          # the incoming data.          # the incoming data.
90          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
91                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
92                                             dataDir              => 'Data',                      # data file directory                                                          # database type
93                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
94                                             userData             => 'root/',                     # user name and password                                                          # data file directory
95                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
96                                                            # database definition file name
97                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98                                                            # user name and password
99                           port         => $FIG_Config::dbport,
100                                                            # database connection port
101                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
102                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
103                           noDBOpen     => 0,               # 1 to suppress the database open
104                                            }, $options);                                            }, $options);
105          # Get the data directory.          # Get the data directory.
106          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 108 
108          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
110          # Connect to the database.          # Connect to the database.
111          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
112        if (! $optionTable->{noDBOpen}) {
113            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114                                    $password, $optionTable->{port});
115        }
116          # Create the ERDB object.          # Create the ERDB object.
117          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
118          my $erdb = ERDB->new($dbh, $xmlFileName);          my $erdb = ERDB->new($dbh, $xmlFileName);
# Line 377  Line 389 
389    
390  =head3 LoadUpdate  =head3 LoadUpdate
391    
392  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
393    
394  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
395  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 420  Line 432 
432          # Loop through the incoming table names.          # Loop through the incoming table names.
433          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
434                  # Find the table's file.                  # Find the table's file.
435                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436                  if (! -e $fileName) {          if (! $fileName) {
437                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438                  }          } else {
439                  # Attempt to load this table.                  # Attempt to load this table.
440                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
442                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
443          }          }
444        }
445          # Return the statistics.          # Return the statistics.
446          return $retVal;          return $retVal;
447  }  }
# Line 570  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 597  Line 610 
610                  if ($prevContig eq $contigID && $dir eq $prevDir) {                  if ($prevContig eq $contigID && $dir eq $prevDir) {
611                          # Here the new segment is in the same direction on the same contig. Insure the                          # Here the new segment is in the same direction on the same contig. Insure the
612                          # new segment's beginning is next to the old segment's end.                          # new segment's beginning is next to the old segment's end.
613                          if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
614                                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
615                                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
616                                  # to include both segments.                  $len += $prevLen;
617                    # Pop the old segment off. The new one will replace it later.
618                    pop @retVal;
619                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
620                    # Here we need to merge two forward blocks. Adjust the beginning and
621                    # length values to include both segments.
622                                  $beg = $prevBeg;                                  $beg = $prevBeg;
623                                  $len += $prevLen;                                  $len += $prevLen;
624                                  # Pop the old segment off. The new one will replace it later.                                  # Pop the old segment off. The new one will replace it later.
# Line 609  Line 627 
627                  }                  }
628                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
629                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
630            # Compute the initial base pair.
631            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
632                  # Add the specifier to the list.                  # Add the specifier to the list.
633                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
634          }          }
635          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
636          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
637  }  }
638    
639  =head3 ParseLocation  =head3 ParseLocation
# Line 644  Line 664 
664      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
665          my ($location) = @_;          my ($location) = @_;
666          # Parse it into segments.          # Parse it into segments.
667          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
668          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
669          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
670          if ($dir eq "_") {          if ($dir eq "_") {
# Line 752  Line 772 
772                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
773                  # before putting it in the return value.                  # before putting it in the return value.
774                  my ($start, $stop);                  my ($start, $stop);
775            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
776                  if ($dir eq "+") {                  if ($dir eq "+") {
777                          $start = $beg;                          $start = $beg;
778                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
779                  } else {                  } else {
780                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
781                          $stop = $beg;                          $stop = $beg;
782                  }                  }
783            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
784                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
785                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
786                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 792 
792                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
793                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
794                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
795                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
796                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
797                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
798                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
799                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
800                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
801                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
802                  }                  }
803                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
804                  if ($dir eq '+') {                  if ($dir eq '+') {
805                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
806                  } else {                  } else {
807                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
808                  }                  }
809          }          }
810          # Return the result.          # Return the result.
# Line 851  Line 874 
874          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
875          if ($sequence) {          if ($sequence) {
876                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
877                  $retVal = $start + $len;          $retVal = $start + $len - 1;
878        }
879        # Return the result.
880        return $retVal;
881    }
882    
883    =head3 ClusterPEGs
884    
885    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
886    
887    Cluster the PEGs in a list according to the cluster coding scheme of the specified
888    subsystem. In order for this to work properly, the subsystem object must have
889    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
890    This causes the cluster numbers to be pulled into the subsystem's color hash.
891    If a PEG is not found in the color hash, it will not appear in the output
892    sequence.
893    
894    =over 4
895    
896    =item sub
897    
898    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
899    method.
900    
901    =item pegs
902    
903    Reference to the list of PEGs to be clustered.
904    
905    =item RETURN
906    
907    Returns a list of the PEGs, grouped into smaller lists by cluster number.
908    
909    =back
910    
911    =cut
912    #: Return Type $@@;
913    sub ClusterPEGs {
914        # Get the parameters.
915        my ($self, $sub, $pegs) = @_;
916        # Declare the return variable.
917        my $retVal = [];
918        # Loop through the PEGs, creating arrays for each cluster.
919        for my $pegID (@{$pegs}) {
920            my $clusterNumber = $sub->get_cluster_number($pegID);
921            # Only proceed if the PEG is in a cluster.
922            if ($clusterNumber >= 0) {
923                # Push this PEG onto the sub-list for the specified cluster number.
924                push @{$retVal->[$clusterNumber]}, $pegID;
925            }
926          }          }
927          # Return the result.          # Return the result.
928          return $retVal;          return $retVal;
# Line 1001  Line 1072 
1072    
1073  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1074    
1075  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1076    
1077  Return the annotations of a feature.  Return the annotations of a feature.
1078    
# Line 1011  Line 1082 
1082    
1083  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1084    
1085    =item rawFlag
1086    
1087    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1088    will be returned in human-readable form.
1089    
1090  =item RETURN  =item RETURN
1091    
1092  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1093    
1094  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1095    
1096  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1097    
1098  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1099    
# Line 1029  Line 1105 
1105  #: Return Type @%;  #: Return Type @%;
1106  sub FeatureAnnotations {  sub FeatureAnnotations {
1107          # Get the parameters.          # Get the parameters.
1108          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1109          # Create a query to get the feature's annotations and the associated users.          # Create a query to get the feature's annotations and the associated users.
1110          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1111                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1118 
1118                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1119                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1120                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1121            # Convert the time, if necessary.
1122            if (! $rawFlag) {
1123                $timeStamp = FriendlyTimestamp($timeStamp);
1124            }
1125                  # Assemble them into a hash.                  # Assemble them into a hash.
1126          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1127                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1128                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1129                  # Add it to the return list.                  # Add it to the return list.
1130                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1073  Line 1153 
1153    
1154  =item RETURN  =item RETURN
1155    
1156  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1157    
1158  =back  =back
1159    
# Line 1083  Line 1163 
1163          # Get the parameters.          # Get the parameters.
1164          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1165          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1166      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1167                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1168                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1169                                               'MadeAnnotation(from-link)']);
1170          # Declare the return hash.          # Declare the return hash.
1171          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1172      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1173      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1174          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1175      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1176          # Get the annotation fields.          # Get the annotation fields.
1177          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1178                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1179                  my ($user, $function) = _ParseAssignment($text);          my ($type, $function) = _ParseAssignment($text);
1180          if ($user && ! exists $timeHash{$user}) {          if ($type && ! exists $retVal{$user}) {
1181              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1182              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1183              # return hash.              # return hash.
1184                          $retVal{$function} = $user;              $retVal{$user} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1185                  }                  }
1186          }          }
1187          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1120  Line 1197 
1197  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1198  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1199  assignment is a type of annotation. The format of an assignment is described in  assignment is a type of annotation. The format of an assignment is described in
1200  L</ParseLocation>. Its worth noting that we cannot filter on the content of the  L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1201  annotation itself because it's a text field; however, this is not a big problem because  annotation itself because it's a text field; however, this is not a big problem because
1202  most features only have a small number of annotations.  most features only have a small number of annotations.
1203    
# Line 1211  Line 1288 
1288          return $retVal;          return $retVal;
1289  }  }
1290    
1291    =head3 FunctionsOf
1292    
1293    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1294    
1295    Return the functional assignments of a particular feature.
1296    
1297    The functional assignment is handled differently depending on the type of feature. If
1298    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1299    assignment is a type of annotation. The format of an assignment is described in
1300    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1301    annotation itself because it's a text field; however, this is not a big problem because
1302    most features only have a small number of annotations.
1303    
1304    If the feature is B<not> identified by a FIG ID, then the functional assignment
1305    information is taken from the B<ExternalAliasFunc> table. If the table does
1306    not contain an entry for the feature, an empty list is returned.
1307    
1308    =over 4
1309    
1310    =item featureID
1311    
1312    ID of the feature whose functional assignments are desired.
1313    
1314    =item RETURN
1315    
1316    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1317    that user.
1318    
1319    =back
1320    
1321    =cut
1322    #: Return Type @@;
1323    sub FunctionsOf {
1324        # Get the parameters.
1325        my ($self, $featureID) = @_;
1326        # Declare the return value.
1327        my @retVal = ();
1328        # Determine the ID type.
1329        if ($featureID =~ m/^fig\|/) {
1330            # Here we have a FIG feature ID. We must build the list of trusted
1331            # users.
1332            my %trusteeTable = ();
1333            # Build a query for all of the feature's annotations, sorted by date.
1334            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],
1335                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1336                                   [$featureID]);
1337            my $timeSelected = 0;
1338            # Loop until we run out of annotations.
1339            while (my $annotation = $query->Fetch()) {
1340                # Get the annotation text.
1341                my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1342                # Check to see if this is a functional assignment for a trusted user.
1343                my ($user, $function) = _ParseAssignment($text);
1344                if ($user) {
1345                    # Here it is a functional assignment.
1346                    push @retVal, [$user, $function];
1347                }
1348            }
1349        } else {
1350            # Here we have a non-FIG feature ID. In this case the user ID does not
1351            # matter. We simply get the information from the External Alias Function
1352            # table.
1353            push @retVal, $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);
1354        }
1355        # Return the assignments found.
1356        return @retVal;
1357    }
1358    
1359  =head3 BBHList  =head3 BBHList
1360    
1361  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1230  Line 1375 
1375    
1376  =item RETURN  =item RETURN
1377    
1378  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1379  their best hits.  on the target genome.
1380    
1381  =back  =back
1382    
# Line 1248  Line 1393 
1393                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1394                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1395                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1396                  # Look for the best hit.          # Peel off the BBHs found.
1397                  my $bbh = $query->Fetch;          my @found = ();
1398                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1399                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1400                  }                  }
1401            $retVal{$featureID} = \@found;
1402          }          }
1403          # Return the mapping.          # Return the mapping.
1404          return \%retVal;          return \%retVal;
1405  }  }
1406    
1407    =head3 SimList
1408    
1409    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1410    
1411    Return a list of the similarities to the specified feature.
1412    
1413    Sprout does not support real similarities, so this method just returns the bidirectional
1414    best hits.
1415    
1416    =over 4
1417    
1418    =item featureID
1419    
1420    ID of the feature whose similarities are desired.
1421    
1422    =item count
1423    
1424    Maximum number of similar features to be returned, or C<0> to return them all.
1425    
1426    =back
1427    
1428    =cut
1429    #: Return Type %;
1430    sub SimList {
1431        # Get the parameters.
1432        my ($self, $featureID, $count) = @_;
1433        # Ask for the best hits.
1434        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1435                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1436                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1437                                  $count);
1438        # Create the return value.
1439        my %retVal = ();
1440        for my $tuple (@lists) {
1441            $retVal{$tuple->[0]} = $tuple->[1];
1442        }
1443        # Return the result.
1444        return %retVal;
1445    }
1446    
1447    
1448    
1449    =head3 IsComplete
1450    
1451    C<< my $flag = $sprout->IsComplete($genomeID); >>
1452    
1453    Return TRUE if the specified genome is complete, else FALSE.
1454    
1455    =over 4
1456    
1457    =item genomeID
1458    
1459    ID of the genome whose completeness status is desired.
1460    
1461    =item RETURN
1462    
1463    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1464    not found.
1465    
1466    =back
1467    
1468    =cut
1469    #: Return Type $;
1470    sub IsComplete {
1471        # Get the parameters.
1472        my ($self, $genomeID) = @_;
1473        # Declare the return variable.
1474        my $retVal;
1475        # Get the genome's data.
1476        my $genomeData = $self->GetEntity('Genome', $genomeID);
1477        if ($genomeData) {
1478            # The genome exists, so get the completeness flag.
1479            ($retVal) = $genomeData->Value('complete');
1480        }
1481        # Return the result.
1482        return $retVal;
1483    }
1484    
1485  =head3 FeatureAliases  =head3 FeatureAliases
1486    
1487  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1572 
1572  sub CoupledFeatures {  sub CoupledFeatures {
1573          # Get the parameters.          # Get the parameters.
1574          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1575          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1576          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1577          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1578          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1579          my $found = 0;          my $found = 0;
1580          # Create the return hash.          # Create the return hash.
1581          my %retVal = ();          my %retVal = ();
1582          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1583          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1584                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1585                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1586                                                            'Coupling(score)']);
1587            # The coupling ID contains the two feature IDs separated by a space. We use
1588            # this information to find the ID of the other feature.
1589            my ($fid1, $fid2) = split / /, $couplingID;
1590            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1591            # Attach the other feature's score to its ID.
1592                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1593                  $found = 1;                  $found = 1;
1594          }          }
# Line 1374  Line 1601 
1601          return %retVal;          return %retVal;
1602  }  }
1603    
1604    =head3 CouplingEvidence
1605    
1606    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1607    
1608    Return the evidence for a functional coupling.
1609    
1610    A pair of features is considered evidence of a coupling between two other
1611    features if they occur close together on a contig and both are similar to
1612    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1613    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1614    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1615    similar to B<A2>.
1616    
1617    The score of a coupling is determined by the number of pieces of evidence
1618    that are considered I<representative>. If several evidence items belong to
1619    a group of genomes that are close to each other, only one of those items
1620    is considered representative. The other evidence items are presumed to be
1621    there because of the relationship between the genomes rather than because
1622    the two proteins generated by the features have a related functionality.
1623    
1624    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1625    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1626    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1627    and FALSE otherwise.
1628    
1629    =over 4
1630    
1631    =item peg1
1632    
1633    ID of the feature of interest.
1634    
1635    =item peg2
1636    
1637    ID of a feature functionally coupled to the feature of interest.
1638    
1639    =item RETURN
1640    
1641    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1642    of interest, a feature similar to the functionally coupled feature, and a flag
1643    that is TRUE for a representative piece of evidence and FALSE otherwise.
1644    
1645    =back
1646    
1647    =cut
1648    #: Return Type @@;
1649    sub CouplingEvidence {
1650        # Get the parameters.
1651        my ($self, $peg1, $peg2) = @_;
1652        # Declare the return variable.
1653        my @retVal = ();
1654        # Our first task is to find out the nature of the coupling: whether or not
1655        # it exists, its score, and whether the features are stored in the same
1656        # order as the ones coming in.
1657        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1658        # Only proceed if a coupling exists.
1659        if ($couplingID) {
1660            # Determine the ordering to place on the evidence items. If we're
1661            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1662            # we want feature 1 before feature 2 (normal).
1663            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1664            my $ordering = ($inverted ? "DESC" : "");
1665            # Get the coupling evidence.
1666            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1667                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1668                                              [$couplingID],
1669                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1670            # Loop through the evidence items. Each piece of evidence is represented by two
1671            # positions in the evidence list, one for each feature on the other side of the
1672            # evidence link. If at some point we want to generalize to couplings with
1673            # more than two positions, this section of code will need to be re-done.
1674            while (@evidenceList > 0) {
1675                my $peg1Data = shift @evidenceList;
1676                my $peg2Data = shift @evidenceList;
1677                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1678                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1679            }
1680            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1681        }
1682        # Return the result.
1683        return @retVal;
1684    }
1685    
1686    =head3 GetCoupling
1687    
1688    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1689    
1690    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1691    exists, we return the coupling ID along with an indicator of whether the
1692    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1693    In the second case, we say the coupling is I<inverted>. The importance of an
1694    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1695    
1696    =over 4
1697    
1698    =item peg1
1699    
1700    ID of the feature of interest.
1701    
1702    =item peg2
1703    
1704    ID of the potentially coupled feature.
1705    
1706    =item RETURN
1707    
1708    Returns a three-element list. The first element contains the database ID of
1709    the coupling. The second element is FALSE if the coupling is stored in the
1710    database in the caller specified order and TRUE if it is stored in the
1711    inverted order. The third element is the coupling's score. If the coupling
1712    does not exist, all three list elements will be C<undef>.
1713    
1714    =back
1715    
1716    =cut
1717    #: Return Type $%@;
1718    sub GetCoupling {
1719        # Get the parameters.
1720        my ($self, $peg1, $peg2) = @_;
1721        # Declare the return values. We'll start with the coupling ID and undefine the
1722        # flag and score until we have more information.
1723        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1724        # Find the coupling data.
1725        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1726                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1727                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1728        # Check to see if we found anything.
1729        if (!@pegs) {
1730            Trace("No coupling found.") if T(Coupling => 4);
1731            # No coupling, so undefine the return value.
1732            $retVal = undef;
1733        } else {
1734            # We have a coupling! Get the score and check for inversion.
1735            $score = $pegs[0]->[1];
1736            my $firstFound = $pegs[0]->[0];
1737            $inverted = ($firstFound ne $peg1);
1738            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1739        }
1740        # Return the result.
1741        return ($retVal, $inverted, $score);
1742    }
1743    
1744    =head3 CouplingID
1745    
1746    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1747    
1748    Return the coupling ID for a pair of feature IDs.
1749    
1750    The coupling ID is currently computed by joining the feature IDs in
1751    sorted order with a space. Client modules (that is, modules which
1752    use Sprout) should not, however, count on this always being the
1753    case. This method provides a way for abstracting the concept of a
1754    coupling ID. All that we know for sure about it is that it can be
1755    generated easily from the feature IDs and the order of the IDs
1756    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1757    will have the same value as C<CouplingID("b1", "a1")>.
1758    
1759    =over 4
1760    
1761    =item peg1
1762    
1763    First feature of interest.
1764    
1765    =item peg2
1766    
1767    Second feature of interest.
1768    
1769    =item RETURN
1770    
1771    Returns the ID that would be used to represent a functional coupling of
1772    the two specified PEGs.
1773    
1774    =back
1775    
1776    =cut
1777    #: Return Type $;
1778    sub CouplingID {
1779        return join " ", sort @_;
1780    }
1781    
1782  =head3 GetEntityTypes  =head3 GetEntityTypes
1783    
1784  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1435  Line 1840 
1840                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1841                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1842                          if ($id) {                          if ($id) {
1843                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1844                          }                          }
1845                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1846                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1847                  } else {                  } else {
1848                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
1849                          # First, we get the actual data out. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
1850                          # case.                          # case.
1851                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1852                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 1854 
1854          }          }
1855          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1856          if ($sequence) {          if ($sequence) {
1857                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1858          }          }
1859          # Close the file.          # Close the file.
1860          close FASTAFILE;          close FASTAFILE;
# Line 1568  Line 1973 
1973  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1974  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1975    
1976  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1977    
1978  =over 4  =over 4
1979    
# Line 1775  Line 2180 
2180          # Get the parameters.          # Get the parameters.
2181          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2182          # Check for the entity instance.          # Check for the entity instance.
2183        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2184          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2185          # Return an existence indicator.          # Return an existence indicator.
2186          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1966  Line 2372 
2372          return @retVal;          return @retVal;
2373  }  }
2374    
2375    =head3 GetProperties
2376    
2377    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2378    
2379    Return a list of the properties with the specified characteristics.
2380    
2381    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2382    will also be associated with genomes.) A property value is represented by a 4-tuple of
2383    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2384    
2385    =over 4
2386    
2387    =item fid
2388    
2389    ID of the feature possessing the property.
2390    
2391    =item key
2392    
2393    Name or key of the property.
2394    
2395    =item value
2396    
2397    Value of the property.
2398    
2399    =item url
2400    
2401    URL of the document that indicated the property should have this particular value, or an
2402    empty string if no such document exists.
2403    
2404    =back
2405    
2406    The parameters act as a filter for the desired data. Any non-null parameter will
2407    automatically match all the tuples returned. So, specifying just the I<$fid> will
2408    return all the properties of the specified feature; similarly, specifying the I<$key>
2409    and I<$value> parameters will return all the features having the specified property
2410    value.
2411    
2412    A single property key can have many values, representing different ideas about the
2413    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2414    virulent, and another may declare that it is not virulent. A query about the virulence of
2415    C<fig|83333.1.peg.10> would be coded as
2416    
2417        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2418    
2419    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2420    not to be filtered. The tuples returned would be
2421    
2422        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2423        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2424    
2425    =cut
2426    #: Return Type @@;
2427    sub GetProperties {
2428        # Get the parameters.
2429        my ($self, @parms) = @_;
2430        # Declare the return variable.
2431        my @retVal = ();
2432        # Now we need to create a WHERE clause that will get us the data we want. First,
2433        # we create a list of the columns containing the data for each parameter.
2434        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2435                        'Property(property-value)', 'HasProperty(evidence)');
2436        # Now we build the WHERE clause and the list of parameter values.
2437        my @where = ();
2438        my @values = ();
2439        for (my $i = 0; $i <= $#colNames; $i++) {
2440            my $parm = $parms[$i];
2441            if (defined $parm && ($parm ne '')) {
2442                push @where, "$colNames[$i] = ?";
2443                push @values, $parm;
2444            }
2445        }
2446        # Format the WHERE clause.
2447        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2448        # Ask for all the propertie values with the desired characteristics.
2449        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2450        while (my $valueObject = $query->Fetch()) {
2451            my @tuple = $valueObject->Values(\@colNames);
2452            push @retVal, \@tuple;
2453        }
2454        # Return the result.
2455        return @retVal;
2456    }
2457    
2458  =head3 FeatureProperties  =head3 FeatureProperties
2459    
2460  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2649 
2649  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2650    
2651  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2652  to the role the feature performs.  to the roles the feature performs.
2653    
2654  =over 4  =over 4
2655    
# Line 2170  Line 2659 
2659    
2660  =item RETURN  =item RETURN
2661    
2662  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2663    
2664  =back  =back
2665    
2666  =cut  =cut
2667  #: Return Type %;  #: Return Type %@;
2668  sub SubsystemsOf {  sub SubsystemsOf {
2669          # Get the parameters.          # Get the parameters.
2670          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2671          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2672          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2673                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2674                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2675          # Create the return value.          # Create the return value.
2676          my %retVal = ();          my %retVal = ();
2677        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2678        # in two spreadsheet cells.
2679        my %dupHash = ();
2680          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2681          for my $record (@subsystems) {          for my $record (@subsystems) {
2682                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2683            my ($subsys, $role) = @{$record};
2684            # Insure it's the first time for both.
2685            my $dupKey = "$subsys\n$role";
2686            if (! exists $dupHash{"$subsys\n$role"}) {
2687                $dupHash{$dupKey} = 1;
2688                push @{$retVal{$subsys}}, $role;
2689            }
2690          }          }
2691          # Return the hash.          # Return the hash.
2692          return %retVal;          return %retVal;
2693  }  }
2694    
2695    =head3 SubsystemList
2696    
2697    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2698    
2699    Return a list containing the names of the subsystems in which the specified
2700    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2701    subsystem names, not the roles.
2702    
2703    =over 4
2704    
2705    =item featureID
2706    
2707    ID of the feature whose subsystem names are desired.
2708    
2709    =item RETURN
2710    
2711    Returns a list of the names of the subsystems in which the feature participates.
2712    
2713    =back
2714    
2715    =cut
2716    #: Return Type @;
2717    sub SubsystemList {
2718        # Get the parameters.
2719        my ($self, $featureID) = @_;
2720        # Get the list of names.
2721        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2722                                    [$featureID], 'HasSSCell(from-link)');
2723        # Return the result.
2724        return @retVal;
2725    }
2726    
2727  =head3 RelatedFeatures  =head3 RelatedFeatures
2728    
2729  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2353  Line 2884 
2884  sub GetAll {  sub GetAll {
2885          # Get the parameters.          # Get the parameters.
2886          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2887          # Create the query.      # Call the ERDB method.
2888          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2889          # Set up a counter of the number of records read.                                          $fields, $count);
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
2890          # Return the resulting list.          # Return the resulting list.
2891          return @retVal;          return @retVal;
2892  }  }
# Line 2624  Line 3142 
3142      return %retVal;      return %retVal;
3143  }  }
3144    
3145    =head3 MyGenomes
3146    
3147    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3148    
3149    Return a list of the genomes to be included in the Sprout.
3150    
3151    This method is provided for use during the Sprout load. It presumes the Genome load file has
3152    already been created. (It will be in the Sprout data directory and called either C<Genome>
3153    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3154    IDs.
3155    
3156    =over 4
3157    
3158    =item dataDir
3159    
3160    Directory containing the Sprout load files.
3161    
3162    =back
3163    
3164    =cut
3165    #: Return Type @;
3166    sub MyGenomes {
3167        # Get the parameters.
3168        my ($dataDir) = @_;
3169        # Compute the genome file name.
3170        my $genomeFileName = LoadFileName($dataDir, "Genome");
3171        # Extract the genome IDs from the files.
3172        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3173        # Return the result.
3174        return @retVal;
3175    }
3176    
3177    =head3 LoadFileName
3178    
3179    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3180    
3181    Return the name of the load file for the specified table in the specified data
3182    directory.
3183    
3184    =over 4
3185    
3186    =item dataDir
3187    
3188    Directory containing the Sprout load files.
3189    
3190    =item tableName
3191    
3192    Name of the table whose load file is desired.
3193    
3194    =item RETURN
3195    
3196    Returns the name of the file containing the load data for the specified table, or
3197    C<undef> if no load file is present.
3198    
3199    =back
3200    
3201    =cut
3202    #: Return Type $;
3203    sub LoadFileName {
3204        # Get the parameters.
3205        my ($dataDir, $tableName) = @_;
3206        # Declare the return variable.
3207        my $retVal;
3208        # Check for the various file names.
3209        if (-e "$dataDir/$tableName") {
3210            $retVal = "$dataDir/$tableName";
3211        } elsif (-e "$dataDir/$tableName.dtx") {
3212            $retVal = "$dataDir/$tableName.dtx";
3213        }
3214        # Return the result.
3215        return $retVal;
3216    }
3217    
3218  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3219    
3220  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2663  Line 3254 
3254          # Declare the return value.          # Declare the return value.
3255          my @retVal = ();          my @retVal = ();
3256          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3257          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3258          if ($type =~ m/^set ([^ ]+) function to$/i) {          if ($type =~ m/^set ([^ ]+) function to$/i) {
3259                  # Here it is, so we return the user name (which is in $1), the functional role text,                  # Here it is, so we return the user name (which is in $1), the functional role text,
3260          # and the assigning user.          # and the assigning user.
3261                  @retVal = ($1, $function, $user);          @retVal = ($1, $function);
3262          }          }
3263          # Return the result list.          # Return the result list.
3264          return @retVal;          return @retVal;
# Line 2695  Line 3286 
3286    
3287  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3288      my ($timeValue) = @_;      my ($timeValue) = @_;
3289      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3290      return $retVal;      return $retVal;
3291  }  }
3292    
3293    =head3 AddProperty
3294    
3295    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3296    
3297    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3298    be added to almost any object. In Sprout, they can only be added to features. In
3299    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3300    pair. If the particular key/value pair coming in is not already in the database, a new
3301    B<Property> record is created to hold it.
3302    
3303    =over 4
3304    
3305    =item peg
3306    
3307    ID of the feature to which the attribute is to be replied.
3308    
3309    =item key
3310    
3311    Name of the attribute (key).
3312    
3313    =item value
3314    
3315    Value of the attribute.
3316    
3317    =item url
3318    
3319    URL or text citation from which the property was obtained.
3320    
3321    =back
3322    
3323    =cut
3324    #: Return Type ;
3325    sub AddProperty {
3326        # Get the parameters.
3327        my ($self, $featureID, $key, $value, $url) = @_;
3328        # Declare the variable to hold the desired property ID.
3329        my $propID;
3330        # Attempt to find a property record for this key/value pair.
3331        my @properties = $self->GetFlat(['Property'],
3332                                       "Property(property-name) = ? AND Property(property-value) = ?",
3333                                       [$key, $value], 'Property(id)');
3334        if (@properties) {
3335            # Here the property is already in the database. We save its ID.
3336            $propID = $properties[0];
3337            # Here the property value does not exist. We need to generate an ID. It will be set
3338            # to a number one greater than the maximum value in the database. This call to
3339            # GetAll will stop after one record.
3340            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3341                                            1);
3342            $propID = $maxProperty[0]->[0] + 1;
3343            # Insert the new property value.
3344            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3345        }
3346        # Now we connect the incoming feature to the property.
3347        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3348    }
3349    
3350    
3351    
3352  1;  1;

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.47

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3