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

Diff of /Sprout/Sprout.pm

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

revision 1.13, Thu May 5 03:14:03 2005 UTC revision 1.55, Mon Apr 3 18:33:58 2006 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::fig/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 720  Line 740 
740  should be of the form returned by L</featureLocation> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
741  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
742    
743    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
744    between positions 1401 and 1532, inclusive.
745    
746        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
747    
748  =over 4  =over 4
749    
750  =item locationList  =item locationList
751    
752  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
753  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
754    
755  =item RETURN  =item RETURN
756    
# Line 752  Line 777 
777                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
778                  # before putting it in the return value.                  # before putting it in the return value.
779                  my ($start, $stop);                  my ($start, $stop);
780            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
781                  if ($dir eq "+") {                  if ($dir eq "+") {
782                          $start = $beg;                          $start = $beg;
783                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
784                  } else {                  } else {
785                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
786                          $stop = $beg;                          $stop = $beg;
787                  }                  }
788            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
789                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
790                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
791                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 797 
797                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
798                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
799                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
800                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
801                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
802                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
803                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
804                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
805                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
806                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
807                  }                  }
808                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
809                  if ($dir eq '+') {                  if ($dir eq '+') {
810                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
811                  } else {                  } else {
812                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
813                  }                  }
814          }          }
815          # Return the result.          # Return the result.
# Line 851  Line 879 
879          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
880          if ($sequence) {          if ($sequence) {
881                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
882                  $retVal = $start + $len;          $retVal = $start + $len - 1;
883        }
884        # Return the result.
885        return $retVal;
886    }
887    
888    =head3 ClusterPEGs
889    
890    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
891    
892    Cluster the PEGs in a list according to the cluster coding scheme of the specified
893    subsystem. In order for this to work properly, the subsystem object must have
894    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
895    This causes the cluster numbers to be pulled into the subsystem's color hash.
896    If a PEG is not found in the color hash, it will not appear in the output
897    sequence.
898    
899    =over 4
900    
901    =item sub
902    
903    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
904    method.
905    
906    =item pegs
907    
908    Reference to the list of PEGs to be clustered.
909    
910    =item RETURN
911    
912    Returns a list of the PEGs, grouped into smaller lists by cluster number.
913    
914    =back
915    
916    =cut
917    #: Return Type $@@;
918    sub ClusterPEGs {
919        # Get the parameters.
920        my ($self, $sub, $pegs) = @_;
921        # Declare the return variable.
922        my $retVal = [];
923        # Loop through the PEGs, creating arrays for each cluster.
924        for my $pegID (@{$pegs}) {
925            my $clusterNumber = $sub->get_cluster_number($pegID);
926            # Only proceed if the PEG is in a cluster.
927            if ($clusterNumber >= 0) {
928                # Push this PEG onto the sub-list for the specified cluster number.
929                push @{$retVal->[$clusterNumber]}, $pegID;
930            }
931          }          }
932          # Return the result.          # Return the result.
933          return $retVal;          return $retVal;
# Line 1001  Line 1077 
1077    
1078  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1079    
1080  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1081    
1082  Return the annotations of a feature.  Return the annotations of a feature.
1083    
# Line 1011  Line 1087 
1087    
1088  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1089    
1090    =item rawFlag
1091    
1092    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1093    will be returned in human-readable form.
1094    
1095  =item RETURN  =item RETURN
1096    
1097  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1098    
1099  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1100    
1101  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1102    
1103  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1104    
# Line 1029  Line 1110 
1110  #: Return Type @%;  #: Return Type @%;
1111  sub FeatureAnnotations {  sub FeatureAnnotations {
1112          # Get the parameters.          # Get the parameters.
1113          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1114          # 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.
1115          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1116                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1123 
1123                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1124                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1125                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1126            # Convert the time, if necessary.
1127            if (! $rawFlag) {
1128                $timeStamp = FriendlyTimestamp($timeStamp);
1129            }
1130                  # Assemble them into a hash.                  # Assemble them into a hash.
1131          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1132                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1133                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1134                  # Add it to the return list.                  # Add it to the return list.
1135                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1073  Line 1158 
1158    
1159  =item RETURN  =item RETURN
1160    
1161  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1162    
1163  =back  =back
1164    
# Line 1083  Line 1168 
1168          # Get the parameters.          # Get the parameters.
1169          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1170          # Get all of the feature's annotations.          # Get all of the feature's annotations.
1171      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1172                                                      "IsTargetOfAnnotation(from-link) = ?",                                                      "IsTargetOfAnnotation(from-link) = ?",
1173                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1174                                               'MadeAnnotation(from-link)']);
1175          # Declare the return hash.          # Declare the return hash.
1176          my %retVal;          my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1177      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1178      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1179          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1180      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1181          # Get the annotation fields.          # Get the annotation fields.
1182          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1183                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1184                  my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1185          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1186              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1187              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1188              # return hash.              # return hash.
1189                          $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1190                  }                  }
1191          }          }
1192          # Return the hash of assignments found.          # Return the hash of assignments found.
# Line 1120  Line 1202 
1202  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
1203  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
1204  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
1205  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
1206  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
1207  most features only have a small number of annotations.  most features only have a small number of annotations.
1208    
# Line 1182  Line 1264 
1264              }              }
1265          }          }
1266          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1267          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1268                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1269                                 [$featureID]);                                 [$featureID]);
1270          my $timeSelected = 0;          my $timeSelected = 0;
1271          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1272          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1273              # Get the annotation text.              # Get the annotation text.
1274              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1275                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1276              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1277              my ($user, $function) = _ParseAssignment($text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1278              if ($user) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1279                if ($actualUser) {
1280                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1281                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1282                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1283                      $retVal = $function;                      $retVal = $function;
1284                      $timeSelected = $time;                      $timeSelected = $time;
1285                  }                  }
# Line 1211  Line 1295 
1295          return $retVal;          return $retVal;
1296  }  }
1297    
1298    =head3 FunctionsOf
1299    
1300    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1301    
1302    Return the functional assignments of a particular feature.
1303    
1304    The functional assignment is handled differently depending on the type of feature. If
1305    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1306    assignment is a type of annotation. The format of an assignment is described in
1307    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1308    annotation itself because it's a text field; however, this is not a big problem because
1309    most features only have a small number of annotations.
1310    
1311    If the feature is B<not> identified by a FIG ID, then the functional assignment
1312    information is taken from the B<ExternalAliasFunc> table. If the table does
1313    not contain an entry for the feature, an empty list is returned.
1314    
1315    =over 4
1316    
1317    =item featureID
1318    
1319    ID of the feature whose functional assignments are desired.
1320    
1321    =item RETURN
1322    
1323    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1324    that user.
1325    
1326    =back
1327    
1328    =cut
1329    #: Return Type @@;
1330    sub FunctionsOf {
1331        # Get the parameters.
1332        my ($self, $featureID) = @_;
1333        # Declare the return value.
1334        my @retVal = ();
1335        # Determine the ID type.
1336        if ($featureID =~ m/^fig\|/) {
1337            # Here we have a FIG feature ID. We must build the list of trusted
1338            # users.
1339            my %trusteeTable = ();
1340            # Build a query for all of the feature's annotations, sorted by date.
1341            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1342                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1343                                   [$featureID]);
1344            my $timeSelected = 0;
1345            # Loop until we run out of annotations.
1346            while (my $annotation = $query->Fetch()) {
1347                # Get the annotation text.
1348                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1349                                                                'Annotation(time)',
1350                                                                'MadeAnnotation(user)']);
1351                # Check to see if this is a functional assignment for a trusted user.
1352                my ($actualUser, $function) = _ParseAssignment($user, $text);
1353                if ($actualUser) {
1354                    # Here it is a functional assignment.
1355                    push @retVal, [$actualUser, $function];
1356                }
1357            }
1358        } else {
1359            # Here we have a non-FIG feature ID. In this case the user ID does not
1360            # matter. We simply get the information from the External Alias Function
1361            # table.
1362            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1363                                                     ['ExternalAliasFunc(func)']);
1364            push @retVal, map { ['master', $_] } @assignments;
1365        }
1366        # Return the assignments found.
1367        return @retVal;
1368    }
1369    
1370  =head3 BBHList  =head3 BBHList
1371    
1372  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1230  Line 1386 
1386    
1387  =item RETURN  =item RETURN
1388    
1389  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
1390  their best hits.  on the target genome.
1391    
1392  =back  =back
1393    
# Line 1248  Line 1404 
1404                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1405                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1406                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1407                  # Look for the best hit.          # Peel off the BBHs found.
1408                  my $bbh = $query->Fetch;          my @found = ();
1409                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1410                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1411                  }                  }
1412            $retVal{$featureID} = \@found;
1413          }          }
1414          # Return the mapping.          # Return the mapping.
1415          return \%retVal;          return \%retVal;
1416  }  }
1417    
1418    =head3 SimList
1419    
1420    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1421    
1422    Return a list of the similarities to the specified feature.
1423    
1424    Sprout does not support real similarities, so this method just returns the bidirectional
1425    best hits.
1426    
1427    =over 4
1428    
1429    =item featureID
1430    
1431    ID of the feature whose similarities are desired.
1432    
1433    =item count
1434    
1435    Maximum number of similar features to be returned, or C<0> to return them all.
1436    
1437    =back
1438    
1439    =cut
1440    #: Return Type %;
1441    sub SimList {
1442        # Get the parameters.
1443        my ($self, $featureID, $count) = @_;
1444        # Ask for the best hits.
1445        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1446                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1447                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1448                                  $count);
1449        # Create the return value.
1450        my %retVal = ();
1451        for my $tuple (@lists) {
1452            $retVal{$tuple->[0]} = $tuple->[1];
1453        }
1454        # Return the result.
1455        return %retVal;
1456    }
1457    
1458    
1459    
1460    =head3 IsComplete
1461    
1462    C<< my $flag = $sprout->IsComplete($genomeID); >>
1463    
1464    Return TRUE if the specified genome is complete, else FALSE.
1465    
1466    =over 4
1467    
1468    =item genomeID
1469    
1470    ID of the genome whose completeness status is desired.
1471    
1472    =item RETURN
1473    
1474    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1475    not found.
1476    
1477    =back
1478    
1479    =cut
1480    #: Return Type $;
1481    sub IsComplete {
1482        # Get the parameters.
1483        my ($self, $genomeID) = @_;
1484        # Declare the return variable.
1485        my $retVal;
1486        # Get the genome's data.
1487        my $genomeData = $self->GetEntity('Genome', $genomeID);
1488        if ($genomeData) {
1489            # The genome exists, so get the completeness flag.
1490            ($retVal) = $genomeData->Value('Genome(complete)');
1491        }
1492        # Return the result.
1493        return $retVal;
1494    }
1495    
1496  =head3 FeatureAliases  =head3 FeatureAliases
1497    
1498  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1583 
1583  sub CoupledFeatures {  sub CoupledFeatures {
1584          # Get the parameters.          # Get the parameters.
1585          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1586          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1587          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1588          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1589          # 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.
1590          my $found = 0;          my $found = 0;
1591          # Create the return hash.          # Create the return hash.
1592          my %retVal = ();          my %retVal = ();
1593          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1594          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1595                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1596                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1597                                                            'Coupling(score)']);
1598            # The coupling ID contains the two feature IDs separated by a space. We use
1599            # this information to find the ID of the other feature.
1600            my ($fid1, $fid2) = split / /, $couplingID;
1601            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1602            # Attach the other feature's score to its ID.
1603                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1604                  $found = 1;                  $found = 1;
1605          }          }
# Line 1374  Line 1612 
1612          return %retVal;          return %retVal;
1613  }  }
1614    
1615    =head3 CouplingEvidence
1616    
1617    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1618    
1619    Return the evidence for a functional coupling.
1620    
1621    A pair of features is considered evidence of a coupling between two other
1622    features if they occur close together on a contig and both are similar to
1623    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1624    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1625    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1626    similar to B<A2>.
1627    
1628    The score of a coupling is determined by the number of pieces of evidence
1629    that are considered I<representative>. If several evidence items belong to
1630    a group of genomes that are close to each other, only one of those items
1631    is considered representative. The other evidence items are presumed to be
1632    there because of the relationship between the genomes rather than because
1633    the two proteins generated by the features have a related functionality.
1634    
1635    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1636    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1637    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1638    and FALSE otherwise.
1639    
1640    =over 4
1641    
1642    =item peg1
1643    
1644    ID of the feature of interest.
1645    
1646    =item peg2
1647    
1648    ID of a feature functionally coupled to the feature of interest.
1649    
1650    =item RETURN
1651    
1652    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1653    of interest, a feature similar to the functionally coupled feature, and a flag
1654    that is TRUE for a representative piece of evidence and FALSE otherwise.
1655    
1656    =back
1657    
1658    =cut
1659    #: Return Type @@;
1660    sub CouplingEvidence {
1661        # Get the parameters.
1662        my ($self, $peg1, $peg2) = @_;
1663        # Declare the return variable.
1664        my @retVal = ();
1665        # Our first task is to find out the nature of the coupling: whether or not
1666        # it exists, its score, and whether the features are stored in the same
1667        # order as the ones coming in.
1668        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1669        # Only proceed if a coupling exists.
1670        if ($couplingID) {
1671            # Determine the ordering to place on the evidence items. If we're
1672            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1673            # we want feature 1 before feature 2 (normal).
1674            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1675            my $ordering = ($inverted ? "DESC" : "");
1676            # Get the coupling evidence.
1677            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1678                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1679                                              [$couplingID],
1680                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1681            # Loop through the evidence items. Each piece of evidence is represented by two
1682            # positions in the evidence list, one for each feature on the other side of the
1683            # evidence link. If at some point we want to generalize to couplings with
1684            # more than two positions, this section of code will need to be re-done.
1685            while (@evidenceList > 0) {
1686                my $peg1Data = shift @evidenceList;
1687                my $peg2Data = shift @evidenceList;
1688                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1689                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1690            }
1691            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1692        }
1693        # Return the result.
1694        return @retVal;
1695    }
1696    
1697    =head3 GetCoupling
1698    
1699    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1700    
1701    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1702    exists, we return the coupling ID along with an indicator of whether the
1703    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1704    In the second case, we say the coupling is I<inverted>. The importance of an
1705    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1706    
1707    =over 4
1708    
1709    =item peg1
1710    
1711    ID of the feature of interest.
1712    
1713    =item peg2
1714    
1715    ID of the potentially coupled feature.
1716    
1717    =item RETURN
1718    
1719    Returns a three-element list. The first element contains the database ID of
1720    the coupling. The second element is FALSE if the coupling is stored in the
1721    database in the caller specified order and TRUE if it is stored in the
1722    inverted order. The third element is the coupling's score. If the coupling
1723    does not exist, all three list elements will be C<undef>.
1724    
1725    =back
1726    
1727    =cut
1728    #: Return Type $%@;
1729    sub GetCoupling {
1730        # Get the parameters.
1731        my ($self, $peg1, $peg2) = @_;
1732        # Declare the return values. We'll start with the coupling ID and undefine the
1733        # flag and score until we have more information.
1734        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1735        # Find the coupling data.
1736        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1737                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1738                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1739        # Check to see if we found anything.
1740        if (!@pegs) {
1741            Trace("No coupling found.") if T(Coupling => 4);
1742            # No coupling, so undefine the return value.
1743            $retVal = undef;
1744        } else {
1745            # We have a coupling! Get the score and check for inversion.
1746            $score = $pegs[0]->[1];
1747            my $firstFound = $pegs[0]->[0];
1748            $inverted = ($firstFound ne $peg1);
1749            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1750        }
1751        # Return the result.
1752        return ($retVal, $inverted, $score);
1753    }
1754    
1755    =head3 CouplingID
1756    
1757    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1758    
1759    Return the coupling ID for a pair of feature IDs.
1760    
1761    The coupling ID is currently computed by joining the feature IDs in
1762    sorted order with a space. Client modules (that is, modules which
1763    use Sprout) should not, however, count on this always being the
1764    case. This method provides a way for abstracting the concept of a
1765    coupling ID. All that we know for sure about it is that it can be
1766    generated easily from the feature IDs and the order of the IDs
1767    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1768    will have the same value as C<CouplingID("b1", "a1")>.
1769    
1770    =over 4
1771    
1772    =item peg1
1773    
1774    First feature of interest.
1775    
1776    =item peg2
1777    
1778    Second feature of interest.
1779    
1780    =item RETURN
1781    
1782    Returns the ID that would be used to represent a functional coupling of
1783    the two specified PEGs.
1784    
1785    =back
1786    
1787    =cut
1788    #: Return Type $;
1789    sub CouplingID {
1790        return join " ", sort @_;
1791    }
1792    
1793  =head3 GetEntityTypes  =head3 GetEntityTypes
1794    
1795  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1435  Line 1851 
1851                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1852                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1853                          if ($id) {                          if ($id) {
1854                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1855                          }                          }
1856                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1857                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1858                  } else {                  } else {
1859                          # 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.
1860                          # 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
1861                          # case.                          # case.
1862                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1863                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 1865 
1865          }          }
1866          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1867          if ($sequence) {          if ($sequence) {
1868                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1869          }          }
1870          # Close the file.          # Close the file.
1871          close FASTAFILE;          close FASTAFILE;
# Line 1568  Line 1984 
1984  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
1985  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>.
1986    
1987  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<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1988    
1989  =over 4  =over 4
1990    
# Line 1775  Line 2191 
2191          # Get the parameters.          # Get the parameters.
2192          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2193          # Check for the entity instance.          # Check for the entity instance.
2194        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2195          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2196          # Return an existence indicator.          # Return an existence indicator.
2197          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1966  Line 2383 
2383          return @retVal;          return @retVal;
2384  }  }
2385    
2386    =head3 GetProperties
2387    
2388    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2389    
2390    Return a list of the properties with the specified characteristics.
2391    
2392    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2393    will also be associated with genomes.) A property value is represented by a 4-tuple of
2394    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2395    
2396    =over 4
2397    
2398    =item fid
2399    
2400    ID of the feature possessing the property.
2401    
2402    =item key
2403    
2404    Name or key of the property.
2405    
2406    =item value
2407    
2408    Value of the property.
2409    
2410    =item url
2411    
2412    URL of the document that indicated the property should have this particular value, or an
2413    empty string if no such document exists.
2414    
2415    =back
2416    
2417    The parameters act as a filter for the desired data. Any non-null parameter will
2418    automatically match all the tuples returned. So, specifying just the I<$fid> will
2419    return all the properties of the specified feature; similarly, specifying the I<$key>
2420    and I<$value> parameters will return all the features having the specified property
2421    value.
2422    
2423    A single property key can have many values, representing different ideas about the
2424    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2425    virulent, and another may declare that it is not virulent. A query about the virulence of
2426    C<fig|83333.1.peg.10> would be coded as
2427    
2428        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2429    
2430    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2431    not to be filtered. The tuples returned would be
2432    
2433        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2434        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2435    
2436    =cut
2437    #: Return Type @@;
2438    sub GetProperties {
2439        # Get the parameters.
2440        my ($self, @parms) = @_;
2441        # Declare the return variable.
2442        my @retVal = ();
2443        # Now we need to create a WHERE clause that will get us the data we want. First,
2444        # we create a list of the columns containing the data for each parameter.
2445        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2446                        'Property(property-value)', 'HasProperty(evidence)');
2447        # Now we build the WHERE clause and the list of parameter values.
2448        my @where = ();
2449        my @values = ();
2450        for (my $i = 0; $i <= $#colNames; $i++) {
2451            my $parm = $parms[$i];
2452            if (defined $parm && ($parm ne '')) {
2453                push @where, "$colNames[$i] = ?";
2454                push @values, $parm;
2455            }
2456        }
2457        # Format the WHERE clause.
2458        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2459        # Ask for all the propertie values with the desired characteristics.
2460        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2461        while (my $valueObject = $query->Fetch()) {
2462            my @tuple = $valueObject->Values(\@colNames);
2463            push @retVal, \@tuple;
2464        }
2465        # Return the result.
2466        return @retVal;
2467    }
2468    
2469  =head3 FeatureProperties  =head3 FeatureProperties
2470    
2471  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2660 
2660  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2661    
2662  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
2663  to the role the feature performs.  to the roles the feature performs.
2664    
2665  =over 4  =over 4
2666    
# Line 2170  Line 2670 
2670    
2671  =item RETURN  =item RETURN
2672    
2673  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.
2674    
2675  =back  =back
2676    
2677  =cut  =cut
2678  #: Return Type %;  #: Return Type %@;
2679  sub SubsystemsOf {  sub SubsystemsOf {
2680          # Get the parameters.          # Get the parameters.
2681          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2682          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2683          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2684                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2685                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2686          # Create the return value.          # Create the return value.
2687          my %retVal = ();          my %retVal = ();
2688        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2689        # in two spreadsheet cells.
2690        my %dupHash = ();
2691          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2692          for my $record (@subsystems) {          for my $record (@subsystems) {
2693                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2694            my ($subsys, $role) = @{$record};
2695            # Insure it's the first time for both.
2696            my $dupKey = "$subsys\n$role";
2697            if (! exists $dupHash{"$subsys\n$role"}) {
2698                $dupHash{$dupKey} = 1;
2699                push @{$retVal{$subsys}}, $role;
2700            }
2701          }          }
2702          # Return the hash.          # Return the hash.
2703          return %retVal;          return %retVal;
2704  }  }
2705    
2706    =head3 SubsystemList
2707    
2708    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2709    
2710    Return a list containing the names of the subsystems in which the specified
2711    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2712    subsystem names, not the roles.
2713    
2714    =over 4
2715    
2716    =item featureID
2717    
2718    ID of the feature whose subsystem names are desired.
2719    
2720    =item RETURN
2721    
2722    Returns a list of the names of the subsystems in which the feature participates.
2723    
2724    =back
2725    
2726    =cut
2727    #: Return Type @;
2728    sub SubsystemList {
2729        # Get the parameters.
2730        my ($self, $featureID) = @_;
2731        # Get the list of names.
2732        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2733                                    [$featureID], 'HasSSCell(from-link)');
2734        # Return the result.
2735        return @retVal;
2736    }
2737    
2738  =head3 RelatedFeatures  =head3 RelatedFeatures
2739    
2740  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2611  Line 3153 
3153      return %retVal;      return %retVal;
3154  }  }
3155    
3156    =head3 MyGenomes
3157    
3158    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3159    
3160    Return a list of the genomes to be included in the Sprout.
3161    
3162    This method is provided for use during the Sprout load. It presumes the Genome load file has
3163    already been created. (It will be in the Sprout data directory and called either C<Genome>
3164    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3165    IDs.
3166    
3167    =over 4
3168    
3169    =item dataDir
3170    
3171    Directory containing the Sprout load files.
3172    
3173    =back
3174    
3175    =cut
3176    #: Return Type @;
3177    sub MyGenomes {
3178        # Get the parameters.
3179        my ($dataDir) = @_;
3180        # Compute the genome file name.
3181        my $genomeFileName = LoadFileName($dataDir, "Genome");
3182        # Extract the genome IDs from the files.
3183        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3184        # Return the result.
3185        return @retVal;
3186    }
3187    
3188    =head3 LoadFileName
3189    
3190    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3191    
3192    Return the name of the load file for the specified table in the specified data
3193    directory.
3194    
3195    =over 4
3196    
3197    =item dataDir
3198    
3199    Directory containing the Sprout load files.
3200    
3201    =item tableName
3202    
3203    Name of the table whose load file is desired.
3204    
3205    =item RETURN
3206    
3207    Returns the name of the file containing the load data for the specified table, or
3208    C<undef> if no load file is present.
3209    
3210    =back
3211    
3212    =cut
3213    #: Return Type $;
3214    sub LoadFileName {
3215        # Get the parameters.
3216        my ($dataDir, $tableName) = @_;
3217        # Declare the return variable.
3218        my $retVal;
3219        # Check for the various file names.
3220        if (-e "$dataDir/$tableName") {
3221            $retVal = "$dataDir/$tableName";
3222        } elsif (-e "$dataDir/$tableName.dtx") {
3223            $retVal = "$dataDir/$tableName.dtx";
3224        }
3225        # Return the result.
3226        return $retVal;
3227    }
3228    
3229    =head3 DeleteGenome
3230    
3231    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3232    
3233    Delete a genome from the database.
3234    
3235    =over 4
3236    
3237    =item genomeID
3238    
3239    ID of the genome to delete
3240    
3241    =item testFlag
3242    
3243    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3244    
3245    =item RETURN
3246    
3247    Returns a statistics object describing the rows deleted.
3248    
3249    =back
3250    
3251    =cut
3252    #: Return Type $%;
3253    sub DeleteGenome {
3254        # Get the parameters.
3255        my ($self, $genomeID, $testFlag) = @_;
3256        # Perform the delete for the genome's features.
3257        my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);
3258        # Perform the delete for the primary genome data.
3259        my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);
3260        $retVal->Accumulate($stats);
3261        # Return the result.
3262        return $retVal;
3263    }
3264    
3265  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3266    
3267  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2621  Line 3272 
3272    
3273  A functional assignment is always of the form  A functional assignment is always of the form
3274    
3275      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3276    
3277    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3278    the user and the assigning user (from MadeAnnotation) will be the same, but that is
3279    not always the case.
3280    
3281  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  In addition, the functional role may contain extra data that is stripped, such as
3282  actual functional role. In most cases, the user and the assigning user will be the  terminating spaces or a comment separated from the rest of the text by a tab.
 same, but that is not always the case.  
3283    
3284  This is a static method.  This is a static method.
3285    
3286  =over 4  =over 4
3287    
3288    =item user
3289    
3290    Name of the assigning user.
3291    
3292  =item text  =item text
3293    
3294  Text of the annotation.  Text of the annotation.
# Line 2646  Line 3304 
3304    
3305  sub _ParseAssignment {  sub _ParseAssignment {
3306          # Get the parameters.          # Get the parameters.
3307          my ($text) = @_;      my ($user, $text) = @_;
3308          # Declare the return value.          # Declare the return value.
3309          my @retVal = ();          my @retVal = ();
3310          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3311          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3312          if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3313                  # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3314          # and the assigning user.          @retVal = ($user, $function);
3315                  @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3316            # Here we have an assignment with a user that is passed back to the caller.
3317            @retVal = ($1, $function);
3318        }
3319        # If we have an assignment, we need to clean the function text. There may be
3320        # extra junk at the end added as a note from the user.
3321        if (@retVal) {
3322            $retVal[1] =~ s/(\t\S)?\s*$//;
3323          }          }
3324          # Return the result list.          # Return the result list.
3325          return @retVal;          return @retVal;
# Line 2682  Line 3347 
3347    
3348  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3349      my ($timeValue) = @_;      my ($timeValue) = @_;
3350      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3351      return $retVal;      return $retVal;
3352  }  }
3353    
3354    =head3 AddProperty
3355    
3356    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3357    
3358    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3359    be added to almost any object. In Sprout, they can only be added to features. In
3360    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3361    pair. If the particular key/value pair coming in is not already in the database, a new
3362    B<Property> record is created to hold it.
3363    
3364    =over 4
3365    
3366    =item peg
3367    
3368    ID of the feature to which the attribute is to be replied.
3369    
3370    =item key
3371    
3372    Name of the attribute (key).
3373    
3374    =item value
3375    
3376    Value of the attribute.
3377    
3378    =item url
3379    
3380    URL or text citation from which the property was obtained.
3381    
3382    =back
3383    
3384    =cut
3385    #: Return Type ;
3386    sub AddProperty {
3387        # Get the parameters.
3388        my ($self, $featureID, $key, $value, $url) = @_;
3389        # Declare the variable to hold the desired property ID.
3390        my $propID;
3391        # Attempt to find a property record for this key/value pair.
3392        my @properties = $self->GetFlat(['Property'],
3393                                       "Property(property-name) = ? AND Property(property-value) = ?",
3394                                       [$key, $value], 'Property(id)');
3395        if (@properties) {
3396            # Here the property is already in the database. We save its ID.
3397            $propID = $properties[0];
3398            # Here the property value does not exist. We need to generate an ID. It will be set
3399            # to a number one greater than the maximum value in the database. This call to
3400            # GetAll will stop after one record.
3401            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3402                                            1);
3403            $propID = $maxProperty[0]->[0] + 1;
3404            # Insert the new property value.
3405            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3406        }
3407        # Now we connect the incoming feature to the property.
3408        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3409    }
3410    
3411    
3412  1;  1;

Legend:
Removed from v.1.13  
changed lines
  Added in v.1.55

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3