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

Diff of /Sprout/Sprout.pm

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

revision 1.14, Thu Jun 9 19:06:55 2005 UTC revision 1.53, Sat Jan 28 08:59:17 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::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 ($actualUser, $function) = _ParseAssignment($user, $text);
1180          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
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;              $retVal{$actualUser} = $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 1182  Line 1259 
1259              }              }
1260          }          }
1261          # 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.
1262          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1263                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1264                                 [$featureID]);                                 [$featureID]);
1265          my $timeSelected = 0;          my $timeSelected = 0;
1266          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1267          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1268              # Get the annotation text.              # Get the annotation text.
1269              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1270                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1271              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1272              my ($user, $function) = _ParseAssignment($text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1273              if ($user) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1274                if ($actualUser) {
1275                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1276                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1277                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1278                      $retVal = $function;                      $retVal = $function;
1279                      $timeSelected = $time;                      $timeSelected = $time;
1280                  }                  }
# Line 1211  Line 1290 
1290          return $retVal;          return $retVal;
1291  }  }
1292    
1293    =head3 FunctionsOf
1294    
1295    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1296    
1297    Return the functional assignments of a particular feature.
1298    
1299    The functional assignment is handled differently depending on the type of feature. If
1300    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1301    assignment is a type of annotation. The format of an assignment is described in
1302    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1303    annotation itself because it's a text field; however, this is not a big problem because
1304    most features only have a small number of annotations.
1305    
1306    If the feature is B<not> identified by a FIG ID, then the functional assignment
1307    information is taken from the B<ExternalAliasFunc> table. If the table does
1308    not contain an entry for the feature, an empty list is returned.
1309    
1310    =over 4
1311    
1312    =item featureID
1313    
1314    ID of the feature whose functional assignments are desired.
1315    
1316    =item RETURN
1317    
1318    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1319    that user.
1320    
1321    =back
1322    
1323    =cut
1324    #: Return Type @@;
1325    sub FunctionsOf {
1326        # Get the parameters.
1327        my ($self, $featureID) = @_;
1328        # Declare the return value.
1329        my @retVal = ();
1330        # Determine the ID type.
1331        if ($featureID =~ m/^fig\|/) {
1332            # Here we have a FIG feature ID. We must build the list of trusted
1333            # users.
1334            my %trusteeTable = ();
1335            # Build a query for all of the feature's annotations, sorted by date.
1336            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1337                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1338                                   [$featureID]);
1339            my $timeSelected = 0;
1340            # Loop until we run out of annotations.
1341            while (my $annotation = $query->Fetch()) {
1342                # Get the annotation text.
1343                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1344                                                                'Annotation(time)',
1345                                                                'MadeAnnotation(user)']);
1346                # Check to see if this is a functional assignment for a trusted user.
1347                my ($actualUser, $function) = _ParseAssignment($user, $text);
1348                if ($actualUser) {
1349                    # Here it is a functional assignment.
1350                    push @retVal, [$actualUser, $function];
1351                }
1352            }
1353        } else {
1354            # Here we have a non-FIG feature ID. In this case the user ID does not
1355            # matter. We simply get the information from the External Alias Function
1356            # table.
1357            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1358                                                     ['ExternalAliasFunc(func)']);
1359            push @retVal, map { ['master', $_] } @assignments;
1360        }
1361        # Return the assignments found.
1362        return @retVal;
1363    }
1364    
1365  =head3 BBHList  =head3 BBHList
1366    
1367  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1230  Line 1381 
1381    
1382  =item RETURN  =item RETURN
1383    
1384  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
1385  their best hits.  on the target genome.
1386    
1387  =back  =back
1388    
# Line 1248  Line 1399 
1399                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1400                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1401                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1402                  # Look for the best hit.          # Peel off the BBHs found.
1403                  my $bbh = $query->Fetch;          my @found = ();
1404                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1405                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1406                  }                  }
1407            $retVal{$featureID} = \@found;
1408          }          }
1409          # Return the mapping.          # Return the mapping.
1410          return \%retVal;          return \%retVal;
1411  }  }
1412    
1413    =head3 SimList
1414    
1415    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1416    
1417    Return a list of the similarities to the specified feature.
1418    
1419    Sprout does not support real similarities, so this method just returns the bidirectional
1420    best hits.
1421    
1422    =over 4
1423    
1424    =item featureID
1425    
1426    ID of the feature whose similarities are desired.
1427    
1428    =item count
1429    
1430    Maximum number of similar features to be returned, or C<0> to return them all.
1431    
1432    =back
1433    
1434    =cut
1435    #: Return Type %;
1436    sub SimList {
1437        # Get the parameters.
1438        my ($self, $featureID, $count) = @_;
1439        # Ask for the best hits.
1440        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1441                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1442                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1443                                  $count);
1444        # Create the return value.
1445        my %retVal = ();
1446        for my $tuple (@lists) {
1447            $retVal{$tuple->[0]} = $tuple->[1];
1448        }
1449        # Return the result.
1450        return %retVal;
1451    }
1452    
1453    
1454    
1455    =head3 IsComplete
1456    
1457    C<< my $flag = $sprout->IsComplete($genomeID); >>
1458    
1459    Return TRUE if the specified genome is complete, else FALSE.
1460    
1461    =over 4
1462    
1463    =item genomeID
1464    
1465    ID of the genome whose completeness status is desired.
1466    
1467    =item RETURN
1468    
1469    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1470    not found.
1471    
1472    =back
1473    
1474    =cut
1475    #: Return Type $;
1476    sub IsComplete {
1477        # Get the parameters.
1478        my ($self, $genomeID) = @_;
1479        # Declare the return variable.
1480        my $retVal;
1481        # Get the genome's data.
1482        my $genomeData = $self->GetEntity('Genome', $genomeID);
1483        if ($genomeData) {
1484            # The genome exists, so get the completeness flag.
1485            ($retVal) = $genomeData->Value('Genome(complete)');
1486        }
1487        # Return the result.
1488        return $retVal;
1489    }
1490    
1491  =head3 FeatureAliases  =head3 FeatureAliases
1492    
1493  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1378  Line 1607 
1607          return %retVal;          return %retVal;
1608  }  }
1609    
1610    =head3 CouplingEvidence
1611    
1612    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1613    
1614    Return the evidence for a functional coupling.
1615    
1616    A pair of features is considered evidence of a coupling between two other
1617    features if they occur close together on a contig and both are similar to
1618    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1619    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1620    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1621    similar to B<A2>.
1622    
1623    The score of a coupling is determined by the number of pieces of evidence
1624    that are considered I<representative>. If several evidence items belong to
1625    a group of genomes that are close to each other, only one of those items
1626    is considered representative. The other evidence items are presumed to be
1627    there because of the relationship between the genomes rather than because
1628    the two proteins generated by the features have a related functionality.
1629    
1630    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1631    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1632    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1633    and FALSE otherwise.
1634    
1635    =over 4
1636    
1637    =item peg1
1638    
1639    ID of the feature of interest.
1640    
1641    =item peg2
1642    
1643    ID of a feature functionally coupled to the feature of interest.
1644    
1645    =item RETURN
1646    
1647    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1648    of interest, a feature similar to the functionally coupled feature, and a flag
1649    that is TRUE for a representative piece of evidence and FALSE otherwise.
1650    
1651    =back
1652    
1653    =cut
1654    #: Return Type @@;
1655    sub CouplingEvidence {
1656        # Get the parameters.
1657        my ($self, $peg1, $peg2) = @_;
1658        # Declare the return variable.
1659        my @retVal = ();
1660        # Our first task is to find out the nature of the coupling: whether or not
1661        # it exists, its score, and whether the features are stored in the same
1662        # order as the ones coming in.
1663        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1664        # Only proceed if a coupling exists.
1665        if ($couplingID) {
1666            # Determine the ordering to place on the evidence items. If we're
1667            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1668            # we want feature 1 before feature 2 (normal).
1669            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1670            my $ordering = ($inverted ? "DESC" : "");
1671            # Get the coupling evidence.
1672            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1673                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1674                                              [$couplingID],
1675                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1676            # Loop through the evidence items. Each piece of evidence is represented by two
1677            # positions in the evidence list, one for each feature on the other side of the
1678            # evidence link. If at some point we want to generalize to couplings with
1679            # more than two positions, this section of code will need to be re-done.
1680            while (@evidenceList > 0) {
1681                my $peg1Data = shift @evidenceList;
1682                my $peg2Data = shift @evidenceList;
1683                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1684                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1685            }
1686            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1687        }
1688        # Return the result.
1689        return @retVal;
1690    }
1691    
1692    =head3 GetCoupling
1693    
1694    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1695    
1696    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1697    exists, we return the coupling ID along with an indicator of whether the
1698    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1699    In the second case, we say the coupling is I<inverted>. The importance of an
1700    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1701    
1702    =over 4
1703    
1704    =item peg1
1705    
1706    ID of the feature of interest.
1707    
1708    =item peg2
1709    
1710    ID of the potentially coupled feature.
1711    
1712    =item RETURN
1713    
1714    Returns a three-element list. The first element contains the database ID of
1715    the coupling. The second element is FALSE if the coupling is stored in the
1716    database in the caller specified order and TRUE if it is stored in the
1717    inverted order. The third element is the coupling's score. If the coupling
1718    does not exist, all three list elements will be C<undef>.
1719    
1720    =back
1721    
1722    =cut
1723    #: Return Type $%@;
1724    sub GetCoupling {
1725        # Get the parameters.
1726        my ($self, $peg1, $peg2) = @_;
1727        # Declare the return values. We'll start with the coupling ID and undefine the
1728        # flag and score until we have more information.
1729        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1730        # Find the coupling data.
1731        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1732                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1733                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1734        # Check to see if we found anything.
1735        if (!@pegs) {
1736            Trace("No coupling found.") if T(Coupling => 4);
1737            # No coupling, so undefine the return value.
1738            $retVal = undef;
1739        } else {
1740            # We have a coupling! Get the score and check for inversion.
1741            $score = $pegs[0]->[1];
1742            my $firstFound = $pegs[0]->[0];
1743            $inverted = ($firstFound ne $peg1);
1744            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1745        }
1746        # Return the result.
1747        return ($retVal, $inverted, $score);
1748    }
1749    
1750    =head3 CouplingID
1751    
1752    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1753    
1754    Return the coupling ID for a pair of feature IDs.
1755    
1756    The coupling ID is currently computed by joining the feature IDs in
1757    sorted order with a space. Client modules (that is, modules which
1758    use Sprout) should not, however, count on this always being the
1759    case. This method provides a way for abstracting the concept of a
1760    coupling ID. All that we know for sure about it is that it can be
1761    generated easily from the feature IDs and the order of the IDs
1762    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1763    will have the same value as C<CouplingID("b1", "a1")>.
1764    
1765    =over 4
1766    
1767    =item peg1
1768    
1769    First feature of interest.
1770    
1771    =item peg2
1772    
1773    Second feature of interest.
1774    
1775    =item RETURN
1776    
1777    Returns the ID that would be used to represent a functional coupling of
1778    the two specified PEGs.
1779    
1780    =back
1781    
1782    =cut
1783    #: Return Type $;
1784    sub CouplingID {
1785        return join " ", sort @_;
1786    }
1787    
1788  =head3 GetEntityTypes  =head3 GetEntityTypes
1789    
1790  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1439  Line 1846 
1846                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1847                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1848                          if ($id) {                          if ($id) {
1849                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1850                          }                          }
1851                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1852                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1853                  } else {                  } else {
1854                          # 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.
1855                          # 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
1856                          # case.                          # case.
1857                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1858                          $sequence .= $1;                          $sequence .= $1;
# Line 1453  Line 1860 
1860          }          }
1861          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1862          if ($sequence) {          if ($sequence) {
1863                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1864          }          }
1865          # Close the file.          # Close the file.
1866          close FASTAFILE;          close FASTAFILE;
# Line 1572  Line 1979 
1979  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
1980  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>.
1981    
1982  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<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1983    
1984  =over 4  =over 4
1985    
# Line 1779  Line 2186 
2186          # Get the parameters.          # Get the parameters.
2187          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2188          # Check for the entity instance.          # Check for the entity instance.
2189        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2190          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2191          # Return an existence indicator.          # Return an existence indicator.
2192          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1970  Line 2378 
2378          return @retVal;          return @retVal;
2379  }  }
2380    
2381    =head3 GetProperties
2382    
2383    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2384    
2385    Return a list of the properties with the specified characteristics.
2386    
2387    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2388    will also be associated with genomes.) A property value is represented by a 4-tuple of
2389    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2390    
2391    =over 4
2392    
2393    =item fid
2394    
2395    ID of the feature possessing the property.
2396    
2397    =item key
2398    
2399    Name or key of the property.
2400    
2401    =item value
2402    
2403    Value of the property.
2404    
2405    =item url
2406    
2407    URL of the document that indicated the property should have this particular value, or an
2408    empty string if no such document exists.
2409    
2410    =back
2411    
2412    The parameters act as a filter for the desired data. Any non-null parameter will
2413    automatically match all the tuples returned. So, specifying just the I<$fid> will
2414    return all the properties of the specified feature; similarly, specifying the I<$key>
2415    and I<$value> parameters will return all the features having the specified property
2416    value.
2417    
2418    A single property key can have many values, representing different ideas about the
2419    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2420    virulent, and another may declare that it is not virulent. A query about the virulence of
2421    C<fig|83333.1.peg.10> would be coded as
2422    
2423        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2424    
2425    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2426    not to be filtered. The tuples returned would be
2427    
2428        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2429        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2430    
2431    =cut
2432    #: Return Type @@;
2433    sub GetProperties {
2434        # Get the parameters.
2435        my ($self, @parms) = @_;
2436        # Declare the return variable.
2437        my @retVal = ();
2438        # Now we need to create a WHERE clause that will get us the data we want. First,
2439        # we create a list of the columns containing the data for each parameter.
2440        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2441                        'Property(property-value)', 'HasProperty(evidence)');
2442        # Now we build the WHERE clause and the list of parameter values.
2443        my @where = ();
2444        my @values = ();
2445        for (my $i = 0; $i <= $#colNames; $i++) {
2446            my $parm = $parms[$i];
2447            if (defined $parm && ($parm ne '')) {
2448                push @where, "$colNames[$i] = ?";
2449                push @values, $parm;
2450            }
2451        }
2452        # Format the WHERE clause.
2453        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2454        # Ask for all the propertie values with the desired characteristics.
2455        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2456        while (my $valueObject = $query->Fetch()) {
2457            my @tuple = $valueObject->Values(\@colNames);
2458            push @retVal, \@tuple;
2459        }
2460        # Return the result.
2461        return @retVal;
2462    }
2463    
2464  =head3 FeatureProperties  =head3 FeatureProperties
2465    
2466  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2164  Line 2655 
2655  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2656    
2657  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
2658  to the role the feature performs.  to the roles the feature performs.
2659    
2660  =over 4  =over 4
2661    
# Line 2174  Line 2665 
2665    
2666  =item RETURN  =item RETURN
2667    
2668  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.
2669    
2670  =back  =back
2671    
2672  =cut  =cut
2673  #: Return Type %;  #: Return Type %@;
2674  sub SubsystemsOf {  sub SubsystemsOf {
2675          # Get the parameters.          # Get the parameters.
2676          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2677          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2678          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2679                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2680                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2681          # Create the return value.          # Create the return value.
2682          my %retVal = ();          my %retVal = ();
2683        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2684        # in two spreadsheet cells.
2685        my %dupHash = ();
2686          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2687          for my $record (@subsystems) {          for my $record (@subsystems) {
2688                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2689            my ($subsys, $role) = @{$record};
2690            # Insure it's the first time for both.
2691            my $dupKey = "$subsys\n$role";
2692            if (! exists $dupHash{"$subsys\n$role"}) {
2693                $dupHash{$dupKey} = 1;
2694                push @{$retVal{$subsys}}, $role;
2695            }
2696          }          }
2697          # Return the hash.          # Return the hash.
2698          return %retVal;          return %retVal;
2699  }  }
2700    
2701    =head3 SubsystemList
2702    
2703    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2704    
2705    Return a list containing the names of the subsystems in which the specified
2706    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2707    subsystem names, not the roles.
2708    
2709    =over 4
2710    
2711    =item featureID
2712    
2713    ID of the feature whose subsystem names are desired.
2714    
2715    =item RETURN
2716    
2717    Returns a list of the names of the subsystems in which the feature participates.
2718    
2719    =back
2720    
2721    =cut
2722    #: Return Type @;
2723    sub SubsystemList {
2724        # Get the parameters.
2725        my ($self, $featureID) = @_;
2726        # Get the list of names.
2727        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2728                                    [$featureID], 'HasSSCell(from-link)');
2729        # Return the result.
2730        return @retVal;
2731    }
2732    
2733  =head3 RelatedFeatures  =head3 RelatedFeatures
2734    
2735  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2615  Line 3148 
3148      return %retVal;      return %retVal;
3149  }  }
3150    
3151    =head3 MyGenomes
3152    
3153    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3154    
3155    Return a list of the genomes to be included in the Sprout.
3156    
3157    This method is provided for use during the Sprout load. It presumes the Genome load file has
3158    already been created. (It will be in the Sprout data directory and called either C<Genome>
3159    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3160    IDs.
3161    
3162    =over 4
3163    
3164    =item dataDir
3165    
3166    Directory containing the Sprout load files.
3167    
3168    =back
3169    
3170    =cut
3171    #: Return Type @;
3172    sub MyGenomes {
3173        # Get the parameters.
3174        my ($dataDir) = @_;
3175        # Compute the genome file name.
3176        my $genomeFileName = LoadFileName($dataDir, "Genome");
3177        # Extract the genome IDs from the files.
3178        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3179        # Return the result.
3180        return @retVal;
3181    }
3182    
3183    =head3 LoadFileName
3184    
3185    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3186    
3187    Return the name of the load file for the specified table in the specified data
3188    directory.
3189    
3190    =over 4
3191    
3192    =item dataDir
3193    
3194    Directory containing the Sprout load files.
3195    
3196    =item tableName
3197    
3198    Name of the table whose load file is desired.
3199    
3200    =item RETURN
3201    
3202    Returns the name of the file containing the load data for the specified table, or
3203    C<undef> if no load file is present.
3204    
3205    =back
3206    
3207    =cut
3208    #: Return Type $;
3209    sub LoadFileName {
3210        # Get the parameters.
3211        my ($dataDir, $tableName) = @_;
3212        # Declare the return variable.
3213        my $retVal;
3214        # Check for the various file names.
3215        if (-e "$dataDir/$tableName") {
3216            $retVal = "$dataDir/$tableName";
3217        } elsif (-e "$dataDir/$tableName.dtx") {
3218            $retVal = "$dataDir/$tableName.dtx";
3219        }
3220        # Return the result.
3221        return $retVal;
3222    }
3223    
3224    =head3 DeleteGenome
3225    
3226    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3227    
3228    Delete a genome from the database.
3229    
3230    =over 4
3231    
3232    =item genomeID
3233    
3234    ID of the genome to delete
3235    
3236    =item testFlag
3237    
3238    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3239    
3240    =item RETURN
3241    
3242    Returns a statistics object describing the rows deleted.
3243    
3244    =back
3245    
3246    =cut
3247    #: Return Type $%;
3248    sub DeleteGenome {
3249        # Get the parameters.
3250        my ($self, $genomeID, $testFlag) = @_;
3251        # Perform the delete for the genome's features.
3252        my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);
3253        # Perform the delete for the primary genome data.
3254        my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);
3255        $retVal->Accumulate($stats);
3256        # Return the result.
3257        return $retVal;
3258    }
3259    
3260  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3261    
3262  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2625  Line 3267 
3267    
3268  A functional assignment is always of the form  A functional assignment is always of the form
3269    
3270      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3271    
3272    where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3273    the user and the assigning user (from MadeAnnotation) will be the same, but that is
3274    not always the case.
3275    
3276  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  In addition, the functional role may contain extra data that is stripped, such as
3277  actual functional role. In most cases, the user and the assigning user will be the  terminating spaces or a comment separated from the rest of the text by a tab.
 same, but that is not always the case.  
3278    
3279  This is a static method.  This is a static method.
3280    
3281  =over 4  =over 4
3282    
3283    =item user
3284    
3285    Name of the assigning user.
3286    
3287  =item text  =item text
3288    
3289  Text of the annotation.  Text of the annotation.
# Line 2650  Line 3299 
3299    
3300  sub _ParseAssignment {  sub _ParseAssignment {
3301          # Get the parameters.          # Get the parameters.
3302          my ($text) = @_;      my ($user, $text) = @_;
3303          # Declare the return value.          # Declare the return value.
3304          my @retVal = ();          my @retVal = ();
3305          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3306          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3307          if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3308                  # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3309          # and the assigning user.          @retVal = ($user, $function);
3310                  @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3311            # Here we have an assignment with a user that is passed back to the caller.
3312            @retVal = ($1, $function);
3313        }
3314        # If we have an assignment, we need to clean the function text. There may be
3315        # extra junk at the end added as a note from the user.
3316        if (@retVal) {
3317            $retVal[1] =~ s/(\t\S)?\s*$//;
3318          }          }
3319          # Return the result list.          # Return the result list.
3320          return @retVal;          return @retVal;
# Line 2686  Line 3342 
3342    
3343  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3344      my ($timeValue) = @_;      my ($timeValue) = @_;
3345      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3346      return $retVal;      return $retVal;
3347  }  }
3348    
3349    =head3 AddProperty
3350    
3351    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3352    
3353    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3354    be added to almost any object. In Sprout, they can only be added to features. In
3355    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3356    pair. If the particular key/value pair coming in is not already in the database, a new
3357    B<Property> record is created to hold it.
3358    
3359    =over 4
3360    
3361    =item peg
3362    
3363    ID of the feature to which the attribute is to be replied.
3364    
3365    =item key
3366    
3367    Name of the attribute (key).
3368    
3369    =item value
3370    
3371    Value of the attribute.
3372    
3373    =item url
3374    
3375    URL or text citation from which the property was obtained.
3376    
3377    =back
3378    
3379    =cut
3380    #: Return Type ;
3381    sub AddProperty {
3382        # Get the parameters.
3383        my ($self, $featureID, $key, $value, $url) = @_;
3384        # Declare the variable to hold the desired property ID.
3385        my $propID;
3386        # Attempt to find a property record for this key/value pair.
3387        my @properties = $self->GetFlat(['Property'],
3388                                       "Property(property-name) = ? AND Property(property-value) = ?",
3389                                       [$key, $value], 'Property(id)');
3390        if (@properties) {
3391            # Here the property is already in the database. We save its ID.
3392            $propID = $properties[0];
3393            # Here the property value does not exist. We need to generate an ID. It will be set
3394            # to a number one greater than the maximum value in the database. This call to
3395            # GetAll will stop after one record.
3396            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3397                                            1);
3398            $propID = $maxProperty[0]->[0] + 1;
3399            # Insert the new property value.
3400            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3401        }
3402        # Now we connect the incoming feature to the property.
3403        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3404    }
3405    
3406    
3407  1;  1;

Legend:
Removed from v.1.14  
changed lines
  Added in v.1.53

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3