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

Diff of /Sprout/Sprout.pm

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

revision 1.15, Wed Jun 22 21:30:45 2005 UTC revision 1.48, Thu Oct 20 12:33:00 2005 UTC
# Line 70  Line 70 
70    
71  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72    
73    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74    
75  =back  =back
76    
77  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
# Line 86  Line 88 
88      # Compute the options. We do this by starting with a table of defaults and overwriting with      # Compute the options. We do this by starting with a table of defaults and overwriting with
89      # the incoming data.      # the incoming data.
90      my $optionTable = Tracer::GetOptions({      my $optionTable = Tracer::GetOptions({
91                         dbType       => 'mysql',         # database type                         dbType       => $FIG_Config::dbms,
92                         dataDir      => 'Data',          # data file directory                                                          # database type
93                         xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
94                         userData     => 'root/',         # user name and password                                                          # data file directory
95                         port         => 0,               # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
96                                                            # database definition file name
97                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98                                                            # user name and password
99                           port         => $FIG_Config::dbport,
100                                                            # database connection port
101                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
102                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
103                           noDBOpen     => 0,               # 1 to suppress the database open
104                        }, $options);                        }, $options);
105      # Get the data directory.      # Get the data directory.
106      my $dataDir = $optionTable->{dataDir};      my $dataDir = $optionTable->{dataDir};
# Line 100  Line 108 
108      $optionTable->{userData} =~ m!([^/]*)/(.*)$!;      $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109      my ($userName, $password) = ($1, $2);      my ($userName, $password) = ($1, $2);
110      # Connect to the database.      # Connect to the database.
111      my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
112        if (! $optionTable->{noDBOpen}) {
113            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114                                    $password, $optionTable->{port});
115        }
116      # Create the ERDB object.      # Create the ERDB object.
117      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
118      my $erdb = ERDB->new($dbh, $xmlFileName);      my $erdb = ERDB->new($dbh, $xmlFileName);
# Line 377  Line 389 
389    
390  =head3 LoadUpdate  =head3 LoadUpdate
391    
392  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
393    
394  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
395  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 420  Line 432 
432      # Loop through the incoming table names.      # Loop through the incoming table names.
433      for my $tableName (@{$tableList}) {      for my $tableName (@{$tableList}) {
434          # Find the table's file.          # Find the table's file.
435          my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436          if (! -e $fileName) {          if (! $fileName) {
437              $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438          }          } else {
439          # Attempt to load this table.          # Attempt to load this table.
440          my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);          my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441          # Accumulate the resulting statistics.          # Accumulate the resulting statistics.
442          $retVal->Accumulate($result);          $retVal->Accumulate($result);
443      }      }
444        }
445      # Return the statistics.      # Return the statistics.
446      return $retVal;      return $retVal;
447  }  }
# Line 570  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 597  Line 610 
610          if ($prevContig eq $contigID && $dir eq $prevDir) {          if ($prevContig eq $contigID && $dir eq $prevDir) {
611              # Here the new segment is in the same direction on the same contig. Insure the              # Here the new segment is in the same direction on the same contig. Insure the
612              # new segment's beginning is next to the old segment's end.              # new segment's beginning is next to the old segment's end.
613              if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
614                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
615                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
616                  # to include both segments.                  $len += $prevLen;
617                    # Pop the old segment off. The new one will replace it later.
618                    pop @retVal;
619                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
620                    # Here we need to merge two forward blocks. Adjust the beginning and
621                    # length values to include both segments.
622                  $beg = $prevBeg;                  $beg = $prevBeg;
623                  $len += $prevLen;                  $len += $prevLen;
624                  # Pop the old segment off. The new one will replace it later.                  # Pop the old segment off. The new one will replace it later.
# Line 609  Line 627 
627          }          }
628          # Remember this specifier for the adjacent-segment test the next time through.          # Remember this specifier for the adjacent-segment test the next time through.
629          ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);          ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
630            # Compute the initial base pair.
631            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
632          # Add the specifier to the list.          # Add the specifier to the list.
633          push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
634      }      }
635      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
636      return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
637  }  }
638    
639  =head3 ParseLocation  =head3 ParseLocation
# Line 644  Line 664 
664      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
665      my ($location) = @_;      my ($location) = @_;
666      # Parse it into segments.      # Parse it into segments.
667      $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
668      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
669      # If the direction is an underscore, convert it to a + or -.      # If the direction is an underscore, convert it to a + or -.
670      if ($dir eq "_") {      if ($dir eq "_") {
# Line 752  Line 772 
772          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
773          # before putting it in the return value.          # before putting it in the return value.
774          my ($start, $stop);          my ($start, $stop);
775            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
776          if ($dir eq "+") {          if ($dir eq "+") {
777              $start = $beg;              $start = $beg;
778              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
779          } else {          } else {
780              $start = $beg + $len + 1;              $start = $beg - $len + 1;
781              $stop = $beg;              $stop = $beg;
782          }          }
783            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
784          my $query = $self->Get(['IsMadeUpOf','Sequence'],          my $query = $self->Get(['IsMadeUpOf','Sequence'],
785              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
786              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 792 
792                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
793                                     'IsMadeUpOf(len)']);                                     'IsMadeUpOf(len)']);
794              my $stopPosition = $startPosition + $sequenceLength;              my $stopPosition = $startPosition + $sequenceLength;
795                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
796              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
797              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
798              my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
799                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
800              # Add the relevant data to the location data.              # Add the relevant data to the location data.
801              $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
802          }          }
803          # Add this location's data to the return string. Note that we may need to reverse it.          # Add this location's data to the return string. Note that we may need to reverse it.
804          if ($dir eq '+') {          if ($dir eq '+') {
805              $retVal .= $locationDNA;              $retVal .= $locationDNA;
806          } else {          } else {
807              $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
             $retVal .= $locationDNA;  
808          }          }
809      }      }
810      # Return the result.      # Return the result.
# Line 851  Line 874 
874      # Set it from the sequence data, if any.      # Set it from the sequence data, if any.
875      if ($sequence) {      if ($sequence) {
876          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
877          $retVal = $start + $len;          $retVal = $start + $len - 1;
878        }
879        # Return the result.
880        return $retVal;
881    }
882    
883    =head3 ClusterPEGs
884    
885    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
886    
887    Cluster the PEGs in a list according to the cluster coding scheme of the specified
888    subsystem. In order for this to work properly, the subsystem object must have
889    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
890    This causes the cluster numbers to be pulled into the subsystem's color hash.
891    If a PEG is not found in the color hash, it will not appear in the output
892    sequence.
893    
894    =over 4
895    
896    =item sub
897    
898    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
899    method.
900    
901    =item pegs
902    
903    Reference to the list of PEGs to be clustered.
904    
905    =item RETURN
906    
907    Returns a list of the PEGs, grouped into smaller lists by cluster number.
908    
909    =back
910    
911    =cut
912    #: Return Type $@@;
913    sub ClusterPEGs {
914        # Get the parameters.
915        my ($self, $sub, $pegs) = @_;
916        # Declare the return variable.
917        my $retVal = [];
918        # Loop through the PEGs, creating arrays for each cluster.
919        for my $pegID (@{$pegs}) {
920            my $clusterNumber = $sub->get_cluster_number($pegID);
921            # Only proceed if the PEG is in a cluster.
922            if ($clusterNumber >= 0) {
923                # Push this PEG onto the sub-list for the specified cluster number.
924                push @{$retVal->[$clusterNumber]}, $pegID;
925            }
926      }      }
927      # Return the result.      # Return the result.
928      return $retVal;      return $retVal;
# Line 1001  Line 1072 
1072    
1073  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1074    
1075  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1076    
1077  Return the annotations of a feature.  Return the annotations of a feature.
1078    
# Line 1011  Line 1082 
1082    
1083  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1084    
1085    =item rawFlag
1086    
1087    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1088    will be returned in human-readable form.
1089    
1090  =item RETURN  =item RETURN
1091    
1092  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1093    
1094  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1095    
1096  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1097    
1098  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1099    
# Line 1029  Line 1105 
1105  #: Return Type @%;  #: Return Type @%;
1106  sub FeatureAnnotations {  sub FeatureAnnotations {
1107      # Get the parameters.      # Get the parameters.
1108      my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1109      # Create a query to get the feature's annotations and the associated users.      # Create a query to get the feature's annotations and the associated users.
1110      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1111                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1118 
1118              $annotation->Values(['IsTargetOfAnnotation(from-link)',              $annotation->Values(['IsTargetOfAnnotation(from-link)',
1119                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1120                                   'Annotation(annotation)']);                                   'Annotation(annotation)']);
1121            # Convert the time, if necessary.
1122            if (! $rawFlag) {
1123                $timeStamp = FriendlyTimestamp($timeStamp);
1124            }
1125          # Assemble them into a hash.          # Assemble them into a hash.
1126          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1127                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1128                                 user => $user, text => $text };                                 user => $user, text => $text };
1129          # Add it to the return list.          # Add it to the return list.
1130          push @retVal, $annotationHash;          push @retVal, $annotationHash;
# Line 1073  Line 1153 
1153    
1154  =item RETURN  =item RETURN
1155    
1156  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1157    
1158  =back  =back
1159    
# Line 1083  Line 1163 
1163      # Get the parameters.      # Get the parameters.
1164      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1165      # Get all of the feature's annotations.      # Get all of the feature's annotations.
1166      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1167                              "IsTargetOfAnnotation(from-link) = ?",                              "IsTargetOfAnnotation(from-link) = ?",
1168                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1169                                               'MadeAnnotation(from-link)']);
1170      # Declare the return hash.      # Declare the return hash.
1171      my %retVal;      my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1172      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1173      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1174      # Loop until we run out of annotations.      # Loop until we run out of annotations.
1175      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1176          # Get the annotation fields.          # Get the annotation fields.
1177          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1178          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
1179          my ($user, $function) = _ParseAssignment($text);          my ($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) {              if ($actualUser) {
1274                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1275                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1276                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1211  Line 1289 
1289      return $retVal;      return $retVal;
1290  }  }
1291    
1292    =head3 FunctionsOf
1293    
1294    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1295    
1296    Return the functional assignments of a particular feature.
1297    
1298    The functional assignment is handled differently depending on the type of feature. If
1299    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1300    assignment is a type of annotation. The format of an assignment is described in
1301    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1302    annotation itself because it's a text field; however, this is not a big problem because
1303    most features only have a small number of annotations.
1304    
1305    If the feature is B<not> identified by a FIG ID, then the functional assignment
1306    information is taken from the B<ExternalAliasFunc> table. If the table does
1307    not contain an entry for the feature, an empty list is returned.
1308    
1309    =over 4
1310    
1311    =item featureID
1312    
1313    ID of the feature whose functional assignments are desired.
1314    
1315    =item RETURN
1316    
1317    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1318    that user.
1319    
1320    =back
1321    
1322    =cut
1323    #: Return Type @@;
1324    sub FunctionsOf {
1325        # Get the parameters.
1326        my ($self, $featureID) = @_;
1327        # Declare the return value.
1328        my @retVal = ();
1329        # Determine the ID type.
1330        if ($featureID =~ m/^fig\|/) {
1331            # Here we have a FIG feature ID. We must build the list of trusted
1332            # users.
1333            my %trusteeTable = ();
1334            # Build a query for all of the feature's annotations, sorted by date.
1335            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1336                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1337                                   [$featureID]);
1338            my $timeSelected = 0;
1339            # Loop until we run out of annotations.
1340            while (my $annotation = $query->Fetch()) {
1341                # Get the annotation text.
1342                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1343                                                                'Annotation(time)',
1344                                                                'MadeAnnotation(user)']);
1345                # Check to see if this is a functional assignment for a trusted user.
1346                my ($actualUser, $function) = _ParseAssignment($user, $text);
1347                if ($actualUser) {
1348                    # Here it is a functional assignment.
1349                    push @retVal, [$actualUser, $function];
1350                }
1351            }
1352        } else {
1353            # Here we have a non-FIG feature ID. In this case the user ID does not
1354            # matter. We simply get the information from the External Alias Function
1355            # table.
1356            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1357                                                     ['ExternalAliasFunc(func)']);
1358            push @retVal, map { ['master', $_] } @assignments;
1359        }
1360        # Return the assignments found.
1361        return @retVal;
1362    }
1363    
1364  =head3 BBHList  =head3 BBHList
1365    
1366  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1248  Line 1398 
1398          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $query = $self->Get(['IsBidirectionalBestHitOf'],
1399                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1400                                 [$featureID, $genomeID]);                                 [$featureID, $genomeID]);
1401          # Look for the best hit.          # Peel off the BBHs found.
1402          my $bbh = $query->Fetch;          my @found = ();
1403          if ($bbh) {          while (my $bbh = $query->Fetch) {
1404              my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
             $retVal{$featureID} = $targetFeature;  
1405          }          }
1406            $retVal{$featureID} = \@found;
1407      }      }
1408      # Return the mapping.      # Return the mapping.
1409      return \%retVal;      return \%retVal;
# Line 1506  Line 1656 
1656      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1657      # Declare the return variable.      # Declare the return variable.
1658      my @retVal = ();      my @retVal = ();
1659      # Our first task is to find out the nature of the coupling.      # Our first task is to find out the nature of the coupling: whether or not
1660        # it exists, its score, and whether the features are stored in the same
1661        # order as the ones coming in.
1662      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1663      # Only proceed if a coupling exists.      # Only proceed if a coupling exists.
1664      if ($couplingID) {      if ($couplingID) {
1665          # Determine the ordering to place on the evidence items. If we're          # Determine the ordering to place on the evidence items. If we're
1666          # inverted, we want to see feature 2 before feature 1; otherwise,          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1667          # we want the reverse.          # we want feature 1 before feature 2 (normal).
1668            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1669          my $ordering = ($inverted ? "DESC" : "");          my $ordering = ($inverted ? "DESC" : "");
1670          # Get the coupling evidence.          # Get the coupling evidence.
1671          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1672                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1673                                            [$couplingID],                                            [$couplingID],
1674                                            ['PCH(used)', 'UsesAsEvidence(pos)']);                                            ['PCH(used)', 'UsesAsEvidence(to-link)']);
1675          # Loop through the evidence items. Each piece of evidence is represented by two          # Loop through the evidence items. Each piece of evidence is represented by two
1676          # positions in the evidence list, one for each feature on the other side of the          # positions in the evidence list, one for each feature on the other side of the
1677          # evidence link. If at some point we want to generalize to couplings with          # evidence link. If at some point we want to generalize to couplings with
# Line 1526  Line 1679 
1679          while (@evidenceList > 0) {          while (@evidenceList > 0) {
1680              my $peg1Data = shift @evidenceList;              my $peg1Data = shift @evidenceList;
1681              my $peg2Data = shift @evidenceList;              my $peg2Data = shift @evidenceList;
1682                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1683              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1684          }          }
1685            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1686      }      }
     # TODO: code  
1687      # Return the result.      # Return the result.
1688      return @retVal;      return @retVal;
1689  }  }
# Line 1575  Line 1729 
1729      # Find the coupling data.      # Find the coupling data.
1730      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1731                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1732                                   [$retVal], "ParticipatesInCoupling(from-link), Coupling(score)");                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1733      # Check to see if we found anything.      # Check to see if we found anything.
1734      if (!@pegs) {      if (!@pegs) {
1735            Trace("No coupling found.") if T(Coupling => 4);
1736          # No coupling, so undefine the return value.          # No coupling, so undefine the return value.
1737          $retVal = undef;          $retVal = undef;
1738      } else {      } else {
1739          # We have a coupling! Get the score and check for inversion.          # We have a coupling! Get the score and check for inversion.
1740          $score = $pegs[0]->[1];          $score = $pegs[0]->[1];
1741          $inverted = ($pegs[0]->[0] eq $peg1);          my $firstFound = $pegs[0]->[0];
1742            $inverted = ($firstFound ne $peg1);
1743            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1744      }      }
1745      # Return the result.      # Return the result.
1746      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
# Line 1688  Line 1845 
1845          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1846              # Here we have a new header. Store the current sequence if we have one.              # Here we have a new header. Store the current sequence if we have one.
1847              if ($id) {              if ($id) {
1848                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1849              }              }
1850              # Clear the sequence accumulator and save the new ID.              # Clear the sequence accumulator and save the new ID.
1851              ($id, $sequence) = ("$prefix$1", "");              ($id, $sequence) = ("$prefix$1", "");
1852          } else {          } else {
1853              # 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.
1854              # 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
1855              # case.              # case.
1856              $line =~ /^\s*(.*?)(\s|\n)/;              $line =~ /^\s*(.*?)(\s|\n)/;
1857              $sequence .= $1;              $sequence .= $1;
# Line 1702  Line 1859 
1859      }      }
1860      # Flush out the last sequence (if any).      # Flush out the last sequence (if any).
1861      if ($sequence) {      if ($sequence) {
1862          $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1863      }      }
1864      # Close the file.      # Close the file.
1865      close FASTAFILE;      close FASTAFILE;
# Line 2028  Line 2185 
2185      # Get the parameters.      # Get the parameters.
2186      my ($self, $entityName, $entityID) = @_;      my ($self, $entityName, $entityID) = @_;
2187      # Check for the entity instance.      # Check for the entity instance.
2188        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2189      my $testInstance = $self->GetEntity($entityName, $entityID);      my $testInstance = $self->GetEntity($entityName, $entityID);
2190      # Return an existence indicator.      # Return an existence indicator.
2191      my $retVal = ($testInstance ? 1 : 0);      my $retVal = ($testInstance ? 1 : 0);
# Line 2219  Line 2377 
2377      return @retVal;      return @retVal;
2378  }  }
2379    
2380    =head3 GetProperties
2381    
2382    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2383    
2384    Return a list of the properties with the specified characteristics.
2385    
2386    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2387    will also be associated with genomes.) A property value is represented by a 4-tuple of
2388    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2389    
2390    =over 4
2391    
2392    =item fid
2393    
2394    ID of the feature possessing the property.
2395    
2396    =item key
2397    
2398    Name or key of the property.
2399    
2400    =item value
2401    
2402    Value of the property.
2403    
2404    =item url
2405    
2406    URL of the document that indicated the property should have this particular value, or an
2407    empty string if no such document exists.
2408    
2409    =back
2410    
2411    The parameters act as a filter for the desired data. Any non-null parameter will
2412    automatically match all the tuples returned. So, specifying just the I<$fid> will
2413    return all the properties of the specified feature; similarly, specifying the I<$key>
2414    and I<$value> parameters will return all the features having the specified property
2415    value.
2416    
2417    A single property key can have many values, representing different ideas about the
2418    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2419    virulent, and another may declare that it is not virulent. A query about the virulence of
2420    C<fig|83333.1.peg.10> would be coded as
2421    
2422        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2423    
2424    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2425    not to be filtered. The tuples returned would be
2426    
2427        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2428        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2429    
2430    =cut
2431    #: Return Type @@;
2432    sub GetProperties {
2433        # Get the parameters.
2434        my ($self, @parms) = @_;
2435        # Declare the return variable.
2436        my @retVal = ();
2437        # Now we need to create a WHERE clause that will get us the data we want. First,
2438        # we create a list of the columns containing the data for each parameter.
2439        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2440                        'Property(property-value)', 'HasProperty(evidence)');
2441        # Now we build the WHERE clause and the list of parameter values.
2442        my @where = ();
2443        my @values = ();
2444        for (my $i = 0; $i <= $#colNames; $i++) {
2445            my $parm = $parms[$i];
2446            if (defined $parm && ($parm ne '')) {
2447                push @where, "$colNames[$i] = ?";
2448                push @values, $parm;
2449            }
2450        }
2451        # Format the WHERE clause.
2452        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2453        # Ask for all the propertie values with the desired characteristics.
2454        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2455        while (my $valueObject = $query->Fetch()) {
2456            my @tuple = $valueObject->Values(\@colNames);
2457            push @retVal, \@tuple;
2458        }
2459        # Return the result.
2460        return @retVal;
2461    }
2462    
2463  =head3 FeatureProperties  =head3 FeatureProperties
2464    
2465  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2413  Line 2654 
2654  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2655    
2656  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
2657  to the role the feature performs.  to the roles the feature performs.
2658    
2659  =over 4  =over 4
2660    
# Line 2423  Line 2664 
2664    
2665  =item RETURN  =item RETURN
2666    
2667  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.
2668    
2669  =back  =back
2670    
2671  =cut  =cut
2672  #: Return Type %;  #: Return Type %@;
2673  sub SubsystemsOf {  sub SubsystemsOf {
2674      # Get the parameters.      # Get the parameters.
2675      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2676      # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2677      my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],      my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2678                                      "ContainsFeature(to-link) = ?", [$featureID],                                      "ContainsFeature(to-link) = ?", [$featureID],
2679                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2680      # Create the return value.      # Create the return value.
2681      my %retVal = ();      my %retVal = ();
2682        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2683        # in two spreadsheet cells.
2684        my %dupHash = ();
2685      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
2686      for my $record (@subsystems) {      for my $record (@subsystems) {
2687          $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2688            my ($subsys, $role) = @{$record};
2689            # Insure it's the first time for both.
2690            my $dupKey = "$subsys\n$role";
2691            if (! exists $dupHash{"$subsys\n$role"}) {
2692                $dupHash{$dupKey} = 1;
2693                push @{$retVal{$subsys}}, $role;
2694            }
2695      }      }
2696      # Return the hash.      # Return the hash.
2697      return %retVal;      return %retVal;
2698  }  }
2699    
2700    =head3 SubsystemList
2701    
2702    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2703    
2704    Return a list containing the names of the subsystems in which the specified
2705    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2706    subsystem names, not the roles.
2707    
2708    =over 4
2709    
2710    =item featureID
2711    
2712    ID of the feature whose subsystem names are desired.
2713    
2714    =item RETURN
2715    
2716    Returns a list of the names of the subsystems in which the feature participates.
2717    
2718    =back
2719    
2720    =cut
2721    #: Return Type @;
2722    sub SubsystemList {
2723        # Get the parameters.
2724        my ($self, $featureID) = @_;
2725        # Get the list of names.
2726        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2727                                    [$featureID], 'HasSSCell(from-link)');
2728        # Return the result.
2729        return @retVal;
2730    }
2731    
2732  =head3 RelatedFeatures  =head3 RelatedFeatures
2733    
2734  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2864  Line 3147 
3147      return %retVal;      return %retVal;
3148  }  }
3149    
3150    =head3 MyGenomes
3151    
3152    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3153    
3154    Return a list of the genomes to be included in the Sprout.
3155    
3156    This method is provided for use during the Sprout load. It presumes the Genome load file has
3157    already been created. (It will be in the Sprout data directory and called either C<Genome>
3158    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3159    IDs.
3160    
3161    =over 4
3162    
3163    =item dataDir
3164    
3165    Directory containing the Sprout load files.
3166    
3167    =back
3168    
3169    =cut
3170    #: Return Type @;
3171    sub MyGenomes {
3172        # Get the parameters.
3173        my ($dataDir) = @_;
3174        # Compute the genome file name.
3175        my $genomeFileName = LoadFileName($dataDir, "Genome");
3176        # Extract the genome IDs from the files.
3177        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3178        # Return the result.
3179        return @retVal;
3180    }
3181    
3182    =head3 LoadFileName
3183    
3184    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3185    
3186    Return the name of the load file for the specified table in the specified data
3187    directory.
3188    
3189    =over 4
3190    
3191    =item dataDir
3192    
3193    Directory containing the Sprout load files.
3194    
3195    =item tableName
3196    
3197    Name of the table whose load file is desired.
3198    
3199    =item RETURN
3200    
3201    Returns the name of the file containing the load data for the specified table, or
3202    C<undef> if no load file is present.
3203    
3204    =back
3205    
3206    =cut
3207    #: Return Type $;
3208    sub LoadFileName {
3209        # Get the parameters.
3210        my ($dataDir, $tableName) = @_;
3211        # Declare the return variable.
3212        my $retVal;
3213        # Check for the various file names.
3214        if (-e "$dataDir/$tableName") {
3215            $retVal = "$dataDir/$tableName";
3216        } elsif (-e "$dataDir/$tableName.dtx") {
3217            $retVal = "$dataDir/$tableName.dtx";
3218        }
3219        # Return the result.
3220        return $retVal;
3221    }
3222    
3223  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3224    
3225  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2874  Line 3230 
3230    
3231  A functional assignment is always of the form  A functional assignment is always of the form
3232    
3233      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3234    
3235  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3236  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
3237  same, but that is not always the case.  not always the case.
3238    
3239  This is a static method.  This is a static method.
3240    
3241  =over 4  =over 4
3242    
3243    =item user
3244    
3245    Name of the assigning user.
3246    
3247  =item text  =item text
3248    
3249  Text of the annotation.  Text of the annotation.
# Line 2899  Line 3259 
3259    
3260  sub _ParseAssignment {  sub _ParseAssignment {
3261      # Get the parameters.      # Get the parameters.
3262      my ($text) = @_;      my ($user, $text) = @_;
3263      # Declare the return value.      # Declare the return value.
3264      my @retVal = ();      my @retVal = ();
3265      # Check to see if this is a functional assignment.      # Check to see if this is a functional assignment.
3266      my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3267      if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3268          # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3269          # and the assigning user.          @retVal = ($user, $function);
3270          @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3271            # Here we have an assignment with a user, that is passed back to the caller.
3272            @retVal = ($1, $function);
3273      }      }
3274      # Return the result list.      # Return the result list.
3275      return @retVal;      return @retVal;
# Line 2935  Line 3297 
3297    
3298  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3299      my ($timeValue) = @_;      my ($timeValue) = @_;
3300      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3301      return $retVal;      return $retVal;
3302  }  }
3303    

Legend:
Removed from v.1.15  
changed lines
  Added in v.1.48

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3