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

Diff of /Sprout/Sprout.pm

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

revision 1.13, Thu May 5 03:14:03 2005 UTC revision 1.44, Thu Oct 20 09:32:18 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 1230  Line 1310 
1310    
1311  =item RETURN  =item RETURN
1312    
1313  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
1314  their best hits.  on the target genome.
1315    
1316  =back  =back
1317    
# Line 1248  Line 1328 
1328                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1329                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1330                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1331                  # Look for the best hit.          # Peel off the BBHs found.
1332                  my $bbh = $query->Fetch;          my @found = ();
1333                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1334                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1335                  }                  }
1336            $retVal{$featureID} = \@found;
1337          }          }
1338          # Return the mapping.          # Return the mapping.
1339          return \%retVal;          return \%retVal;
1340  }  }
1341    
1342    =head3 SimList
1343    
1344    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1345    
1346    Return a list of the similarities to the specified feature.
1347    
1348    Sprout does not support real similarities, so this method just returns the bidirectional
1349    best hits.
1350    
1351    =over 4
1352    
1353    =item featureID
1354    
1355    ID of the feature whose similarities are desired.
1356    
1357    =item count
1358    
1359    Maximum number of similar features to be returned, or C<0> to return them all.
1360    
1361    =back
1362    
1363    =cut
1364    #: Return Type %;
1365    sub SimList {
1366        # Get the parameters.
1367        my ($self, $featureID, $count) = @_;
1368        # Ask for the best hits.
1369        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1370                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1371                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1372                                  $count);
1373        # Create the return value.
1374        my %retVal = ();
1375        for my $tuple (@lists) {
1376            $retVal{$tuple->[0]} = $tuple->[1];
1377        }
1378        # Return the result.
1379        return %retVal;
1380    }
1381    
1382    
1383    
1384    =head3 IsComplete
1385    
1386    C<< my $flag = $sprout->IsComplete($genomeID); >>
1387    
1388    Return TRUE if the specified genome is complete, else FALSE.
1389    
1390    =over 4
1391    
1392    =item genomeID
1393    
1394    ID of the genome whose completeness status is desired.
1395    
1396    =item RETURN
1397    
1398    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1399    not found.
1400    
1401    =back
1402    
1403    =cut
1404    #: Return Type $;
1405    sub IsComplete {
1406        # Get the parameters.
1407        my ($self, $genomeID) = @_;
1408        # Declare the return variable.
1409        my $retVal;
1410        # Get the genome's data.
1411        my $genomeData = $self->GetEntity('Genome', $genomeID);
1412        if ($genomeData) {
1413            # The genome exists, so get the completeness flag.
1414            ($retVal) = $genomeData->Value('complete');
1415        }
1416        # Return the result.
1417        return $retVal;
1418    }
1419    
1420  =head3 FeatureAliases  =head3 FeatureAliases
1421    
1422  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1507 
1507  sub CoupledFeatures {  sub CoupledFeatures {
1508          # Get the parameters.          # Get the parameters.
1509          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1510          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1511          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1512          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1513          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1514          my $found = 0;          my $found = 0;
1515          # Create the return hash.          # Create the return hash.
1516          my %retVal = ();          my %retVal = ();
1517          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1518          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1519                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1520                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1521                                                            'Coupling(score)']);
1522            # The coupling ID contains the two feature IDs separated by a space. We use
1523            # this information to find the ID of the other feature.
1524            my ($fid1, $fid2) = split / /, $couplingID;
1525            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1526            # Attach the other feature's score to its ID.
1527                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1528                  $found = 1;                  $found = 1;
1529          }          }
# Line 1374  Line 1536 
1536          return %retVal;          return %retVal;
1537  }  }
1538    
1539    =head3 CouplingEvidence
1540    
1541    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1542    
1543    Return the evidence for a functional coupling.
1544    
1545    A pair of features is considered evidence of a coupling between two other
1546    features if they occur close together on a contig and both are similar to
1547    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1548    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1549    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1550    similar to B<A2>.
1551    
1552    The score of a coupling is determined by the number of pieces of evidence
1553    that are considered I<representative>. If several evidence items belong to
1554    a group of genomes that are close to each other, only one of those items
1555    is considered representative. The other evidence items are presumed to be
1556    there because of the relationship between the genomes rather than because
1557    the two proteins generated by the features have a related functionality.
1558    
1559    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1560    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1561    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1562    and FALSE otherwise.
1563    
1564    =over 4
1565    
1566    =item peg1
1567    
1568    ID of the feature of interest.
1569    
1570    =item peg2
1571    
1572    ID of a feature functionally coupled to the feature of interest.
1573    
1574    =item RETURN
1575    
1576    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1577    of interest, a feature similar to the functionally coupled feature, and a flag
1578    that is TRUE for a representative piece of evidence and FALSE otherwise.
1579    
1580    =back
1581    
1582    =cut
1583    #: Return Type @@;
1584    sub CouplingEvidence {
1585        # Get the parameters.
1586        my ($self, $peg1, $peg2) = @_;
1587        # Declare the return variable.
1588        my @retVal = ();
1589        # Our first task is to find out the nature of the coupling: whether or not
1590        # it exists, its score, and whether the features are stored in the same
1591        # order as the ones coming in.
1592        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1593        # Only proceed if a coupling exists.
1594        if ($couplingID) {
1595            # Determine the ordering to place on the evidence items. If we're
1596            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1597            # we want feature 1 before feature 2 (normal).
1598            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1599            my $ordering = ($inverted ? "DESC" : "");
1600            # Get the coupling evidence.
1601            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1602                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1603                                              [$couplingID],
1604                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1605            # Loop through the evidence items. Each piece of evidence is represented by two
1606            # positions in the evidence list, one for each feature on the other side of the
1607            # evidence link. If at some point we want to generalize to couplings with
1608            # more than two positions, this section of code will need to be re-done.
1609            while (@evidenceList > 0) {
1610                my $peg1Data = shift @evidenceList;
1611                my $peg2Data = shift @evidenceList;
1612                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1613                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1614            }
1615            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1616        }
1617        # Return the result.
1618        return @retVal;
1619    }
1620    
1621    =head3 GetCoupling
1622    
1623    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1624    
1625    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1626    exists, we return the coupling ID along with an indicator of whether the
1627    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1628    In the second case, we say the coupling is I<inverted>. The importance of an
1629    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1630    
1631    =over 4
1632    
1633    =item peg1
1634    
1635    ID of the feature of interest.
1636    
1637    =item peg2
1638    
1639    ID of the potentially coupled feature.
1640    
1641    =item RETURN
1642    
1643    Returns a three-element list. The first element contains the database ID of
1644    the coupling. The second element is FALSE if the coupling is stored in the
1645    database in the caller specified order and TRUE if it is stored in the
1646    inverted order. The third element is the coupling's score. If the coupling
1647    does not exist, all three list elements will be C<undef>.
1648    
1649    =back
1650    
1651    =cut
1652    #: Return Type $%@;
1653    sub GetCoupling {
1654        # Get the parameters.
1655        my ($self, $peg1, $peg2) = @_;
1656        # Declare the return values. We'll start with the coupling ID and undefine the
1657        # flag and score until we have more information.
1658        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1659        # Find the coupling data.
1660        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1661                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1662                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1663        # Check to see if we found anything.
1664        if (!@pegs) {
1665            Trace("No coupling found.") if T(Coupling => 4);
1666            # No coupling, so undefine the return value.
1667            $retVal = undef;
1668        } else {
1669            # We have a coupling! Get the score and check for inversion.
1670            $score = $pegs[0]->[1];
1671            my $firstFound = $pegs[0]->[0];
1672            $inverted = ($firstFound ne $peg1);
1673            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1674        }
1675        # Return the result.
1676        return ($retVal, $inverted, $score);
1677    }
1678    
1679    =head3 CouplingID
1680    
1681    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1682    
1683    Return the coupling ID for a pair of feature IDs.
1684    
1685    The coupling ID is currently computed by joining the feature IDs in
1686    sorted order with a space. Client modules (that is, modules which
1687    use Sprout) should not, however, count on this always being the
1688    case. This method provides a way for abstracting the concept of a
1689    coupling ID. All that we know for sure about it is that it can be
1690    generated easily from the feature IDs and the order of the IDs
1691    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1692    will have the same value as C<CouplingID("b1", "a1")>.
1693    
1694    =over 4
1695    
1696    =item peg1
1697    
1698    First feature of interest.
1699    
1700    =item peg2
1701    
1702    Second feature of interest.
1703    
1704    =item RETURN
1705    
1706    Returns the ID that would be used to represent a functional coupling of
1707    the two specified PEGs.
1708    
1709    =back
1710    
1711    =cut
1712    #: Return Type $;
1713    sub CouplingID {
1714        return join " ", sort @_;
1715    }
1716    
1717  =head3 GetEntityTypes  =head3 GetEntityTypes
1718    
1719  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1435  Line 1775 
1775                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1776                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1777                          if ($id) {                          if ($id) {
1778                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1779                          }                          }
1780                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1781                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1782                  } else {                  } else {
1783                          # 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.
1784                          # 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
1785                          # case.                          # case.
1786                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1787                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 1789 
1789          }          }
1790          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1791          if ($sequence) {          if ($sequence) {
1792                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1793          }          }
1794          # Close the file.          # Close the file.
1795          close FASTAFILE;          close FASTAFILE;
# Line 1568  Line 1908 
1908  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
1909  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>.
1910    
1911  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<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1912    
1913  =over 4  =over 4
1914    
# Line 1775  Line 2115 
2115          # Get the parameters.          # Get the parameters.
2116          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2117          # Check for the entity instance.          # Check for the entity instance.
2118        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2119          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2120          # Return an existence indicator.          # Return an existence indicator.
2121          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1966  Line 2307 
2307          return @retVal;          return @retVal;
2308  }  }
2309    
2310    =head3 GetProperties
2311    
2312    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2313    
2314    Return a list of the properties with the specified characteristics.
2315    
2316    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2317    will also be associated with genomes.) A property value is represented by a 4-tuple of
2318    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2319    
2320    =over 4
2321    
2322    =item fid
2323    
2324    ID of the feature possessing the property.
2325    
2326    =item key
2327    
2328    Name or key of the property.
2329    
2330    =item value
2331    
2332    Value of the property.
2333    
2334    =item url
2335    
2336    URL of the document that indicated the property should have this particular value, or an
2337    empty string if no such document exists.
2338    
2339    =back
2340    
2341    The parameters act as a filter for the desired data. Any non-null parameter will
2342    automatically match all the tuples returned. So, specifying just the I<$fid> will
2343    return all the properties of the specified feature; similarly, specifying the I<$key>
2344    and I<$value> parameters will return all the features having the specified property
2345    value.
2346    
2347    A single property key can have many values, representing different ideas about the
2348    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2349    virulent, and another may declare that it is not virulent. A query about the virulence of
2350    C<fig|83333.1.peg.10> would be coded as
2351    
2352        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2353    
2354    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2355    not to be filtered. The tuples returned would be
2356    
2357        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2358        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2359    
2360    =cut
2361    #: Return Type @@;
2362    sub GetProperties {
2363        # Get the parameters.
2364        my ($self, @parms) = @_;
2365        # Declare the return variable.
2366        my @retVal = ();
2367        # Now we need to create a WHERE clause that will get us the data we want. First,
2368        # we create a list of the columns containing the data for each parameter.
2369        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2370                        'Property(property-value)', 'HasProperty(evidence)');
2371        # Now we build the WHERE clause and the list of parameter values.
2372        my @where = ();
2373        my @values = ();
2374        for (my $i = 0; $i <= $#colNames; $i++) {
2375            my $parm = $parms[$i];
2376            if (defined $parm && ($parm ne '')) {
2377                push @where, "$colNames[$i] = ?";
2378                push @values, $parm;
2379            }
2380        }
2381        # Format the WHERE clause.
2382        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2383        # Ask for all the propertie values with the desired characteristics.
2384        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2385        while (my $valueObject = $query->Fetch()) {
2386            my @tuple = $valueObject->Values(\@colNames);
2387            push @retVal, \@tuple;
2388        }
2389        # Return the result.
2390        return @retVal;
2391    }
2392    
2393  =head3 FeatureProperties  =head3 FeatureProperties
2394    
2395  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2584 
2584  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2585    
2586  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
2587  to the role the feature performs.  to the roles the feature performs.
2588    
2589  =over 4  =over 4
2590    
# Line 2170  Line 2594 
2594    
2595  =item RETURN  =item RETURN
2596    
2597  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.
2598    
2599  =back  =back
2600    
2601  =cut  =cut
2602  #: Return Type %;  #: Return Type %@;
2603  sub SubsystemsOf {  sub SubsystemsOf {
2604          # Get the parameters.          # Get the parameters.
2605          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2606          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2607          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2608                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2609                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2610          # Create the return value.          # Create the return value.
2611          my %retVal = ();          my %retVal = ();
2612        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2613        # in two spreadsheet cells.
2614        my %dupHash = ();
2615          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2616          for my $record (@subsystems) {          for my $record (@subsystems) {
2617                  $retVal{$record->[0]} = $record->[1];          # Get this subsystem and role.
2618            my ($subsys, $role) = @{$record};
2619            # Insure it's the first time for both.
2620            my $dupKey = "$subsys\n$role";
2621            if (! exists $dupHash{"$subsys\n$role"}) {
2622                $dupHash{$dupKey} = 1;
2623                push @{$retVal{$subsys}}, $role;
2624            }
2625          }          }
2626          # Return the hash.          # Return the hash.
2627          return %retVal;          return %retVal;
2628  }  }
2629    
2630    =head3 SubsystemList
2631    
2632    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2633    
2634    Return a list containing the names of the subsystems in which the specified
2635    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2636    subsystem names, not the roles.
2637    
2638    =over 4
2639    
2640    =item featureID
2641    
2642    ID of the feature whose subsystem names are desired.
2643    
2644    =item RETURN
2645    
2646    Returns a list of the names of the subsystems in which the feature participates.
2647    
2648    =back
2649    
2650    =cut
2651    #: Return Type @;
2652    sub SubsystemList {
2653        # Get the parameters.
2654        my ($self, $featureID) = @_;
2655        # Get the list of names.
2656        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2657                                    [$featureID], 'HasSSCell(from-link)');
2658        # Return the result.
2659        return @retVal;
2660    }
2661    
2662  =head3 RelatedFeatures  =head3 RelatedFeatures
2663    
2664  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2611  Line 3077 
3077      return %retVal;      return %retVal;
3078  }  }
3079    
3080    =head3 MyGenomes
3081    
3082    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3083    
3084    Return a list of the genomes to be included in the Sprout.
3085    
3086    This method is provided for use during the Sprout load. It presumes the Genome load file has
3087    already been created. (It will be in the Sprout data directory and called either C<Genome>
3088    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3089    IDs.
3090    
3091    =over 4
3092    
3093    =item dataDir
3094    
3095    Directory containing the Sprout load files.
3096    
3097    =back
3098    
3099    =cut
3100    #: Return Type @;
3101    sub MyGenomes {
3102        # Get the parameters.
3103        my ($dataDir) = @_;
3104        # Compute the genome file name.
3105        my $genomeFileName = LoadFileName($dataDir, "Genome");
3106        # Extract the genome IDs from the files.
3107        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3108        # Return the result.
3109        return @retVal;
3110    }
3111    
3112    =head3 LoadFileName
3113    
3114    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3115    
3116    Return the name of the load file for the specified table in the specified data
3117    directory.
3118    
3119    =over 4
3120    
3121    =item dataDir
3122    
3123    Directory containing the Sprout load files.
3124    
3125    =item tableName
3126    
3127    Name of the table whose load file is desired.
3128    
3129    =item RETURN
3130    
3131    Returns the name of the file containing the load data for the specified table, or
3132    C<undef> if no load file is present.
3133    
3134    =back
3135    
3136    =cut
3137    #: Return Type $;
3138    sub LoadFileName {
3139        # Get the parameters.
3140        my ($dataDir, $tableName) = @_;
3141        # Declare the return variable.
3142        my $retVal;
3143        # Check for the various file names.
3144        if (-e "$dataDir/$tableName") {
3145            $retVal = "$dataDir/$tableName";
3146        } elsif (-e "$dataDir/$tableName.dtx") {
3147            $retVal = "$dataDir/$tableName.dtx";
3148        }
3149        # Return the result.
3150        return $retVal;
3151    }
3152    
3153  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3154    
3155  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2650  Line 3189 
3189          # Declare the return value.          # Declare the return value.
3190          my @retVal = ();          my @retVal = ();
3191          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3192          my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3193          if ($type =~ m/^set ([^ ]+) function to$/i) {          if ($type =~ m/^set ([^ ]+) function to$/i) {
3194                  # Here it is, so we return the user name (which is in $1), the functional role text,                  # Here it is, so we return the user name (which is in $1), the functional role text,
3195          # and the assigning user.          # and the assigning user.
3196                  @retVal = ($1, $function, $user);          @retVal = ($1, $function);
3197          }          }
3198          # Return the result list.          # Return the result list.
3199          return @retVal;          return @retVal;
# Line 2682  Line 3221 
3221    
3222  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3223      my ($timeValue) = @_;      my ($timeValue) = @_;
3224      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3225      return $retVal;      return $retVal;
3226  }  }
3227    
3228    =head3 AddProperty
3229    
3230    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3231    
3232    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3233    be added to almost any object. In Sprout, they can only be added to features. In
3234    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3235    pair. If the particular key/value pair coming in is not already in the database, a new
3236    B<Property> record is created to hold it.
3237    
3238    =over 4
3239    
3240    =item peg
3241    
3242    ID of the feature to which the attribute is to be replied.
3243    
3244    =item key
3245    
3246    Name of the attribute (key).
3247    
3248    =item value
3249    
3250    Value of the attribute.
3251    
3252    =item url
3253    
3254    URL or text citation from which the property was obtained.
3255    
3256    =back
3257    
3258    =cut
3259    #: Return Type ;
3260    sub AddProperty {
3261        # Get the parameters.
3262        my ($self, $featureID, $key, $value, $url) = @_;
3263        # Declare the variable to hold the desired property ID.
3264        my $propID;
3265        # Attempt to find a property record for this key/value pair.
3266        my @properties = $self->GetFlat(['Property'],
3267                                       "Property(property-name) = ? AND Property(property-value) = ?",
3268                                       [$key, $value], 'Property(id)');
3269        if (@properties) {
3270            # Here the property is already in the database. We save its ID.
3271            $propID = $properties[0];
3272            # Here the property value does not exist. We need to generate an ID. It will be set
3273            # to a number one greater than the maximum value in the database. This call to
3274            # GetAll will stop after one record.
3275            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3276                                            1);
3277            $propID = $maxProperty[0]->[0] + 1;
3278            # Insert the new property value.
3279            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3280        }
3281        # Now we connect the incoming feature to the property.
3282        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3283    }
3284    
3285    
3286    
3287  1;  1;

Legend:
Removed from v.1.13  
changed lines
  Added in v.1.44

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3