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

Diff of /Sprout/Sprout.pm

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

revision 1.12, Wed May 4 03:24:43 2005 UTC revision 1.40, Wed Oct 12 03:12:24 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 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 $retVal;
447  }  }
# Line 570  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 609  Line 622 
622                  }                  }
623                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
624                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
625            # Compute the initial base pair.
626            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
627                  # Add the specifier to the list.                  # Add the specifier to the list.
628                  push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
629          }          }
630          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
631          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
632  }  }
633    
634  =head3 ParseLocation  =head3 ParseLocation
# Line 644  Line 659 
659      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
660          my ($location) = @_;          my ($location) = @_;
661          # Parse it into segments.          # Parse it into segments.
662          $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
663          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);          my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
664          # If the direction is an underscore, convert it to a + or -.          # If the direction is an underscore, convert it to a + or -.
665          if ($dir eq "_") {          if ($dir eq "_") {
# Line 752  Line 767 
767                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
768                  # before putting it in the return value.                  # before putting it in the return value.
769                  my ($start, $stop);                  my ($start, $stop);
770            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
771                  if ($dir eq "+") {                  if ($dir eq "+") {
772                          $start = $beg;                          $start = $beg;
773                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
774                  } else {                  } else {
775                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
776                          $stop = $beg;                          $stop = $beg;
777                  }                  }
778            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
779                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
780                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
781                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 787 
787                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
788                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
789                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
790                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
791                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
792                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
793                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
794                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
795                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
796                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
797                  }                  }
798                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
799                  if ($dir eq '+') {                  if ($dir eq '+') {
800                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
801                  } else {                  } else {
802                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
803                  }                  }
804          }          }
805          # Return the result.          # Return the result.
# Line 851  Line 869 
869          # Set it from the sequence data, if any.          # Set it from the sequence data, if any.
870          if ($sequence) {          if ($sequence) {
871                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);                  my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
872                  $retVal = $start + $len;          $retVal = $start + $len - 1;
873        }
874        # Return the result.
875        return $retVal;
876    }
877    
878    =head3 ClusterPEGs
879    
880    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
881    
882    Cluster the PEGs in a list according to the cluster coding scheme of the specified
883    subsystem. In order for this to work properly, the subsystem object must have
884    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
885    This causes the cluster numbers to be pulled into the subsystem's color hash.
886    If a PEG is not found in the color hash, it will not appear in the output
887    sequence.
888    
889    =over 4
890    
891    =item sub
892    
893    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
894    method.
895    
896    =item pegs
897    
898    Reference to the list of PEGs to be clustered.
899    
900    =item RETURN
901    
902    Returns a list of the PEGs, grouped into smaller lists by cluster number.
903    
904    =back
905    
906    =cut
907    #: Return Type $@@;
908    sub ClusterPEGs {
909        # Get the parameters.
910        my ($self, $sub, $pegs) = @_;
911        # Declare the return variable.
912        my $retVal = [];
913        # Loop through the PEGs, creating arrays for each cluster.
914        for my $pegID (@{$pegs}) {
915            my $clusterNumber = $sub->get_cluster_number($pegID);
916            # Only proceed if the PEG is in a cluster.
917            if ($clusterNumber >= 0) {
918                # Push this PEG onto the sub-list for the specified cluster number.
919                push @{$retVal->[$clusterNumber]}, $pegID;
920            }
921          }          }
922          # Return the result.          # Return the result.
923          return $retVal;          return $retVal;
# Line 1001  Line 1067 
1067    
1068  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1069    
1070  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1071    
1072  Return the annotations of a feature.  Return the annotations of a feature.
1073    
# Line 1011  Line 1077 
1077    
1078  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1079    
1080    =item rawFlag
1081    
1082    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1083    will be returned in human-readable form.
1084    
1085  =item RETURN  =item RETURN
1086    
1087  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1088    
1089  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1090    
1091  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1092    
1093  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1094    
# Line 1029  Line 1100 
1100  #: Return Type @%;  #: Return Type @%;
1101  sub FeatureAnnotations {  sub FeatureAnnotations {
1102          # Get the parameters.          # Get the parameters.
1103          my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1104          # 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.
1105          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1106                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                                                     "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1042  Line 1113 
1113                          $annotation->Values(['IsTargetOfAnnotation(from-link)',                          $annotation->Values(['IsTargetOfAnnotation(from-link)',
1114                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1115                                                                   'Annotation(annotation)']);                                                                   'Annotation(annotation)']);
1116            # Convert the time, if necessary.
1117            if (! $rawFlag) {
1118                $timeStamp = FriendlyTimestamp($timeStamp);
1119            }
1120                  # Assemble them into a hash.                  # Assemble them into a hash.
1121          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1122                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1123                                                             user => $user, text => $text };                                                             user => $user, text => $text };
1124                  # Add it to the return list.                  # Add it to the return list.
1125                  push @retVal, $annotationHash;                  push @retVal, $annotationHash;
# Line 1230  Line 1305 
1305    
1306  =item RETURN  =item RETURN
1307    
1308  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
1309  their best hits.  on the target genome.
1310    
1311  =back  =back
1312    
# Line 1248  Line 1323 
1323                  my $query = $self->Get(['IsBidirectionalBestHitOf'],                  my $query = $self->Get(['IsBidirectionalBestHitOf'],
1324                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                                             "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1325                                                             [$featureID, $genomeID]);                                                             [$featureID, $genomeID]);
1326                  # Look for the best hit.          # Peel off the BBHs found.
1327                  my $bbh = $query->Fetch;          my @found = ();
1328                  if ($bbh) {          while (my $bbh = $query->Fetch) {
1329                          my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
                         $retVal{$featureID} = $targetFeature;  
1330                  }                  }
1331            $retVal{$featureID} = \@found;
1332          }          }
1333          # Return the mapping.          # Return the mapping.
1334          return \%retVal;          return \%retVal;
1335  }  }
1336    
1337    =head3 SimList
1338    
1339    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1340    
1341    Return a list of the similarities to the specified feature.
1342    
1343    Sprout does not support real similarities, so this method just returns the bidirectional
1344    best hits.
1345    
1346    =over 4
1347    
1348    =item featureID
1349    
1350    ID of the feature whose similarities are desired.
1351    
1352    =item count
1353    
1354    Maximum number of similar features to be returned, or C<0> to return them all.
1355    
1356    =back
1357    
1358    =cut
1359    #: Return Type %;
1360    sub SimList {
1361        # Get the parameters.
1362        my ($self, $featureID, $count) = @_;
1363        # Ask for the best hits.
1364        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1365                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1366                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1367                                  $count);
1368        # Create the return value.
1369        my %retVal = ();
1370        for my $tuple (@lists) {
1371            $retVal{$tuple->[0]} = $tuple->[1];
1372        }
1373        # Return the result.
1374        return %retVal;
1375    }
1376    
1377    
1378    
1379    =head3 IsComplete
1380    
1381    C<< my $flag = $sprout->IsComplete($genomeID); >>
1382    
1383    Return TRUE if the specified genome is complete, else FALSE.
1384    
1385    =over 4
1386    
1387    =item genomeID
1388    
1389    ID of the genome whose completeness status is desired.
1390    
1391    =item RETURN
1392    
1393    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1394    not found.
1395    
1396    =back
1397    
1398    =cut
1399    #: Return Type $;
1400    sub IsComplete {
1401        # Get the parameters.
1402        my ($self, $genomeID) = @_;
1403        # Declare the return variable.
1404        my $retVal;
1405        # Get the genome's data.
1406        my $genomeData = $self->GetEntity('Genome', $genomeID);
1407        if ($genomeData) {
1408            # The genome exists, so get the completeness flag.
1409            ($retVal) = $genomeData->Value('complete');
1410        }
1411        # Return the result.
1412        return $retVal;
1413    }
1414    
1415  =head3 FeatureAliases  =head3 FeatureAliases
1416    
1417  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1502 
1502  sub CoupledFeatures {  sub CoupledFeatures {
1503          # Get the parameters.          # Get the parameters.
1504          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1505          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1506          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1507          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1508          # 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.
1509          my $found = 0;          my $found = 0;
1510          # Create the return hash.          # Create the return hash.
1511          my %retVal = ();          my %retVal = ();
1512          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1513          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1514                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1515                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1516                                                            'Coupling(score)']);
1517            # The coupling ID contains the two feature IDs separated by a space. We use
1518            # this information to find the ID of the other feature.
1519            my ($fid1, $fid2) = split / /, $couplingID;
1520            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1521            # Attach the other feature's score to its ID.
1522                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1523                  $found = 1;                  $found = 1;
1524          }          }
# Line 1374  Line 1531 
1531          return %retVal;          return %retVal;
1532  }  }
1533    
1534    =head3 CouplingEvidence
1535    
1536    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1537    
1538    Return the evidence for a functional coupling.
1539    
1540    A pair of features is considered evidence of a coupling between two other
1541    features if they occur close together on a contig and both are similar to
1542    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1543    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1544    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1545    similar to B<A2>.
1546    
1547    The score of a coupling is determined by the number of pieces of evidence
1548    that are considered I<representative>. If several evidence items belong to
1549    a group of genomes that are close to each other, only one of those items
1550    is considered representative. The other evidence items are presumed to be
1551    there because of the relationship between the genomes rather than because
1552    the two proteins generated by the features have a related functionality.
1553    
1554    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1555    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1556    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1557    and FALSE otherwise.
1558    
1559    =over 4
1560    
1561    =item peg1
1562    
1563    ID of the feature of interest.
1564    
1565    =item peg2
1566    
1567    ID of a feature functionally coupled to the feature of interest.
1568    
1569    =item RETURN
1570    
1571    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1572    of interest, a feature similar to the functionally coupled feature, and a flag
1573    that is TRUE for a representative piece of evidence and FALSE otherwise.
1574    
1575    =back
1576    
1577    =cut
1578    #: Return Type @@;
1579    sub CouplingEvidence {
1580        # Get the parameters.
1581        my ($self, $peg1, $peg2) = @_;
1582        # Declare the return variable.
1583        my @retVal = ();
1584        # Our first task is to find out the nature of the coupling: whether or not
1585        # it exists, its score, and whether the features are stored in the same
1586        # order as the ones coming in.
1587        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1588        # Only proceed if a coupling exists.
1589        if ($couplingID) {
1590            # Determine the ordering to place on the evidence items. If we're
1591            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1592            # we want feature 1 before feature 2 (normal).
1593            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1594            my $ordering = ($inverted ? "DESC" : "");
1595            # Get the coupling evidence.
1596            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1597                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1598                                              [$couplingID],
1599                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1600            # Loop through the evidence items. Each piece of evidence is represented by two
1601            # positions in the evidence list, one for each feature on the other side of the
1602            # evidence link. If at some point we want to generalize to couplings with
1603            # more than two positions, this section of code will need to be re-done.
1604            while (@evidenceList > 0) {
1605                my $peg1Data = shift @evidenceList;
1606                my $peg2Data = shift @evidenceList;
1607                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1608                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1609            }
1610            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1611        }
1612        # Return the result.
1613        return @retVal;
1614    }
1615    
1616    =head3 GetCoupling
1617    
1618    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1619    
1620    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1621    exists, we return the coupling ID along with an indicator of whether the
1622    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1623    In the second case, we say the coupling is I<inverted>. The importance of an
1624    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1625    
1626    =over 4
1627    
1628    =item peg1
1629    
1630    ID of the feature of interest.
1631    
1632    =item peg2
1633    
1634    ID of the potentially coupled feature.
1635    
1636    =item RETURN
1637    
1638    Returns a three-element list. The first element contains the database ID of
1639    the coupling. The second element is FALSE if the coupling is stored in the
1640    database in the caller specified order and TRUE if it is stored in the
1641    inverted order. The third element is the coupling's score. If the coupling
1642    does not exist, all three list elements will be C<undef>.
1643    
1644    =back
1645    
1646    =cut
1647    #: Return Type $%@;
1648    sub GetCoupling {
1649        # Get the parameters.
1650        my ($self, $peg1, $peg2) = @_;
1651        # Declare the return values. We'll start with the coupling ID and undefine the
1652        # flag and score until we have more information.
1653        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1654        # Find the coupling data.
1655        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1656                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1657                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1658        # Check to see if we found anything.
1659        if (!@pegs) {
1660            Trace("No coupling found.") if T(Coupling => 4);
1661            # No coupling, so undefine the return value.
1662            $retVal = undef;
1663        } else {
1664            # We have a coupling! Get the score and check for inversion.
1665            $score = $pegs[0]->[1];
1666            my $firstFound = $pegs[0]->[0];
1667            $inverted = ($firstFound ne $peg1);
1668            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1669        }
1670        # Return the result.
1671        return ($retVal, $inverted, $score);
1672    }
1673    
1674    =head3 CouplingID
1675    
1676    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1677    
1678    Return the coupling ID for a pair of feature IDs.
1679    
1680    The coupling ID is currently computed by joining the feature IDs in
1681    sorted order with a space. Client modules (that is, modules which
1682    use Sprout) should not, however, count on this always being the
1683    case. This method provides a way for abstracting the concept of a
1684    coupling ID. All that we know for sure about it is that it can be
1685    generated easily from the feature IDs and the order of the IDs
1686    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1687    will have the same value as C<CouplingID("b1", "a1")>.
1688    
1689    =over 4
1690    
1691    =item peg1
1692    
1693    First feature of interest.
1694    
1695    =item peg2
1696    
1697    Second feature of interest.
1698    
1699    =item RETURN
1700    
1701    Returns the ID that would be used to represent a functional coupling of
1702    the two specified PEGs.
1703    
1704    =back
1705    
1706    =cut
1707    #: Return Type $;
1708    sub CouplingID {
1709        return join " ", sort @_;
1710    }
1711    
1712  =head3 GetEntityTypes  =head3 GetEntityTypes
1713    
1714  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1435  Line 1770 
1770                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1771                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1772                          if ($id) {                          if ($id) {
1773                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1774                          }                          }
1775                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1776                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1777                  } else {                  } else {
1778                          # 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.
1779                          # 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
1780                          # case.                          # case.
1781                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1782                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 1784 
1784          }          }
1785          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1786          if ($sequence) {          if ($sequence) {
1787                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1788          }          }
1789          # Close the file.          # Close the file.
1790          close FASTAFILE;          close FASTAFILE;
# Line 1568  Line 1903 
1903  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
1904  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>.
1905    
1906  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<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1907    
1908  =over 4  =over 4
1909    
# Line 1775  Line 2110 
2110          # Get the parameters.          # Get the parameters.
2111          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2112          # Check for the entity instance.          # Check for the entity instance.
2113        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2114          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2115          # Return an existence indicator.          # Return an existence indicator.
2116          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1966  Line 2302 
2302          return @retVal;          return @retVal;
2303  }  }
2304    
2305    =head3 GetProperties
2306    
2307    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2308    
2309    Return a list of the properties with the specified characteristics.
2310    
2311    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2312    will also be associated with genomes.) A property value is represented by a 4-tuple of
2313    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2314    
2315    =over 4
2316    
2317    =item fid
2318    
2319    ID of the feature possessing the property.
2320    
2321    =item key
2322    
2323    Name or key of the property.
2324    
2325    =item value
2326    
2327    Value of the property.
2328    
2329    =item url
2330    
2331    URL of the document that indicated the property should have this particular value, or an
2332    empty string if no such document exists.
2333    
2334    =back
2335    
2336    The parameters act as a filter for the desired data. Any non-null parameter will
2337    automatically match all the tuples returned. So, specifying just the I<$fid> will
2338    return all the properties of the specified feature; similarly, specifying the I<$key>
2339    and I<$value> parameters will return all the features having the specified property
2340    value.
2341    
2342    A single property key can have many values, representing different ideas about the
2343    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2344    virulent, and another may declare that it is not virulent. A query about the virulence of
2345    C<fig|83333.1.peg.10> would be coded as
2346    
2347        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2348    
2349    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2350    not to be filtered. The tuples returned would be
2351    
2352        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2353        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2354    
2355    =cut
2356    #: Return Type @@;
2357    sub GetProperties {
2358        # Get the parameters.
2359        my ($self, @parms) = @_;
2360        # Declare the return variable.
2361        my @retVal = ();
2362        # Now we need to create a WHERE clause that will get us the data we want. First,
2363        # we create a list of the columns containing the data for each parameter.
2364        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2365                        'Property(property-value)', 'HasProperty(evidence)');
2366        # Now we build the WHERE clause and the list of parameter values.
2367        my @where = ();
2368        my @values = ();
2369        for (my $i = 0; $i <= $#colNames; $i++) {
2370            my $parm = $parms[$i];
2371            if (defined $parm && ($parm ne '')) {
2372                push @where, "$colNames[$i] = ?";
2373                push @values, $parm;
2374            }
2375        }
2376        # Format the WHERE clause.
2377        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2378        # Ask for all the propertie values with the desired characteristics.
2379        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2380        while (my $valueObject = $query->Fetch()) {
2381            my @tuple = $valueObject->Values(\@colNames);
2382            push @retVal, \@tuple;
2383        }
2384        # Return the result.
2385        return @retVal;
2386    }
2387    
2388  =head3 FeatureProperties  =head3 FeatureProperties
2389    
2390  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2579 
2579  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2580    
2581  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
2582  to the role the feature performs.  to the roles the feature performs.
2583    
2584  =over 4  =over 4
2585    
# Line 2170  Line 2589 
2589    
2590  =item RETURN  =item RETURN
2591    
2592  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.
2593    
2594  =back  =back
2595    
2596  =cut  =cut
2597  #: Return Type %;  #: Return Type %@;
2598  sub SubsystemsOf {  sub SubsystemsOf {
2599          # Get the parameters.          # Get the parameters.
2600          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2601          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2602          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2603                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2604                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2187  Line 2606 
2606          my %retVal = ();          my %retVal = ();
2607          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2608          for my $record (@subsystems) {          for my $record (@subsystems) {
2609                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2610            if (exists $retVal{$subsys}) {
2611                push @{$retVal{$subsys}}, $role;
2612            } else {
2613                $retVal{$subsys} = [$role];
2614            }
2615          }          }
2616          # Return the hash.          # Return the hash.
2617          return %retVal;          return %retVal;
2618  }  }
2619    
2620    =head3 SubsystemList
2621    
2622    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2623    
2624    Return a list containing the names of the subsystems in which the specified
2625    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2626    subsystem names, not the roles.
2627    
2628    =over 4
2629    
2630    =item featureID
2631    
2632    ID of the feature whose subsystem names are desired.
2633    
2634    =item RETURN
2635    
2636    Returns a list of the names of the subsystems in which the feature participates.
2637    
2638    =back
2639    
2640    =cut
2641    #: Return Type @;
2642    sub SubsystemList {
2643        # Get the parameters.
2644        my ($self, $featureID) = @_;
2645        # Get the list of names.
2646        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2647                                    [$featureID], 'HasSSCell(from-link)');
2648        # Return the result.
2649        return @retVal;
2650    }
2651    
2652  =head3 RelatedFeatures  =head3 RelatedFeatures
2653    
2654  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2353  Line 2809 
2809  sub GetAll {  sub GetAll {
2810          # Get the parameters.          # Get the parameters.
2811          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2812          # Create the query.      # Call the ERDB method.
2813          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2814          # Set up a counter of the number of records read.                                          $fields, $count);
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
2815          # Return the resulting list.          # Return the resulting list.
2816          return @retVal;          return @retVal;
2817  }  }
# Line 2624  Line 3067 
3067      return %retVal;      return %retVal;
3068  }  }
3069    
3070    =head3 MyGenomes
3071    
3072    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3073    
3074    Return a list of the genomes to be included in the Sprout.
3075    
3076    This method is provided for use during the Sprout load. It presumes the Genome load file has
3077    already been created. (It will be in the Sprout data directory and called either C<Genome>
3078    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3079    IDs.
3080    
3081    =over 4
3082    
3083    =item dataDir
3084    
3085    Directory containing the Sprout load files.
3086    
3087    =back
3088    
3089    =cut
3090    #: Return Type @;
3091    sub MyGenomes {
3092        # Get the parameters.
3093        my ($dataDir) = @_;
3094        # Compute the genome file name.
3095        my $genomeFileName = LoadFileName($dataDir, "Genome");
3096        # Extract the genome IDs from the files.
3097        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3098        # Return the result.
3099        return @retVal;
3100    }
3101    
3102    =head3 LoadFileName
3103    
3104    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3105    
3106    Return the name of the load file for the specified table in the specified data
3107    directory.
3108    
3109    =over 4
3110    
3111    =item dataDir
3112    
3113    Directory containing the Sprout load files.
3114    
3115    =item tableName
3116    
3117    Name of the table whose load file is desired.
3118    
3119    =item RETURN
3120    
3121    Returns the name of the file containing the load data for the specified table, or
3122    C<undef> if no load file is present.
3123    
3124    =back
3125    
3126    =cut
3127    #: Return Type $;
3128    sub LoadFileName {
3129        # Get the parameters.
3130        my ($dataDir, $tableName) = @_;
3131        # Declare the return variable.
3132        my $retVal;
3133        # Check for the various file names.
3134        if (-e "$dataDir/$tableName") {
3135            $retVal = "$dataDir/$tableName";
3136        } elsif (-e "$dataDir/$tableName.dtx") {
3137            $retVal = "$dataDir/$tableName.dtx";
3138        }
3139        # Return the result.
3140        return $retVal;
3141    }
3142    
3143  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3144    
3145  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2695  Line 3211 
3211    
3212  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3213      my ($timeValue) = @_;      my ($timeValue) = @_;
3214      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3215      return $retVal;      return $retVal;
3216  }  }
3217    
3218    =head3 AddProperty
3219    
3220    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3221    
3222    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3223    be added to almost any object. In Sprout, they can only be added to features. In
3224    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3225    pair. If the particular key/value pair coming in is not already in the database, a new
3226    B<Property> record is created to hold it.
3227    
3228    =over 4
3229    
3230    =item peg
3231    
3232    ID of the feature to which the attribute is to be replied.
3233    
3234    =item key
3235    
3236    Name of the attribute (key).
3237    
3238    =item value
3239    
3240    Value of the attribute.
3241    
3242    =item url
3243    
3244    URL or text citation from which the property was obtained.
3245    
3246    =back
3247    
3248    =cut
3249    #: Return Type ;
3250    sub AddProperty {
3251        # Get the parameters.
3252        my ($self, $featureID, $key, $value, $url) = @_;
3253        # Declare the variable to hold the desired property ID.
3254        my $propID;
3255        # Attempt to find a property record for this key/value pair.
3256        my @properties = $self->GetFlat(['Property'],
3257                                       "Property(property-name) = ? AND Property(property-value) = ?",
3258                                       [$key, $value], 'Property(id)');
3259        if (@properties) {
3260            # Here the property is already in the database. We save its ID.
3261            $propID = $properties[0];
3262            # Here the property value does not exist. We need to generate an ID. It will be set
3263            # to a number one greater than the maximum value in the database. This call to
3264            # GetAll will stop after one record.
3265            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3266                                            1);
3267            $propID = $maxProperty[0]->[0] + 1;
3268            # Insert the new property value.
3269            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3270        }
3271        # Now we connect the incoming feature to the property.
3272        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3273    }
3274    
3275    
3276    
3277  1;  1;

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.40

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3