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

Diff of /Sprout/Sprout.pm

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

revision 1.10, Fri Feb 25 18:41:45 2005 UTC revision 1.23, Fri Sep 9 21:15:47 2005 UTC
# Line 86  Line 86 
86          # 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
87          # the incoming data.          # the incoming data.
88          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
89                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
90                                             dataDir              => 'Data',                      # data file directory                                                          # database type
91                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
92                                             userData             => 'root/',                     # user name and password                                                          # data file directory
93                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
94                                                            # database definition file name
95                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
96                                                            # user name and password
97                           port         => $FIG_Config::dbport,
98                                                            # database connection port
99                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
100                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
101                                            }, $options);                                            }, $options);
# Line 269  Line 274 
274  sub GetEntity {  sub GetEntity {
275          # Get the parameters.          # Get the parameters.
276          my ($self, $entityType, $ID) = @_;          my ($self, $entityType, $ID) = @_;
277          # Create a query.      # Call the ERDB method.
278          my $query = $self->Get([$entityType], "$entityType(id) = ?", [$ID]);      return $self->{_erdb}->GetEntity($entityType, $ID);
         # Get the first (and only) object.  
         my $retVal = $query->Fetch();  
         # Return the result.  
         return $retVal;  
279  }  }
280    
281  =head3 GetEntityValues  =head3 GetEntityValues
# Line 308  Line 309 
309  sub GetEntityValues {  sub GetEntityValues {
310          # Get the parameters.          # Get the parameters.
311          my ($self, $entityType, $ID, $fields) = @_;          my ($self, $entityType, $ID, $fields) = @_;
312          # Get the specified entity.      # Call the ERDB method.
313          my $entity = $self->GetEntity($entityType, $ID);      return $self->{_erdb}->GetEntityValues($entityType, $ID, $fields);
         # Declare the return list.  
         my @retVal = ();  
         # If we found the entity, push the values into the return list.  
         if ($entity) {  
                 push @retVal, $entity->Values($fields);  
         }  
         # Return the result.  
         return @retVal;  
314  }  }
315    
316  =head3 ShowMetaData  =head3 ShowMetaData
# Line 432  Line 425 
425          # Loop through the incoming table names.          # Loop through the incoming table names.
426          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
427                  # Find the table's file.                  # Find the table's file.
428                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
429                  if (! -e $fileName) {          if (! $fileName) {
430                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
431                  }          } else {
432                  # Attempt to load this table.                  # Attempt to load this table.
433                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
434                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
435                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
436          }          }
437        }
438          # Return the statistics.          # Return the statistics.
439          return $retVal;          return $retVal;
440  }  }
# Line 582  Line 576 
576  =item RETURN  =item RETURN
577    
578  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
579  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
580    
581  =back  =back
582    
# Line 625  Line 619 
619                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
620          }          }
621          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
622          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
623  }  }
624    
625  =head3 ParseLocation  =head3 ParseLocation
# Line 1070  Line 1064 
1064  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1065    
1066  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1067  hash of functional assignments to user IDs. A functional assignment is a type of annotation.  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
1068  It has the format "XXXX\nset XXXX function to\nYYYYY". In this instance, XXXX is the user ID  Functional assignments are described in the L</ParseAssignment> function. Its worth noting that
1069  and YYYYY is the functional assignment text. Its worth noting that we cannot filter on the content  we cannot filter on the content of the annotation itself because it's a text field; however,
1070  of the annotation itself because it's a text field; however, this is not a big problem because most  this is not a big problem because most features only have a small number of annotations.
1071  features only have a small number of annotations. Finally, if a single user has multiple  Finally, if a single user has multiple functional assignments, we will only keep the most
1072  functional assignments, we will only keep the most recent one.  recent one.
1073    
1074  =over 4  =over 4
1075    
# Line 1109  Line 1103 
1103          # Get the annotation fields.          # Get the annotation fields.
1104          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text) = @{$annotation};
1105                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1106                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1107          if ($user && ! exists $timeHash{$user}) {          if ($user && ! exists $timeHash{$user}) {
1108              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1109              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
# Line 1131  Line 1125 
1125    
1126  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1127  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1128  assignment is a type of annotation. It has the format "XXXX\nset XXXX function to\nYYYYY". In this  assignment is a type of annotation. The format of an assignment is described in
1129  instance, XXXX is the user ID and YYYYY is the functional assignment text. Its worth noting that  L</ParseLocation>. Its worth noting that we cannot filter on the content of the
1130  we cannot filter on the content of the annotation itself because it's a text field; however, this  annotation itself because it's a text field; however, this is not a big problem because
1131  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1132    
1133  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1134  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1203  Line 1197 
1197              # Get the annotation text.              # Get the annotation text.
1198              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1199              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1200              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1201              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1202                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1203                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1204                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1242  Line 1236 
1236    
1237  =item RETURN  =item RETURN
1238    
1239  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
1240  their best hits.  on the target genome.
1241    
1242  =back  =back
1243    
# Line 1271  Line 1265 
1265          return \%retVal;          return \%retVal;
1266  }  }
1267    
1268    =head3 SimList
1269    
1270    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1271    
1272    Return a list of the similarities to the specified feature.
1273    
1274    Sprout does not support real similarities, so this method just returns the bidirectional
1275    best hits.
1276    
1277    =over 4
1278    
1279    =item featureID
1280    
1281    ID of the feature whose similarities are desired.
1282    
1283    =item count
1284    
1285    Maximum number of similar features to be returned, or C<0> to return them all.
1286    
1287    =back
1288    
1289    =cut
1290    #: Return Type %;
1291    sub SimList {
1292        # Get the parameters.
1293        my ($self, $featureID, $count) = @_;
1294        # Ask for the best hits.
1295        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1296                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1297                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1298                                  $count);
1299        # Create the return value.
1300        my %retVal = ();
1301        for my $tuple (@lists) {
1302            $retVal{$tuple->[0]} = $tuple->[1];
1303        }
1304        # Return the result.
1305        return %retVal;
1306    }
1307    
1308    
1309    
1310    =head3 IsComplete
1311    
1312    C<< my $flag = $sprout->IsComplete($genomeID); >>
1313    
1314    Return TRUE if the specified genome is complete, else FALSE.
1315    
1316    =over 4
1317    
1318    =item genomeID
1319    
1320    ID of the genome whose completeness status is desired.
1321    
1322    =item RETURN
1323    
1324    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1325    not found.
1326    
1327    =back
1328    
1329    =cut
1330    #: Return Type $;
1331    sub IsComplete {
1332        # Get the parameters.
1333        my ($self, $genomeID) = @_;
1334        # Declare the return variable.
1335        my $retVal;
1336        # Get the genome's data.
1337        my $genomeData = $self->GetEntity('Genome', $genomeID);
1338        if ($genomeData) {
1339            # The genome exists, so get the completeness flag.
1340            ($retVal) = $genomeData->Value('complete');
1341        }
1342        # Return the result.
1343        return $retVal;
1344    }
1345    
1346  =head3 FeatureAliases  =head3 FeatureAliases
1347    
1348  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1361  Line 1433 
1433  sub CoupledFeatures {  sub CoupledFeatures {
1434          # Get the parameters.          # Get the parameters.
1435          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1436          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1437          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1438          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1439          # 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.
1440          my $found = 0;          my $found = 0;
1441          # Create the return hash.          # Create the return hash.
1442          my %retVal = ();          my %retVal = ();
1443          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1444          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1445                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1446                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1447                                                            'Coupling(score)']);
1448            # The coupling ID contains the two feature IDs separated by a space. We use
1449            # this information to find the ID of the other feature.
1450            my ($fid1, $fid2) = split / /, $couplingID;
1451            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1452            # Attach the other feature's score to its ID.
1453                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1454                  $found = 1;                  $found = 1;
1455          }          }
# Line 1386  Line 1462 
1462          return %retVal;          return %retVal;
1463  }  }
1464    
1465    =head3 CouplingEvidence
1466    
1467    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1468    
1469    Return the evidence for a functional coupling.
1470    
1471    A pair of features is considered evidence of a coupling between two other
1472    features if they occur close together on a contig and both are similar to
1473    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1474    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1475    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1476    similar to B<A2>.
1477    
1478    The score of a coupling is determined by the number of pieces of evidence
1479    that are considered I<representative>. If several evidence items belong to
1480    a group of genomes that are close to each other, only one of those items
1481    is considered representative. The other evidence items are presumed to be
1482    there because of the relationship between the genomes rather than because
1483    the two proteins generated by the features have a related functionality.
1484    
1485    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1486    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1487    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1488    and FALSE otherwise.
1489    
1490    =over 4
1491    
1492    =item peg1
1493    
1494    ID of the feature of interest.
1495    
1496    =item peg2
1497    
1498    ID of a feature functionally coupled to the feature of interest.
1499    
1500    =item RETURN
1501    
1502    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1503    of interest, a feature similar to the functionally coupled feature, and a flag
1504    that is TRUE for a representative piece of evidence and FALSE otherwise.
1505    
1506    =back
1507    
1508    =cut
1509    #: Return Type @@;
1510    sub CouplingEvidence {
1511        # Get the parameters.
1512        my ($self, $peg1, $peg2) = @_;
1513        # Declare the return variable.
1514        my @retVal = ();
1515        # Our first task is to find out the nature of the coupling: whether or not
1516        # it exists, its score, and whether the features are stored in the same
1517        # order as the ones coming in.
1518        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1519        # Only proceed if a coupling exists.
1520        if ($couplingID) {
1521            # Determine the ordering to place on the evidence items. If we're
1522            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1523            # we want feature 1 before feature 2 (normal).
1524            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1525            my $ordering = ($inverted ? "DESC" : "");
1526            # Get the coupling evidence.
1527            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1528                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1529                                              [$couplingID],
1530                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1531            # Loop through the evidence items. Each piece of evidence is represented by two
1532            # positions in the evidence list, one for each feature on the other side of the
1533            # evidence link. If at some point we want to generalize to couplings with
1534            # more than two positions, this section of code will need to be re-done.
1535            while (@evidenceList > 0) {
1536                my $peg1Data = shift @evidenceList;
1537                my $peg2Data = shift @evidenceList;
1538                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1539                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1540            }
1541            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1542        }
1543        # Return the result.
1544        return @retVal;
1545    }
1546    
1547    =head3 GetCoupling
1548    
1549    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1550    
1551    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1552    exists, we return the coupling ID along with an indicator of whether the
1553    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1554    In the second case, we say the coupling is I<inverted>. The importance of an
1555    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1556    
1557    =over 4
1558    
1559    =item peg1
1560    
1561    ID of the feature of interest.
1562    
1563    =item peg2
1564    
1565    ID of the potentially coupled feature.
1566    
1567    =item RETURN
1568    
1569    Returns a three-element list. The first element contains the database ID of
1570    the coupling. The second element is FALSE if the coupling is stored in the
1571    database in the caller specified order and TRUE if it is stored in the
1572    inverted order. The third element is the coupling's score. If the coupling
1573    does not exist, all three list elements will be C<undef>.
1574    
1575    =back
1576    
1577    =cut
1578    #: Return Type $%@;
1579    sub GetCoupling {
1580        # Get the parameters.
1581        my ($self, $peg1, $peg2) = @_;
1582        # Declare the return values. We'll start with the coupling ID and undefine the
1583        # flag and score until we have more information.
1584        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1585        # Find the coupling data.
1586        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1587                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1588                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1589        # Check to see if we found anything.
1590        if (!@pegs) {
1591            Trace("No coupling found.") if T(Coupling => 4);
1592            # No coupling, so undefine the return value.
1593            $retVal = undef;
1594        } else {
1595            # We have a coupling! Get the score and check for inversion.
1596            $score = $pegs[0]->[1];
1597            my $firstFound = $pegs[0]->[0];
1598            $inverted = ($firstFound ne $peg1);
1599            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1600        }
1601        # Return the result.
1602        return ($retVal, $inverted, $score);
1603    }
1604    
1605    =head3 CouplingID
1606    
1607    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1608    
1609    Return the coupling ID for a pair of feature IDs.
1610    
1611    The coupling ID is currently computed by joining the feature IDs in
1612    sorted order with a space. Client modules (that is, modules which
1613    use Sprout) should not, however, count on this always being the
1614    case. This method provides a way for abstracting the concept of a
1615    coupling ID. All that we know for sure about it is that it can be
1616    generated easily from the feature IDs and the order of the IDs
1617    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1618    will have the same value as C<CouplingID("b1", "a1")>.
1619    
1620    =over 4
1621    
1622    =item peg1
1623    
1624    First feature of interest.
1625    
1626    =item peg2
1627    
1628    Second feature of interest.
1629    
1630    =item RETURN
1631    
1632    Returns the ID that would be used to represent a functional coupling of
1633    the two specified PEGs.
1634    
1635    =back
1636    
1637    =cut
1638    #: Return Type $;
1639    sub CouplingID {
1640        return join " ", sort @_;
1641    }
1642    
1643  =head3 GetEntityTypes  =head3 GetEntityTypes
1644    
1645  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1447  Line 1701 
1701                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1702                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1703                          if ($id) {                          if ($id) {
1704                                  $retVal{$id} = $sequence;                  $retVal{$id} = uc $sequence;
1705                          }                          }
1706                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1707                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1708                  } else {                  } else {
1709                          # 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.
1710                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to upper
1711                # case.
1712                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1713                          $sequence .= $1;                          $sequence .= $1;
1714                  }                  }
1715          }          }
1716          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1717          if ($sequence) {          if ($sequence) {
1718                  $retVal {$id} = $sequence;          $retVal{$id} = uc $sequence;
1719          }          }
1720        # Close the file.
1721        close FASTAFILE;
1722          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1723          return %retVal;          return %retVal;
1724  }  }
# Line 1577  Line 1834 
1834  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
1835  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>.
1836    
1837  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'}); >>
1838    
1839  =over 4  =over 4
1840    
# Line 1656  Line 1913 
1913    
1914  =head3 AssignFunction  =head3 AssignFunction
1915    
1916  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1917    
1918  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
1919  format is "XXXX\nset XXXX function to\nYYYYY" where XXXX is the feature type and YYYY is the functional  format is described in L</ParseAssignment>.
 assignment text.  
1920    
1921  =over 4  =over 4
1922    
# Line 1670  Line 1926 
1926    
1927  =item user  =item user
1928    
1929  Name of the user making the assignment. This is frequently a group name, like C<kegg> or C<fig>.  Name of the user group making the assignment, such as C<kegg> or C<fig>.
1930    
1931  =item function  =item function
1932    
1933  Text of the function being assigned.  Text of the function being assigned.
1934    
1935    =item assigningUser (optional)
1936    
1937    Name of the individual user making the assignment. If omitted, defaults to the user group.
1938    
1939  =item RETURN  =item RETURN
1940    
1941  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1686  Line 1946 
1946  #: Return Type $;  #: Return Type $;
1947  sub AssignFunction {  sub AssignFunction {
1948          # Get the parameters.          # Get the parameters.
1949          my ($self, $featureID, $user, $function) = @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1950        # Default the assigning user.
1951        if (! $assigningUser) {
1952            $assigningUser = $user;
1953        }
1954          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1955          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1956          # Get the current time.          # Get the current time.
1957          my $now = time;          my $now = time;
1958          # Declare the return variable.          # Declare the return variable.
# Line 1968  Line 2232 
2232          return @retVal;          return @retVal;
2233  }  }
2234    
2235    =head3 GetProperties
2236    
2237    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2238    
2239    Return a list of the properties with the specified characteristics.
2240    
2241    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2242    will also be associated with genomes.) A property value is represented by a 4-tuple of
2243    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2244    
2245    =over 4
2246    
2247    =item fid
2248    
2249    ID of the feature possessing the property.
2250    
2251    =item key
2252    
2253    Name or key of the property.
2254    
2255    =item value
2256    
2257    Value of the property.
2258    
2259    =item url
2260    
2261    URL of the document that indicated the property should have this particular value, or an
2262    empty string if no such document exists.
2263    
2264    =back
2265    
2266    The parameters act as a filter for the desired data. Any non-null parameter will
2267    automatically match all the tuples returned. So, specifying just the I<$fid> will
2268    return all the properties of the specified feature; similarly, specifying the I<$key>
2269    and I<$value> parameters will return all the features having the specified property
2270    value.
2271    
2272    A single property key can have many values, representing different ideas about the
2273    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2274    virulent, and another may declare that it is not virulent. A query about the virulence of
2275    C<fig|83333.1.peg.10> would be coded as
2276    
2277        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2278    
2279    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2280    not to be filtered. The tuples returned would be
2281    
2282        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2283        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2284    
2285    =cut
2286    #: Return Type @@;
2287    sub GetProperties {
2288        # Get the parameters.
2289        my ($self, @parms) = @_;
2290        # Declare the return variable.
2291        my @retVal = ();
2292        # Now we need to create a WHERE clause that will get us the data we want. First,
2293        # we create a list of the columns containing the data for each parameter.
2294        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2295                        'Property(property-value)', 'HasProperty(evidence)');
2296        # Now we build the WHERE clause and the list of parameter values.
2297        my @where = ();
2298        my @values = ();
2299        for (my $i = 0; $i <= $#colNames; $i++) {
2300            my $parm = $parms[$i];
2301            if (defined $parm && ($parm ne '')) {
2302                push @where, "$colNames[$i] = ?";
2303                push @values, $parm;
2304            }
2305        }
2306        # Format the WHERE clause.
2307        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2308        # Ask for all the propertie values with the desired characteristics.
2309        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2310        while (my $valueObject = $query->Fetch()) {
2311            my @tuple = $valueObject->Values(\@colNames);
2312            push @retVal, \@tuple;
2313        }
2314        # Return the result.
2315        return @retVal;
2316    }
2317    
2318  =head3 FeatureProperties  =head3 FeatureProperties
2319    
2320  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2162  Line 2509 
2509  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2510    
2511  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
2512  to the role the feature performs.  to the roles the feature performs.
2513    
2514  =over 4  =over 4
2515    
# Line 2172  Line 2519 
2519    
2520  =item RETURN  =item RETURN
2521    
2522  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.
2523    
2524  =back  =back
2525    
2526  =cut  =cut
2527  #: Return Type %;  #: Return Type %@;
2528  sub SubsystemsOf {  sub SubsystemsOf {
2529          # Get the parameters.          # Get the parameters.
2530          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2531          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2532          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2533                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2534                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2189  Line 2536 
2536          my %retVal = ();          my %retVal = ();
2537          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2538          for my $record (@subsystems) {          for my $record (@subsystems) {
2539                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2540            if (exists $retVal{$subsys}) {
2541                push @{$retVal{$subsys}}, $role;
2542            } else {
2543                $retVal{$subsys} = [$role];
2544            }
2545          }          }
2546          # Return the hash.          # Return the hash.
2547          return %retVal;          return %retVal;
2548  }  }
2549    
2550    =head3 SubsystemList
2551    
2552    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2553    
2554    Return a list containing the names of the subsystems in which the specified
2555    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2556    subsystem names, not the roles.
2557    
2558    =over 4
2559    
2560    =item featureID
2561    
2562    ID of the feature whose subsystem names are desired.
2563    
2564    =item RETURN
2565    
2566    Returns a list of the names of the subsystems in which the feature participates.
2567    
2568    =back
2569    
2570    =cut
2571    #: Return Type @;
2572    sub SubsystemList {
2573        # Get the parameters.
2574        my ($self, $featureID) = @_;
2575        # Get the list of names.
2576        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2577                                    [$featureID], 'HasSSCell(from-link)');
2578        # Return the result.
2579        return @retVal;
2580    }
2581    
2582  =head3 RelatedFeatures  =head3 RelatedFeatures
2583    
2584  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2355  Line 2739 
2739  sub GetAll {  sub GetAll {
2740          # Get the parameters.          # Get the parameters.
2741          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2742          # Create the query.      # Call the ERDB method.
2743          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2744          # 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;  
                 $fetched++;  
         }  
2745          # Return the resulting list.          # Return the resulting list.
2746          return @retVal;          return @retVal;
2747  }  }
# Line 2626  Line 2997 
2997      return %retVal;      return %retVal;
2998  }  }
2999    
3000    =head3 MyGenomes
3001    
3002    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3003    
3004    Return a list of the genomes to be included in the Sprout.
3005    
3006    This method is provided for use during the Sprout load. It presumes the Genome load file has
3007    already been created. (It will be in the Sprout data directory and called either C<Genome>
3008    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3009    IDs.
3010    
3011    =over 4
3012    
3013    =item dataDir
3014    
3015    Directory containing the Sprout load files.
3016    
3017    =back
3018    
3019    =cut
3020    #: Return Type @;
3021    sub MyGenomes {
3022        # Get the parameters.
3023        my ($dataDir) = @_;
3024        # Compute the genome file name.
3025        my $genomeFileName = LoadFileName($dataDir, "Genome");
3026        # Extract the genome IDs from the files.
3027        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3028        # Return the result.
3029        return @retVal;
3030    }
3031    
3032    =head3 LoadFileName
3033    
3034    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3035    
3036    Return the name of the load file for the specified table in the specified data
3037    directory.
3038    
3039    =over 4
3040    
3041    =item dataDir
3042    
3043    Directory containing the Sprout load files.
3044    
3045    =item tableName
3046    
3047    Name of the table whose load file is desired.
3048    
3049    =item RETURN
3050    
3051    Returns the name of the file containing the load data for the specified table, or
3052    C<undef> if no load file is present.
3053    
3054    =back
3055    
3056    =cut
3057    #: Return Type $;
3058    sub LoadFileName {
3059        # Get the parameters.
3060        my ($dataDir, $tableName) = @_;
3061        # Declare the return variable.
3062        my $retVal;
3063        # Check for the various file names.
3064        if (-e "$dataDir/$tableName") {
3065            $retVal = "$dataDir/$tableName";
3066        } elsif (-e "$dataDir/$tableName.dtx") {
3067            $retVal = "$dataDir/$tableName.dtx";
3068        }
3069        # Return the result.
3070        return $retVal;
3071    }
3072    
3073  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3074    
3075  =head3 ParseAssignment  =head3 ParseAssignment
3076    
3077  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3078  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3079  will be returned.  isn't, an empty list will be returned.
3080    
3081    A functional assignment is always of the form
3082    
3083        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3084    
3085    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3086    actual functional role. In most cases, the user and the assigning user will be the
3087    same, but that is not always the case.
3088    
3089  This is a static method.  This is a static method.
3090    
# Line 2651  Line 3103 
3103    
3104  =cut  =cut
3105    
3106  sub ParseAssignment {  sub _ParseAssignment {
3107          # Get the parameters.          # Get the parameters.
3108          my ($text) = @_;          my ($text) = @_;
3109          # Declare the return value.          # Declare the return value.
3110          my @retVal = ();          my @retVal = ();
3111          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3112          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3113          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3114                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3115                  @retVal = ($user, $function);          # and the assigning user.
3116            @retVal = ($1, $function, $user);
3117          }          }
3118          # Return the result list.          # Return the result list.
3119          return @retVal;          return @retVal;
# Line 2692  Line 3145 
3145      return $retVal;      return $retVal;
3146  }  }
3147    
3148    =head3 AddProperty
3149    
3150    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3151    
3152    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3153    be added to almost any object. In Sprout, they can only be added to features. In
3154    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3155    pair. If the particular key/value pair coming in is not already in the database, a new
3156    B<Property> record is created to hold it.
3157    
3158    =over 4
3159    
3160    =item peg
3161    
3162    ID of the feature to which the attribute is to be replied.
3163    
3164    =item key
3165    
3166    Name of the attribute (key).
3167    
3168    =item value
3169    
3170    Value of the attribute.
3171    
3172    =item url
3173    
3174    URL or text citation from which the property was obtained.
3175    
3176    =back
3177    
3178    =cut
3179    #: Return Type ;
3180    sub AddProperty {
3181        # Get the parameters.
3182        my ($self, $featureID, $key, $value, $url) = @_;
3183        # Declare the variable to hold the desired property ID.
3184        my $propID;
3185        # Attempt to find a property record for this key/value pair.
3186        my @properties = $self->GetFlat(['Property'],
3187                                       "Property(property-name) = ? AND Property(property-value) = ?",
3188                                       [$key, $value], 'Property(id)');
3189        if (@properties) {
3190            # Here the property is already in the database. We save its ID.
3191            $propID = $properties[0];
3192            # Here the property value does not exist. We need to generate an ID. It will be set
3193            # to a number one greater than the maximum value in the database. This call to
3194            # GetAll will stop after one record.
3195            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3196                                            1);
3197            $propID = $maxProperty[0]->[0] + 1;
3198            # Insert the new property value.
3199            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3200        }
3201        # Now we connect the incoming feature to the property.
3202        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3203    }
3204    
3205    
3206    
3207  1;  1;

Legend:
Removed from v.1.10  
changed lines
  Added in v.1.23

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3