[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 1.26, Tue Sep 13 18:33:20 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, $xmlFileName);
# Line 269  Line 281 
281  sub GetEntity {  sub GetEntity {
282          # Get the parameters.          # Get the parameters.
283          my ($self, $entityType, $ID) = @_;          my ($self, $entityType, $ID) = @_;
284          # Create a query.      # Call the ERDB method.
285          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 $retVal;  
286  }  }
287    
288  =head3 GetEntityValues  =head3 GetEntityValues
# Line 308  Line 316 
316  sub GetEntityValues {  sub GetEntityValues {
317          # Get the parameters.          # Get the parameters.
318          my ($self, $entityType, $ID, $fields) = @_;          my ($self, $entityType, $ID, $fields) = @_;
319          # Get the specified entity.      # Call the ERDB method.
320          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;  
321  }  }
322    
323  =head3 ShowMetaData  =head3 ShowMetaData
# Line 432  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 $retVal;
447  }  }
# Line 582  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 625  Line 626 
626                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
627          }          }
628          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
629          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 1070  Line 1071 
1071  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1072    
1073  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
1074  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,
1075  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
1076  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,
1077  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.
1078  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
1079  functional assignments, we will only keep the most recent one.  recent one.
1080    
1081  =over 4  =over 4
1082    
# Line 1109  Line 1110 
1110          # Get the annotation fields.          # Get the annotation fields.
1111          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text) = @{$annotation};
1112                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1113                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1114          if ($user && ! exists $timeHash{$user}) {          if ($user && ! exists $timeHash{$user}) {
1115              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1116              # 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 1132 
1132    
1133  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
1134  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
1135  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
1136  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
1137  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
1138  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1139    
1140  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
1141  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 1204 
1204              # Get the annotation text.              # Get the annotation text.
1205              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1206              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1207              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1208              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1209                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1210                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1211                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1242  Line 1243 
1243    
1244  =item RETURN  =item RETURN
1245    
1246  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
1247  their best hits.  on the target genome.
1248    
1249  =back  =back
1250    
# Line 1271  Line 1272 
1272          return \%retVal;          return \%retVal;
1273  }  }
1274    
1275    =head3 SimList
1276    
1277    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1278    
1279    Return a list of the similarities to the specified feature.
1280    
1281    Sprout does not support real similarities, so this method just returns the bidirectional
1282    best hits.
1283    
1284    =over 4
1285    
1286    =item featureID
1287    
1288    ID of the feature whose similarities are desired.
1289    
1290    =item count
1291    
1292    Maximum number of similar features to be returned, or C<0> to return them all.
1293    
1294    =back
1295    
1296    =cut
1297    #: Return Type %;
1298    sub SimList {
1299        # Get the parameters.
1300        my ($self, $featureID, $count) = @_;
1301        # Ask for the best hits.
1302        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1303                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1304                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1305                                  $count);
1306        # Create the return value.
1307        my %retVal = ();
1308        for my $tuple (@lists) {
1309            $retVal{$tuple->[0]} = $tuple->[1];
1310        }
1311        # Return the result.
1312        return %retVal;
1313    }
1314    
1315    
1316    
1317    =head3 IsComplete
1318    
1319    C<< my $flag = $sprout->IsComplete($genomeID); >>
1320    
1321    Return TRUE if the specified genome is complete, else FALSE.
1322    
1323    =over 4
1324    
1325    =item genomeID
1326    
1327    ID of the genome whose completeness status is desired.
1328    
1329    =item RETURN
1330    
1331    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1332    not found.
1333    
1334    =back
1335    
1336    =cut
1337    #: Return Type $;
1338    sub IsComplete {
1339        # Get the parameters.
1340        my ($self, $genomeID) = @_;
1341        # Declare the return variable.
1342        my $retVal;
1343        # Get the genome's data.
1344        my $genomeData = $self->GetEntity('Genome', $genomeID);
1345        if ($genomeData) {
1346            # The genome exists, so get the completeness flag.
1347            ($retVal) = $genomeData->Value('complete');
1348        }
1349        # Return the result.
1350        return $retVal;
1351    }
1352    
1353  =head3 FeatureAliases  =head3 FeatureAliases
1354    
1355  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1361  Line 1440 
1440  sub CoupledFeatures {  sub CoupledFeatures {
1441          # Get the parameters.          # Get the parameters.
1442          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1443          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1444          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1445          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1446          # 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.
1447          my $found = 0;          my $found = 0;
1448          # Create the return hash.          # Create the return hash.
1449          my %retVal = ();          my %retVal = ();
1450          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1451          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1452                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1453                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1454                                                            'Coupling(score)']);
1455            # The coupling ID contains the two feature IDs separated by a space. We use
1456            # this information to find the ID of the other feature.
1457            my ($fid1, $fid2) = split / /, $couplingID;
1458            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1459            # Attach the other feature's score to its ID.
1460                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1461                  $found = 1;                  $found = 1;
1462          }          }
# Line 1386  Line 1469 
1469          return %retVal;          return %retVal;
1470  }  }
1471    
1472    =head3 CouplingEvidence
1473    
1474    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1475    
1476    Return the evidence for a functional coupling.
1477    
1478    A pair of features is considered evidence of a coupling between two other
1479    features if they occur close together on a contig and both are similar to
1480    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1481    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1482    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1483    similar to B<A2>.
1484    
1485    The score of a coupling is determined by the number of pieces of evidence
1486    that are considered I<representative>. If several evidence items belong to
1487    a group of genomes that are close to each other, only one of those items
1488    is considered representative. The other evidence items are presumed to be
1489    there because of the relationship between the genomes rather than because
1490    the two proteins generated by the features have a related functionality.
1491    
1492    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1493    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1494    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1495    and FALSE otherwise.
1496    
1497    =over 4
1498    
1499    =item peg1
1500    
1501    ID of the feature of interest.
1502    
1503    =item peg2
1504    
1505    ID of a feature functionally coupled to the feature of interest.
1506    
1507    =item RETURN
1508    
1509    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1510    of interest, a feature similar to the functionally coupled feature, and a flag
1511    that is TRUE for a representative piece of evidence and FALSE otherwise.
1512    
1513    =back
1514    
1515    =cut
1516    #: Return Type @@;
1517    sub CouplingEvidence {
1518        # Get the parameters.
1519        my ($self, $peg1, $peg2) = @_;
1520        # Declare the return variable.
1521        my @retVal = ();
1522        # Our first task is to find out the nature of the coupling: whether or not
1523        # it exists, its score, and whether the features are stored in the same
1524        # order as the ones coming in.
1525        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1526        # Only proceed if a coupling exists.
1527        if ($couplingID) {
1528            # Determine the ordering to place on the evidence items. If we're
1529            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1530            # we want feature 1 before feature 2 (normal).
1531            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1532            my $ordering = ($inverted ? "DESC" : "");
1533            # Get the coupling evidence.
1534            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1535                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1536                                              [$couplingID],
1537                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1538            # Loop through the evidence items. Each piece of evidence is represented by two
1539            # positions in the evidence list, one for each feature on the other side of the
1540            # evidence link. If at some point we want to generalize to couplings with
1541            # more than two positions, this section of code will need to be re-done.
1542            while (@evidenceList > 0) {
1543                my $peg1Data = shift @evidenceList;
1544                my $peg2Data = shift @evidenceList;
1545                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1546                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1547            }
1548            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1549        }
1550        # Return the result.
1551        return @retVal;
1552    }
1553    
1554    =head3 GetCoupling
1555    
1556    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1557    
1558    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1559    exists, we return the coupling ID along with an indicator of whether the
1560    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1561    In the second case, we say the coupling is I<inverted>. The importance of an
1562    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1563    
1564    =over 4
1565    
1566    =item peg1
1567    
1568    ID of the feature of interest.
1569    
1570    =item peg2
1571    
1572    ID of the potentially coupled feature.
1573    
1574    =item RETURN
1575    
1576    Returns a three-element list. The first element contains the database ID of
1577    the coupling. The second element is FALSE if the coupling is stored in the
1578    database in the caller specified order and TRUE if it is stored in the
1579    inverted order. The third element is the coupling's score. If the coupling
1580    does not exist, all three list elements will be C<undef>.
1581    
1582    =back
1583    
1584    =cut
1585    #: Return Type $%@;
1586    sub GetCoupling {
1587        # Get the parameters.
1588        my ($self, $peg1, $peg2) = @_;
1589        # Declare the return values. We'll start with the coupling ID and undefine the
1590        # flag and score until we have more information.
1591        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1592        # Find the coupling data.
1593        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1594                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1595                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1596        # Check to see if we found anything.
1597        if (!@pegs) {
1598            Trace("No coupling found.") if T(Coupling => 4);
1599            # No coupling, so undefine the return value.
1600            $retVal = undef;
1601        } else {
1602            # We have a coupling! Get the score and check for inversion.
1603            $score = $pegs[0]->[1];
1604            my $firstFound = $pegs[0]->[0];
1605            $inverted = ($firstFound ne $peg1);
1606            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1607        }
1608        # Return the result.
1609        return ($retVal, $inverted, $score);
1610    }
1611    
1612    =head3 CouplingID
1613    
1614    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1615    
1616    Return the coupling ID for a pair of feature IDs.
1617    
1618    The coupling ID is currently computed by joining the feature IDs in
1619    sorted order with a space. Client modules (that is, modules which
1620    use Sprout) should not, however, count on this always being the
1621    case. This method provides a way for abstracting the concept of a
1622    coupling ID. All that we know for sure about it is that it can be
1623    generated easily from the feature IDs and the order of the IDs
1624    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1625    will have the same value as C<CouplingID("b1", "a1")>.
1626    
1627    =over 4
1628    
1629    =item peg1
1630    
1631    First feature of interest.
1632    
1633    =item peg2
1634    
1635    Second feature of interest.
1636    
1637    =item RETURN
1638    
1639    Returns the ID that would be used to represent a functional coupling of
1640    the two specified PEGs.
1641    
1642    =back
1643    
1644    =cut
1645    #: Return Type $;
1646    sub CouplingID {
1647        return join " ", sort @_;
1648    }
1649    
1650  =head3 GetEntityTypes  =head3 GetEntityTypes
1651    
1652  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1447  Line 1708 
1708                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1709                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1710                          if ($id) {                          if ($id) {
1711                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1712                          }                          }
1713                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1714                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1715                  } else {                  } else {
1716                          # 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.
1717                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1718                # case.
1719                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1720                          $sequence .= $1;                          $sequence .= $1;
1721                  }                  }
1722          }          }
1723          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1724          if ($sequence) {          if ($sequence) {
1725                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1726          }          }
1727        # Close the file.
1728        close FASTAFILE;
1729          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1730          return %retVal;          return %retVal;
1731  }  }
# Line 1577  Line 1841 
1841  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
1842  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>.
1843    
1844  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'}); >>
1845    
1846  =over 4  =over 4
1847    
# Line 1656  Line 1920 
1920    
1921  =head3 AssignFunction  =head3 AssignFunction
1922    
1923  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1924    
1925  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
1926  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.  
1927    
1928  =over 4  =over 4
1929    
# Line 1670  Line 1933 
1933    
1934  =item user  =item user
1935    
1936  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>.
1937    
1938  =item function  =item function
1939    
1940  Text of the function being assigned.  Text of the function being assigned.
1941    
1942    =item assigningUser (optional)
1943    
1944    Name of the individual user making the assignment. If omitted, defaults to the user group.
1945    
1946  =item RETURN  =item RETURN
1947    
1948  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1686  Line 1953 
1953  #: Return Type $;  #: Return Type $;
1954  sub AssignFunction {  sub AssignFunction {
1955          # Get the parameters.          # Get the parameters.
1956          my ($self, $featureID, $user, $function) = @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1957        # Default the assigning user.
1958        if (! $assigningUser) {
1959            $assigningUser = $user;
1960        }
1961          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1962          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1963          # Get the current time.          # Get the current time.
1964          my $now = time;          my $now = time;
1965          # Declare the return variable.          # Declare the return variable.
# Line 1777  Line 2048 
2048          # Get the parameters.          # Get the parameters.
2049          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2050          # Check for the entity instance.          # Check for the entity instance.
2051        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2052          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2053          # Return an existence indicator.          # Return an existence indicator.
2054          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1968  Line 2240 
2240          return @retVal;          return @retVal;
2241  }  }
2242    
2243    =head3 GetProperties
2244    
2245    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2246    
2247    Return a list of the properties with the specified characteristics.
2248    
2249    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2250    will also be associated with genomes.) A property value is represented by a 4-tuple of
2251    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2252    
2253    =over 4
2254    
2255    =item fid
2256    
2257    ID of the feature possessing the property.
2258    
2259    =item key
2260    
2261    Name or key of the property.
2262    
2263    =item value
2264    
2265    Value of the property.
2266    
2267    =item url
2268    
2269    URL of the document that indicated the property should have this particular value, or an
2270    empty string if no such document exists.
2271    
2272    =back
2273    
2274    The parameters act as a filter for the desired data. Any non-null parameter will
2275    automatically match all the tuples returned. So, specifying just the I<$fid> will
2276    return all the properties of the specified feature; similarly, specifying the I<$key>
2277    and I<$value> parameters will return all the features having the specified property
2278    value.
2279    
2280    A single property key can have many values, representing different ideas about the
2281    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2282    virulent, and another may declare that it is not virulent. A query about the virulence of
2283    C<fig|83333.1.peg.10> would be coded as
2284    
2285        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2286    
2287    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2288    not to be filtered. The tuples returned would be
2289    
2290        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2291        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2292    
2293    =cut
2294    #: Return Type @@;
2295    sub GetProperties {
2296        # Get the parameters.
2297        my ($self, @parms) = @_;
2298        # Declare the return variable.
2299        my @retVal = ();
2300        # Now we need to create a WHERE clause that will get us the data we want. First,
2301        # we create a list of the columns containing the data for each parameter.
2302        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2303                        'Property(property-value)', 'HasProperty(evidence)');
2304        # Now we build the WHERE clause and the list of parameter values.
2305        my @where = ();
2306        my @values = ();
2307        for (my $i = 0; $i <= $#colNames; $i++) {
2308            my $parm = $parms[$i];
2309            if (defined $parm && ($parm ne '')) {
2310                push @where, "$colNames[$i] = ?";
2311                push @values, $parm;
2312            }
2313        }
2314        # Format the WHERE clause.
2315        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2316        # Ask for all the propertie values with the desired characteristics.
2317        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2318        while (my $valueObject = $query->Fetch()) {
2319            my @tuple = $valueObject->Values(\@colNames);
2320            push @retVal, \@tuple;
2321        }
2322        # Return the result.
2323        return @retVal;
2324    }
2325    
2326  =head3 FeatureProperties  =head3 FeatureProperties
2327    
2328  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2162  Line 2517 
2517  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2518    
2519  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
2520  to the role the feature performs.  to the roles the feature performs.
2521    
2522  =over 4  =over 4
2523    
# Line 2172  Line 2527 
2527    
2528  =item RETURN  =item RETURN
2529    
2530  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.
2531    
2532  =back  =back
2533    
2534  =cut  =cut
2535  #: Return Type %;  #: Return Type %@;
2536  sub SubsystemsOf {  sub SubsystemsOf {
2537          # Get the parameters.          # Get the parameters.
2538          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2539          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2540          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2541                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2542                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2189  Line 2544 
2544          my %retVal = ();          my %retVal = ();
2545          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2546          for my $record (@subsystems) {          for my $record (@subsystems) {
2547                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2548            if (exists $retVal{$subsys}) {
2549                push @{$retVal{$subsys}}, $role;
2550            } else {
2551                $retVal{$subsys} = [$role];
2552            }
2553          }          }
2554          # Return the hash.          # Return the hash.
2555          return %retVal;          return %retVal;
2556  }  }
2557    
2558    =head3 SubsystemList
2559    
2560    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2561    
2562    Return a list containing the names of the subsystems in which the specified
2563    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2564    subsystem names, not the roles.
2565    
2566    =over 4
2567    
2568    =item featureID
2569    
2570    ID of the feature whose subsystem names are desired.
2571    
2572    =item RETURN
2573    
2574    Returns a list of the names of the subsystems in which the feature participates.
2575    
2576    =back
2577    
2578    =cut
2579    #: Return Type @;
2580    sub SubsystemList {
2581        # Get the parameters.
2582        my ($self, $featureID) = @_;
2583        # Get the list of names.
2584        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2585                                    [$featureID], 'HasSSCell(from-link)');
2586        # Return the result.
2587        return @retVal;
2588    }
2589    
2590  =head3 RelatedFeatures  =head3 RelatedFeatures
2591    
2592  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2355  Line 2747 
2747  sub GetAll {  sub GetAll {
2748          # Get the parameters.          # Get the parameters.
2749          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2750          # Create the query.      # Call the ERDB method.
2751          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2752          # 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;  
                 $fetched++;  
         }  
2753          # Return the resulting list.          # Return the resulting list.
2754          return @retVal;          return @retVal;
2755  }  }
# Line 2626  Line 3005 
3005      return %retVal;      return %retVal;
3006  }  }
3007    
3008    =head3 MyGenomes
3009    
3010    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3011    
3012    Return a list of the genomes to be included in the Sprout.
3013    
3014    This method is provided for use during the Sprout load. It presumes the Genome load file has
3015    already been created. (It will be in the Sprout data directory and called either C<Genome>
3016    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3017    IDs.
3018    
3019    =over 4
3020    
3021    =item dataDir
3022    
3023    Directory containing the Sprout load files.
3024    
3025    =back
3026    
3027    =cut
3028    #: Return Type @;
3029    sub MyGenomes {
3030        # Get the parameters.
3031        my ($dataDir) = @_;
3032        # Compute the genome file name.
3033        my $genomeFileName = LoadFileName($dataDir, "Genome");
3034        # Extract the genome IDs from the files.
3035        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3036        # Return the result.
3037        return @retVal;
3038    }
3039    
3040    =head3 LoadFileName
3041    
3042    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3043    
3044    Return the name of the load file for the specified table in the specified data
3045    directory.
3046    
3047    =over 4
3048    
3049    =item dataDir
3050    
3051    Directory containing the Sprout load files.
3052    
3053    =item tableName
3054    
3055    Name of the table whose load file is desired.
3056    
3057    =item RETURN
3058    
3059    Returns the name of the file containing the load data for the specified table, or
3060    C<undef> if no load file is present.
3061    
3062    =back
3063    
3064    =cut
3065    #: Return Type $;
3066    sub LoadFileName {
3067        # Get the parameters.
3068        my ($dataDir, $tableName) = @_;
3069        # Declare the return variable.
3070        my $retVal;
3071        # Check for the various file names.
3072        if (-e "$dataDir/$tableName") {
3073            $retVal = "$dataDir/$tableName";
3074        } elsif (-e "$dataDir/$tableName.dtx") {
3075            $retVal = "$dataDir/$tableName.dtx";
3076        }
3077        # Return the result.
3078        return $retVal;
3079    }
3080    
3081  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3082    
3083  =head3 ParseAssignment  =head3 ParseAssignment
3084    
3085  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3086  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3087  will be returned.  isn't, an empty list will be returned.
3088    
3089    A functional assignment is always of the form
3090    
3091        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3092    
3093    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3094    actual functional role. In most cases, the user and the assigning user will be the
3095    same, but that is not always the case.
3096    
3097  This is a static method.  This is a static method.
3098    
# Line 2651  Line 3111 
3111    
3112  =cut  =cut
3113    
3114  sub ParseAssignment {  sub _ParseAssignment {
3115          # Get the parameters.          # Get the parameters.
3116          my ($text) = @_;          my ($text) = @_;
3117          # Declare the return value.          # Declare the return value.
3118          my @retVal = ();          my @retVal = ();
3119          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3120          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3121          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3122                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3123                  @retVal = ($user, $function);          # and the assigning user.
3124            @retVal = ($1, $function, $user);
3125          }          }
3126          # Return the result list.          # Return the result list.
3127          return @retVal;          return @retVal;
# Line 2692  Line 3153 
3153      return $retVal;      return $retVal;
3154  }  }
3155    
3156    =head3 AddProperty
3157    
3158    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3159    
3160    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3161    be added to almost any object. In Sprout, they can only be added to features. In
3162    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3163    pair. If the particular key/value pair coming in is not already in the database, a new
3164    B<Property> record is created to hold it.
3165    
3166    =over 4
3167    
3168    =item peg
3169    
3170    ID of the feature to which the attribute is to be replied.
3171    
3172    =item key
3173    
3174    Name of the attribute (key).
3175    
3176    =item value
3177    
3178    Value of the attribute.
3179    
3180    =item url
3181    
3182    URL or text citation from which the property was obtained.
3183    
3184    =back
3185    
3186    =cut
3187    #: Return Type ;
3188    sub AddProperty {
3189        # Get the parameters.
3190        my ($self, $featureID, $key, $value, $url) = @_;
3191        # Declare the variable to hold the desired property ID.
3192        my $propID;
3193        # Attempt to find a property record for this key/value pair.
3194        my @properties = $self->GetFlat(['Property'],
3195                                       "Property(property-name) = ? AND Property(property-value) = ?",
3196                                       [$key, $value], 'Property(id)');
3197        if (@properties) {
3198            # Here the property is already in the database. We save its ID.
3199            $propID = $properties[0];
3200            # Here the property value does not exist. We need to generate an ID. It will be set
3201            # to a number one greater than the maximum value in the database. This call to
3202            # GetAll will stop after one record.
3203            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3204                                            1);
3205            $propID = $maxProperty[0]->[0] + 1;
3206            # Insert the new property value.
3207            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3208        }
3209        # Now we connect the incoming feature to the property.
3210        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3211    }
3212    
3213    
3214    
3215  1;  1;

Legend:
Removed from v.1.10  
changed lines
  Added in v.1.26

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3