[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 1.27, Wed Sep 14 12:56:13 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$len";
627          }          }
628          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
629          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 792  Line 793 
793                  if ($dir eq '+') {                  if ($dir eq '+') {
794                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
795                  } else {                  } else {
796                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
797                  }                  }
798          }          }
799          # Return the result.          # Return the result.
# Line 1070  Line 1070 
1070  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>
1071    
1072  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
1073  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,
1074  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
1075  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,
1076  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.
1077  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
1078  functional assignments, we will only keep the most recent one.  recent one.
1079    
1080  =over 4  =over 4
1081    
# Line 1109  Line 1109 
1109          # Get the annotation fields.          # Get the annotation fields.
1110          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text) = @{$annotation};
1111                  # Check to see if this is a functional assignment.                  # Check to see if this is a functional assignment.
1112                  my ($user, $function) = ParseAssignment($text);          my ($user, $function) = _ParseAssignment($text);
1113          if ($user && ! exists $timeHash{$user}) {          if ($user && ! exists $timeHash{$user}) {
1114              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1115              # 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 1131 
1131    
1132  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
1133  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
1134  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
1135  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
1136  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
1137  is not a big problem because most features only have a small number of annotations.  most features only have a small number of annotations.
1138    
1139  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
1140  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 1203 
1203              # Get the annotation text.              # Get the annotation text.
1204              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);
1205              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1206              my ($user, $type, $function) = split(/\n/, $text);              my ($user, $function) = _ParseAssignment($text);
1207              if ($type =~ m/^set $user function to$/i) {              if ($user) {
1208                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1209                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1210                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {
# Line 1242  Line 1242 
1242    
1243  =item RETURN  =item RETURN
1244    
1245  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
1246  their best hits.  on the target genome.
1247    
1248  =back  =back
1249    
# Line 1271  Line 1271 
1271          return \%retVal;          return \%retVal;
1272  }  }
1273    
1274    =head3 SimList
1275    
1276    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1277    
1278    Return a list of the similarities to the specified feature.
1279    
1280    Sprout does not support real similarities, so this method just returns the bidirectional
1281    best hits.
1282    
1283    =over 4
1284    
1285    =item featureID
1286    
1287    ID of the feature whose similarities are desired.
1288    
1289    =item count
1290    
1291    Maximum number of similar features to be returned, or C<0> to return them all.
1292    
1293    =back
1294    
1295    =cut
1296    #: Return Type %;
1297    sub SimList {
1298        # Get the parameters.
1299        my ($self, $featureID, $count) = @_;
1300        # Ask for the best hits.
1301        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1302                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1303                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1304                                  $count);
1305        # Create the return value.
1306        my %retVal = ();
1307        for my $tuple (@lists) {
1308            $retVal{$tuple->[0]} = $tuple->[1];
1309        }
1310        # Return the result.
1311        return %retVal;
1312    }
1313    
1314    
1315    
1316    =head3 IsComplete
1317    
1318    C<< my $flag = $sprout->IsComplete($genomeID); >>
1319    
1320    Return TRUE if the specified genome is complete, else FALSE.
1321    
1322    =over 4
1323    
1324    =item genomeID
1325    
1326    ID of the genome whose completeness status is desired.
1327    
1328    =item RETURN
1329    
1330    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1331    not found.
1332    
1333    =back
1334    
1335    =cut
1336    #: Return Type $;
1337    sub IsComplete {
1338        # Get the parameters.
1339        my ($self, $genomeID) = @_;
1340        # Declare the return variable.
1341        my $retVal;
1342        # Get the genome's data.
1343        my $genomeData = $self->GetEntity('Genome', $genomeID);
1344        if ($genomeData) {
1345            # The genome exists, so get the completeness flag.
1346            ($retVal) = $genomeData->Value('complete');
1347        }
1348        # Return the result.
1349        return $retVal;
1350    }
1351    
1352  =head3 FeatureAliases  =head3 FeatureAliases
1353    
1354  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1361  Line 1439 
1439  sub CoupledFeatures {  sub CoupledFeatures {
1440          # Get the parameters.          # Get the parameters.
1441          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1442          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1443          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1444          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1445          # 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.
1446          my $found = 0;          my $found = 0;
1447          # Create the return hash.          # Create the return hash.
1448          my %retVal = ();          my %retVal = ();
1449          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1450          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1451                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1452                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1453                                                            'Coupling(score)']);
1454            # The coupling ID contains the two feature IDs separated by a space. We use
1455            # this information to find the ID of the other feature.
1456            my ($fid1, $fid2) = split / /, $couplingID;
1457            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1458            # Attach the other feature's score to its ID.
1459                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1460                  $found = 1;                  $found = 1;
1461          }          }
# Line 1386  Line 1468 
1468          return %retVal;          return %retVal;
1469  }  }
1470    
1471    =head3 CouplingEvidence
1472    
1473    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1474    
1475    Return the evidence for a functional coupling.
1476    
1477    A pair of features is considered evidence of a coupling between two other
1478    features if they occur close together on a contig and both are similar to
1479    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1480    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1481    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1482    similar to B<A2>.
1483    
1484    The score of a coupling is determined by the number of pieces of evidence
1485    that are considered I<representative>. If several evidence items belong to
1486    a group of genomes that are close to each other, only one of those items
1487    is considered representative. The other evidence items are presumed to be
1488    there because of the relationship between the genomes rather than because
1489    the two proteins generated by the features have a related functionality.
1490    
1491    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1492    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1493    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1494    and FALSE otherwise.
1495    
1496    =over 4
1497    
1498    =item peg1
1499    
1500    ID of the feature of interest.
1501    
1502    =item peg2
1503    
1504    ID of a feature functionally coupled to the feature of interest.
1505    
1506    =item RETURN
1507    
1508    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1509    of interest, a feature similar to the functionally coupled feature, and a flag
1510    that is TRUE for a representative piece of evidence and FALSE otherwise.
1511    
1512    =back
1513    
1514    =cut
1515    #: Return Type @@;
1516    sub CouplingEvidence {
1517        # Get the parameters.
1518        my ($self, $peg1, $peg2) = @_;
1519        # Declare the return variable.
1520        my @retVal = ();
1521        # Our first task is to find out the nature of the coupling: whether or not
1522        # it exists, its score, and whether the features are stored in the same
1523        # order as the ones coming in.
1524        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1525        # Only proceed if a coupling exists.
1526        if ($couplingID) {
1527            # Determine the ordering to place on the evidence items. If we're
1528            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1529            # we want feature 1 before feature 2 (normal).
1530            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1531            my $ordering = ($inverted ? "DESC" : "");
1532            # Get the coupling evidence.
1533            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1534                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1535                                              [$couplingID],
1536                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1537            # Loop through the evidence items. Each piece of evidence is represented by two
1538            # positions in the evidence list, one for each feature on the other side of the
1539            # evidence link. If at some point we want to generalize to couplings with
1540            # more than two positions, this section of code will need to be re-done.
1541            while (@evidenceList > 0) {
1542                my $peg1Data = shift @evidenceList;
1543                my $peg2Data = shift @evidenceList;
1544                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1545                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1546            }
1547            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1548        }
1549        # Return the result.
1550        return @retVal;
1551    }
1552    
1553    =head3 GetCoupling
1554    
1555    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1556    
1557    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1558    exists, we return the coupling ID along with an indicator of whether the
1559    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1560    In the second case, we say the coupling is I<inverted>. The importance of an
1561    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1562    
1563    =over 4
1564    
1565    =item peg1
1566    
1567    ID of the feature of interest.
1568    
1569    =item peg2
1570    
1571    ID of the potentially coupled feature.
1572    
1573    =item RETURN
1574    
1575    Returns a three-element list. The first element contains the database ID of
1576    the coupling. The second element is FALSE if the coupling is stored in the
1577    database in the caller specified order and TRUE if it is stored in the
1578    inverted order. The third element is the coupling's score. If the coupling
1579    does not exist, all three list elements will be C<undef>.
1580    
1581    =back
1582    
1583    =cut
1584    #: Return Type $%@;
1585    sub GetCoupling {
1586        # Get the parameters.
1587        my ($self, $peg1, $peg2) = @_;
1588        # Declare the return values. We'll start with the coupling ID and undefine the
1589        # flag and score until we have more information.
1590        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1591        # Find the coupling data.
1592        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1593                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1594                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1595        # Check to see if we found anything.
1596        if (!@pegs) {
1597            Trace("No coupling found.") if T(Coupling => 4);
1598            # No coupling, so undefine the return value.
1599            $retVal = undef;
1600        } else {
1601            # We have a coupling! Get the score and check for inversion.
1602            $score = $pegs[0]->[1];
1603            my $firstFound = $pegs[0]->[0];
1604            $inverted = ($firstFound ne $peg1);
1605            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1606        }
1607        # Return the result.
1608        return ($retVal, $inverted, $score);
1609    }
1610    
1611    =head3 CouplingID
1612    
1613    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1614    
1615    Return the coupling ID for a pair of feature IDs.
1616    
1617    The coupling ID is currently computed by joining the feature IDs in
1618    sorted order with a space. Client modules (that is, modules which
1619    use Sprout) should not, however, count on this always being the
1620    case. This method provides a way for abstracting the concept of a
1621    coupling ID. All that we know for sure about it is that it can be
1622    generated easily from the feature IDs and the order of the IDs
1623    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1624    will have the same value as C<CouplingID("b1", "a1")>.
1625    
1626    =over 4
1627    
1628    =item peg1
1629    
1630    First feature of interest.
1631    
1632    =item peg2
1633    
1634    Second feature of interest.
1635    
1636    =item RETURN
1637    
1638    Returns the ID that would be used to represent a functional coupling of
1639    the two specified PEGs.
1640    
1641    =back
1642    
1643    =cut
1644    #: Return Type $;
1645    sub CouplingID {
1646        return join " ", sort @_;
1647    }
1648    
1649  =head3 GetEntityTypes  =head3 GetEntityTypes
1650    
1651  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1447  Line 1707 
1707                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1708                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1709                          if ($id) {                          if ($id) {
1710                                  $retVal{$id} = $sequence;                  $retVal{$id} = lc $sequence;
1711                          }                          }
1712                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1713                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1714                  } else {                  } else {
1715                          # 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.
1716                          # First, we get the actual data out.              # First, we get the actual data out. Note that we normalize to lower
1717                # case.
1718                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1719                          $sequence .= $1;                          $sequence .= $1;
1720                  }                  }
1721          }          }
1722          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1723          if ($sequence) {          if ($sequence) {
1724                  $retVal {$id} = $sequence;          $retVal{$id} = lc $sequence;
1725          }          }
1726        # Close the file.
1727        close FASTAFILE;
1728          # Return the hash constructed from the file.          # Return the hash constructed from the file.
1729          return %retVal;          return %retVal;
1730  }  }
# Line 1577  Line 1840 
1840  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
1841  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>.
1842    
1843  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'}); >>
1844    
1845  =over 4  =over 4
1846    
# Line 1656  Line 1919 
1919    
1920  =head3 AssignFunction  =head3 AssignFunction
1921    
1922  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function); >>  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>
1923    
1924  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
1925  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.  
1926    
1927  =over 4  =over 4
1928    
# Line 1670  Line 1932 
1932    
1933  =item user  =item user
1934    
1935  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>.
1936    
1937  =item function  =item function
1938    
1939  Text of the function being assigned.  Text of the function being assigned.
1940    
1941    =item assigningUser (optional)
1942    
1943    Name of the individual user making the assignment. If omitted, defaults to the user group.
1944    
1945  =item RETURN  =item RETURN
1946    
1947  Returns 1 if successful, 0 if an error occurred.  Returns 1 if successful, 0 if an error occurred.
# Line 1686  Line 1952 
1952  #: Return Type $;  #: Return Type $;
1953  sub AssignFunction {  sub AssignFunction {
1954          # Get the parameters.          # Get the parameters.
1955          my ($self, $featureID, $user, $function) = @_;      my ($self, $featureID, $user, $function, $assigningUser) = @_;
1956        # Default the assigning user.
1957        if (! $assigningUser) {
1958            $assigningUser = $user;
1959        }
1960          # Create an annotation string from the parameters.          # Create an annotation string from the parameters.
1961          my $annotationText = "$user\nset $user function to\n$function";      my $annotationText = "$assigningUser\nset $user function to\n$function";
1962          # Get the current time.          # Get the current time.
1963          my $now = time;          my $now = time;
1964          # Declare the return variable.          # Declare the return variable.
# Line 1777  Line 2047 
2047          # Get the parameters.          # Get the parameters.
2048          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2049          # Check for the entity instance.          # Check for the entity instance.
2050        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2051          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2052          # Return an existence indicator.          # Return an existence indicator.
2053          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1968  Line 2239 
2239          return @retVal;          return @retVal;
2240  }  }
2241    
2242    =head3 GetProperties
2243    
2244    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2245    
2246    Return a list of the properties with the specified characteristics.
2247    
2248    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2249    will also be associated with genomes.) A property value is represented by a 4-tuple of
2250    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2251    
2252    =over 4
2253    
2254    =item fid
2255    
2256    ID of the feature possessing the property.
2257    
2258    =item key
2259    
2260    Name or key of the property.
2261    
2262    =item value
2263    
2264    Value of the property.
2265    
2266    =item url
2267    
2268    URL of the document that indicated the property should have this particular value, or an
2269    empty string if no such document exists.
2270    
2271    =back
2272    
2273    The parameters act as a filter for the desired data. Any non-null parameter will
2274    automatically match all the tuples returned. So, specifying just the I<$fid> will
2275    return all the properties of the specified feature; similarly, specifying the I<$key>
2276    and I<$value> parameters will return all the features having the specified property
2277    value.
2278    
2279    A single property key can have many values, representing different ideas about the
2280    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2281    virulent, and another may declare that it is not virulent. A query about the virulence of
2282    C<fig|83333.1.peg.10> would be coded as
2283    
2284        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2285    
2286    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2287    not to be filtered. The tuples returned would be
2288    
2289        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2290        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2291    
2292    =cut
2293    #: Return Type @@;
2294    sub GetProperties {
2295        # Get the parameters.
2296        my ($self, @parms) = @_;
2297        # Declare the return variable.
2298        my @retVal = ();
2299        # Now we need to create a WHERE clause that will get us the data we want. First,
2300        # we create a list of the columns containing the data for each parameter.
2301        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2302                        'Property(property-value)', 'HasProperty(evidence)');
2303        # Now we build the WHERE clause and the list of parameter values.
2304        my @where = ();
2305        my @values = ();
2306        for (my $i = 0; $i <= $#colNames; $i++) {
2307            my $parm = $parms[$i];
2308            if (defined $parm && ($parm ne '')) {
2309                push @where, "$colNames[$i] = ?";
2310                push @values, $parm;
2311            }
2312        }
2313        # Format the WHERE clause.
2314        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2315        # Ask for all the propertie values with the desired characteristics.
2316        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2317        while (my $valueObject = $query->Fetch()) {
2318            my @tuple = $valueObject->Values(\@colNames);
2319            push @retVal, \@tuple;
2320        }
2321        # Return the result.
2322        return @retVal;
2323    }
2324    
2325  =head3 FeatureProperties  =head3 FeatureProperties
2326    
2327  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2162  Line 2516 
2516  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2517    
2518  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
2519  to the role the feature performs.  to the roles the feature performs.
2520    
2521  =over 4  =over 4
2522    
# Line 2172  Line 2526 
2526    
2527  =item RETURN  =item RETURN
2528    
2529  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.
2530    
2531  =back  =back
2532    
2533  =cut  =cut
2534  #: Return Type %;  #: Return Type %@;
2535  sub SubsystemsOf {  sub SubsystemsOf {
2536          # Get the parameters.          # Get the parameters.
2537          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2538          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2539          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2540                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2541                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2189  Line 2543 
2543          my %retVal = ();          my %retVal = ();
2544          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2545          for my $record (@subsystems) {          for my $record (@subsystems) {
2546                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2547            if (exists $retVal{$subsys}) {
2548                push @{$retVal{$subsys}}, $role;
2549            } else {
2550                $retVal{$subsys} = [$role];
2551            }
2552          }          }
2553          # Return the hash.          # Return the hash.
2554          return %retVal;          return %retVal;
2555  }  }
2556    
2557    =head3 SubsystemList
2558    
2559    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2560    
2561    Return a list containing the names of the subsystems in which the specified
2562    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2563    subsystem names, not the roles.
2564    
2565    =over 4
2566    
2567    =item featureID
2568    
2569    ID of the feature whose subsystem names are desired.
2570    
2571    =item RETURN
2572    
2573    Returns a list of the names of the subsystems in which the feature participates.
2574    
2575    =back
2576    
2577    =cut
2578    #: Return Type @;
2579    sub SubsystemList {
2580        # Get the parameters.
2581        my ($self, $featureID) = @_;
2582        # Get the list of names.
2583        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2584                                    [$featureID], 'HasSSCell(from-link)');
2585        # Return the result.
2586        return @retVal;
2587    }
2588    
2589  =head3 RelatedFeatures  =head3 RelatedFeatures
2590    
2591  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2355  Line 2746 
2746  sub GetAll {  sub GetAll {
2747          # Get the parameters.          # Get the parameters.
2748          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2749          # Create the query.      # Call the ERDB method.
2750          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2751          # 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;  
                 $fetched++;  
         }  
2752          # Return the resulting list.          # Return the resulting list.
2753          return @retVal;          return @retVal;
2754  }  }
# Line 2626  Line 3004 
3004      return %retVal;      return %retVal;
3005  }  }
3006    
3007    =head3 MyGenomes
3008    
3009    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3010    
3011    Return a list of the genomes to be included in the Sprout.
3012    
3013    This method is provided for use during the Sprout load. It presumes the Genome load file has
3014    already been created. (It will be in the Sprout data directory and called either C<Genome>
3015    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3016    IDs.
3017    
3018    =over 4
3019    
3020    =item dataDir
3021    
3022    Directory containing the Sprout load files.
3023    
3024    =back
3025    
3026    =cut
3027    #: Return Type @;
3028    sub MyGenomes {
3029        # Get the parameters.
3030        my ($dataDir) = @_;
3031        # Compute the genome file name.
3032        my $genomeFileName = LoadFileName($dataDir, "Genome");
3033        # Extract the genome IDs from the files.
3034        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3035        # Return the result.
3036        return @retVal;
3037    }
3038    
3039    =head3 LoadFileName
3040    
3041    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3042    
3043    Return the name of the load file for the specified table in the specified data
3044    directory.
3045    
3046    =over 4
3047    
3048    =item dataDir
3049    
3050    Directory containing the Sprout load files.
3051    
3052    =item tableName
3053    
3054    Name of the table whose load file is desired.
3055    
3056    =item RETURN
3057    
3058    Returns the name of the file containing the load data for the specified table, or
3059    C<undef> if no load file is present.
3060    
3061    =back
3062    
3063    =cut
3064    #: Return Type $;
3065    sub LoadFileName {
3066        # Get the parameters.
3067        my ($dataDir, $tableName) = @_;
3068        # Declare the return variable.
3069        my $retVal;
3070        # Check for the various file names.
3071        if (-e "$dataDir/$tableName") {
3072            $retVal = "$dataDir/$tableName";
3073        } elsif (-e "$dataDir/$tableName.dtx") {
3074            $retVal = "$dataDir/$tableName.dtx";
3075        }
3076        # Return the result.
3077        return $retVal;
3078    }
3079    
3080  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3081    
3082  =head3 ParseAssignment  =head3 ParseAssignment
3083    
3084  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
3085  the user and function text will be returned as a 2-element list. If it isn't, an empty list  the user, function text, and assigning user will be returned as a 3-element list. If it
3086  will be returned.  isn't, an empty list will be returned.
3087    
3088    A functional assignment is always of the form
3089    
3090        I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>
3091    
3092    where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the
3093    actual functional role. In most cases, the user and the assigning user will be the
3094    same, but that is not always the case.
3095    
3096  This is a static method.  This is a static method.
3097    
# Line 2651  Line 3110 
3110    
3111  =cut  =cut
3112    
3113  sub ParseAssignment {  sub _ParseAssignment {
3114          # Get the parameters.          # Get the parameters.
3115          my ($text) = @_;          my ($text) = @_;
3116          # Declare the return value.          # Declare the return value.
3117          my @retVal = ();          my @retVal = ();
3118          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
3119          my ($user, $type, $function) = split(/\n/, $text);          my ($user, $type, $function) = split(/\n/, $text);
3120          if ($type =~ m/^set $user function to$/i) {      if ($type =~ m/^set ([^ ]+) function to$/i) {
3121                  # Here it is, so we return the user name and function text.          # Here it is, so we return the user name (which is in $1), the functional role text,
3122                  @retVal = ($user, $function);          # and the assigning user.
3123            @retVal = ($1, $function, $user);
3124          }          }
3125          # Return the result list.          # Return the result list.
3126          return @retVal;          return @retVal;
# Line 2692  Line 3152 
3152      return $retVal;      return $retVal;
3153  }  }
3154    
3155    =head3 AddProperty
3156    
3157    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3158    
3159    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3160    be added to almost any object. In Sprout, they can only be added to features. In
3161    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3162    pair. If the particular key/value pair coming in is not already in the database, a new
3163    B<Property> record is created to hold it.
3164    
3165    =over 4
3166    
3167    =item peg
3168    
3169    ID of the feature to which the attribute is to be replied.
3170    
3171    =item key
3172    
3173    Name of the attribute (key).
3174    
3175    =item value
3176    
3177    Value of the attribute.
3178    
3179    =item url
3180    
3181    URL or text citation from which the property was obtained.
3182    
3183    =back
3184    
3185    =cut
3186    #: Return Type ;
3187    sub AddProperty {
3188        # Get the parameters.
3189        my ($self, $featureID, $key, $value, $url) = @_;
3190        # Declare the variable to hold the desired property ID.
3191        my $propID;
3192        # Attempt to find a property record for this key/value pair.
3193        my @properties = $self->GetFlat(['Property'],
3194                                       "Property(property-name) = ? AND Property(property-value) = ?",
3195                                       [$key, $value], 'Property(id)');
3196        if (@properties) {
3197            # Here the property is already in the database. We save its ID.
3198            $propID = $properties[0];
3199            # Here the property value does not exist. We need to generate an ID. It will be set
3200            # to a number one greater than the maximum value in the database. This call to
3201            # GetAll will stop after one record.
3202            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3203                                            1);
3204            $propID = $maxProperty[0]->[0] + 1;
3205            # Insert the new property value.
3206            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3207        }
3208        # Now we connect the incoming feature to the property.
3209        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3210    }
3211    
3212    
3213    
3214  1;  1;

Legend:
Removed from v.1.10  
changed lines
  Added in v.1.27

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3