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

Diff of /Sprout/Sprout.pm

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

revision 1.12, Wed May 4 03:24:43 2005 UTC revision 1.22, Fri Sep 9 21:10:46 2005 UTC
# Line 86  Line 86 
86          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
87          # the incoming data.          # the incoming data.
88          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
89                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
90                                             dataDir              => 'Data',                      # data file directory                                                          # database type
91                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
92                                             userData             => 'root/',                     # user name and password                                                          # data file directory
93                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
94                                                            # database definition file name
95                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
96                                                            # user name and password
97                           port         => $FIG_Config::dbport,
98                                                            # database connection port
99                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
100                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
101                                            }, $options);                                            }, $options);
# Line 420  Line 425 
425          # Loop through the incoming table names.          # Loop through the incoming table names.
426          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
427                  # Find the table's file.                  # Find the table's file.
428                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
429                  if (! -e $fileName) {          if (! $fileName) {
430                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
431                  }          } else {
432                  # Attempt to load this table.                  # Attempt to load this table.
433                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
434                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
435                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
436          }          }
437        }
438          # Return the statistics.          # Return the statistics.
439          return $retVal;          return $retVal;
440  }  }
# Line 570  Line 576 
576  =item RETURN  =item RETURN
577    
578  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
579  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
580    
581  =back  =back
582    
# Line 613  Line 619 
619                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
620          }          }
621          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
622          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
623  }  }
624    
625  =head3 ParseLocation  =head3 ParseLocation
# Line 1230  Line 1236 
1236    
1237  =item RETURN  =item RETURN
1238    
1239  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1240  their best hits.  on the target genome.
1241    
1242  =back  =back
1243    
# Line 1259  Line 1265 
1265          return \%retVal;          return \%retVal;
1266  }  }
1267    
1268    =head3 SimList
1269    
1270    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1271    
1272    Return a list of the similarities to the specified feature.
1273    
1274    Sprout does not support real similarities, so this method just returns the bidirectional
1275    best hits.
1276    
1277    =over 4
1278    
1279    =item featureID
1280    
1281    ID of the feature whose similarities are desired.
1282    
1283    =item count
1284    
1285    Maximum number of similar features to be returned, or C<0> to return them all.
1286    
1287    =back
1288    
1289    =cut
1290    #: Return Type %;
1291    sub SimList {
1292        # Get the parameters.
1293        my ($self, $featureID, $count) = @_;
1294        # Ask for the best hits.
1295        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1296                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1297                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1298                                  $count);
1299        # Create the return value.
1300        my %retVal = ();
1301        for my $tuple (@lists) {
1302            $retVal{$tuple->[0]} = $tuple->[1];
1303        }
1304        # Return the result.
1305        return %retVal;
1306    }
1307    
1308    
1309    
1310    =head3 IsComplete
1311    
1312    C<< my $flag = $sprout->IsComplete($genomeID); >>
1313    
1314    Return TRUE if the specified genome is complete, else FALSE.
1315    
1316    =over 4
1317    
1318    =item genomeID
1319    
1320    ID of the genome whose completeness status is desired.
1321    
1322    =item RETURN
1323    
1324    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1325    not found.
1326    
1327    =back
1328    
1329    =cut
1330    #: Return Type $;
1331    sub IsComplete {
1332        # Get the parameters.
1333        my ($self, $genomeID) = @_;
1334        # Declare the return variable.
1335        my $retVal;
1336        # Get the genome's data.
1337        my $genomeData = $self->GetEntity('Genome', $genomeID);
1338        if ($genomeData) {
1339            # The genome exists, so get the completeness flag.
1340            ($retVal) = $genomeData->Value('complete');
1341        }
1342        # Return the result.
1343        return $retVal;
1344    }
1345    
1346  =head3 FeatureAliases  =head3 FeatureAliases
1347    
1348  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1433 
1433  sub CoupledFeatures {  sub CoupledFeatures {
1434          # Get the parameters.          # Get the parameters.
1435          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1436          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1437          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1438          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1439          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1440          my $found = 0;          my $found = 0;
1441          # Create the return hash.          # Create the return hash.
1442          my %retVal = ();          my %retVal = ();
1443          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1444          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1445                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1446                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1447                                                            'Coupling(score)']);
1448            # The coupling ID contains the two feature IDs separated by a space. We use
1449            # this information to find the ID of the other feature.
1450            my ($fid1, $fid2) = split / /, $couplingID;
1451            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1452            # Attach the other feature's score to its ID.
1453                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1454                  $found = 1;                  $found = 1;
1455          }          }
# Line 1374  Line 1462 
1462          return %retVal;          return %retVal;
1463  }  }
1464    
1465    =head3 CouplingEvidence
1466    
1467    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1468    
1469    Return the evidence for a functional coupling.
1470    
1471    A pair of features is considered evidence of a coupling between two other
1472    features if they occur close together on a contig and both are similar to
1473    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1474    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1475    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1476    similar to B<A2>.
1477    
1478    The score of a coupling is determined by the number of pieces of evidence
1479    that are considered I<representative>. If several evidence items belong to
1480    a group of genomes that are close to each other, only one of those items
1481    is considered representative. The other evidence items are presumed to be
1482    there because of the relationship between the genomes rather than because
1483    the two proteins generated by the features have a related functionality.
1484    
1485    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1486    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1487    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1488    and FALSE otherwise.
1489    
1490    =over 4
1491    
1492    =item peg1
1493    
1494    ID of the feature of interest.
1495    
1496    =item peg2
1497    
1498    ID of a feature functionally coupled to the feature of interest.
1499    
1500    =item RETURN
1501    
1502    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1503    of interest, a feature similar to the functionally coupled feature, and a flag
1504    that is TRUE for a representative piece of evidence and FALSE otherwise.
1505    
1506    =back
1507    
1508    =cut
1509    #: Return Type @@;
1510    sub CouplingEvidence {
1511        # Get the parameters.
1512        my ($self, $peg1, $peg2) = @_;
1513        # Declare the return variable.
1514        my @retVal = ();
1515        # Our first task is to find out the nature of the coupling: whether or not
1516        # it exists, its score, and whether the features are stored in the same
1517        # order as the ones coming in.
1518        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1519        # Only proceed if a coupling exists.
1520        if ($couplingID) {
1521            # Determine the ordering to place on the evidence items. If we're
1522            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1523            # we want feature 1 before feature 2 (normal).
1524            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1525            my $ordering = ($inverted ? "DESC" : "");
1526            # Get the coupling evidence.
1527            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1528                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1529                                              [$couplingID],
1530                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1531            # Loop through the evidence items. Each piece of evidence is represented by two
1532            # positions in the evidence list, one for each feature on the other side of the
1533            # evidence link. If at some point we want to generalize to couplings with
1534            # more than two positions, this section of code will need to be re-done.
1535            while (@evidenceList > 0) {
1536                my $peg1Data = shift @evidenceList;
1537                my $peg2Data = shift @evidenceList;
1538                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1539                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1540            }
1541            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1542        }
1543        # Return the result.
1544        return @retVal;
1545    }
1546    
1547    =head3 GetCoupling
1548    
1549    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1550    
1551    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1552    exists, we return the coupling ID along with an indicator of whether the
1553    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1554    In the second case, we say the coupling is I<inverted>. The importance of an
1555    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1556    
1557    =over 4
1558    
1559    =item peg1
1560    
1561    ID of the feature of interest.
1562    
1563    =item peg2
1564    
1565    ID of the potentially coupled feature.
1566    
1567    =item RETURN
1568    
1569    Returns a three-element list. The first element contains the database ID of
1570    the coupling. The second element is FALSE if the coupling is stored in the
1571    database in the caller specified order and TRUE if it is stored in the
1572    inverted order. The third element is the coupling's score. If the coupling
1573    does not exist, all three list elements will be C<undef>.
1574    
1575    =back
1576    
1577    =cut
1578    #: Return Type $%@;
1579    sub GetCoupling {
1580        # Get the parameters.
1581        my ($self, $peg1, $peg2) = @_;
1582        # Declare the return values. We'll start with the coupling ID and undefine the
1583        # flag and score until we have more information.
1584        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1585        # Find the coupling data.
1586        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1587                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1588                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1589        # Check to see if we found anything.
1590        if (!@pegs) {
1591            # No coupling, so undefine the return value.
1592            $retVal = undef;
1593        } else {
1594            # We have a coupling! Get the score and check for inversion.
1595            $score = $pegs[0]->[1];
1596            $inverted = ($pegs[0]->[0] eq $peg1);
1597        }
1598        # Return the result.
1599        return ($retVal, $inverted, $score);
1600    }
1601    
1602    =head3 CouplingID
1603    
1604    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1605    
1606    Return the coupling ID for a pair of feature IDs.
1607    
1608    The coupling ID is currently computed by joining the feature IDs in
1609    sorted order with a space. Client modules (that is, modules which
1610    use Sprout) should not, however, count on this always being the
1611    case. This method provides a way for abstracting the concept of a
1612    coupling ID. All that we know for sure about it is that it can be
1613    generated easily from the feature IDs and the order of the IDs
1614    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1615    will have the same value as C<CouplingID("b1", "a1")>.
1616    
1617    =over 4
1618    
1619    =item peg1
1620    
1621    First feature of interest.
1622    
1623    =item peg2
1624    
1625    Second feature of interest.
1626    
1627    =item RETURN
1628    
1629    Returns the ID that would be used to represent a functional coupling of
1630    the two specified PEGs.
1631    
1632    =back
1633    
1634    =cut
1635    #: Return Type $;
1636    sub CouplingID {
1637        return join " ", sort @_;
1638    }
1639    
1640  =head3 GetEntityTypes  =head3 GetEntityTypes
1641    
1642  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1568  Line 1831 
1831  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
1832  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>.
1833    
1834  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'}); >>
1835    
1836  =over 4  =over 4
1837    
# Line 1966  Line 2229 
2229          return @retVal;          return @retVal;
2230  }  }
2231    
2232    =head3 GetProperties
2233    
2234    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2235    
2236    Return a list of the properties with the specified characteristics.
2237    
2238    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2239    will also be associated with genomes.) A property value is represented by a 4-tuple of
2240    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2241    
2242    =over 4
2243    
2244    =item fid
2245    
2246    ID of the feature possessing the property.
2247    
2248    =item key
2249    
2250    Name or key of the property.
2251    
2252    =item value
2253    
2254    Value of the property.
2255    
2256    =item url
2257    
2258    URL of the document that indicated the property should have this particular value, or an
2259    empty string if no such document exists.
2260    
2261    =back
2262    
2263    The parameters act as a filter for the desired data. Any non-null parameter will
2264    automatically match all the tuples returned. So, specifying just the I<$fid> will
2265    return all the properties of the specified feature; similarly, specifying the I<$key>
2266    and I<$value> parameters will return all the features having the specified property
2267    value.
2268    
2269    A single property key can have many values, representing different ideas about the
2270    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2271    virulent, and another may declare that it is not virulent. A query about the virulence of
2272    C<fig|83333.1.peg.10> would be coded as
2273    
2274        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2275    
2276    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2277    not to be filtered. The tuples returned would be
2278    
2279        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2280        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2281    
2282    =cut
2283    #: Return Type @@;
2284    sub GetProperties {
2285        # Get the parameters.
2286        my ($self, @parms) = @_;
2287        # Declare the return variable.
2288        my @retVal = ();
2289        # Now we need to create a WHERE clause that will get us the data we want. First,
2290        # we create a list of the columns containing the data for each parameter.
2291        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2292                        'Property(property-value)', 'HasProperty(evidence)');
2293        # Now we build the WHERE clause and the list of parameter values.
2294        my @where = ();
2295        my @values = ();
2296        for (my $i = 0; $i <= $#colNames; $i++) {
2297            my $parm = $parms[$i];
2298            if (defined $parm && ($parm ne '')) {
2299                push @where, "$colNames[$i] = ?";
2300                push @values, $parm;
2301            }
2302        }
2303        # Format the WHERE clause.
2304        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2305        # Ask for all the propertie values with the desired characteristics.
2306        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2307        while (my $valueObject = $query->Fetch()) {
2308            my @tuple = $valueObject->Values(\@colNames);
2309            push @retVal, \@tuple;
2310        }
2311        # Return the result.
2312        return @retVal;
2313    }
2314    
2315  =head3 FeatureProperties  =head3 FeatureProperties
2316    
2317  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2506 
2506  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2507    
2508  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
2509  to the role the feature performs.  to the roles the feature performs.
2510    
2511  =over 4  =over 4
2512    
# Line 2170  Line 2516 
2516    
2517  =item RETURN  =item RETURN
2518    
2519  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.
2520    
2521  =back  =back
2522    
2523  =cut  =cut
2524  #: Return Type %;  #: Return Type %@;
2525  sub SubsystemsOf {  sub SubsystemsOf {
2526          # Get the parameters.          # Get the parameters.
2527          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2528          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2529          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2530                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2531                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2187  Line 2533 
2533          my %retVal = ();          my %retVal = ();
2534          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2535          for my $record (@subsystems) {          for my $record (@subsystems) {
2536                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2537            if (exists $retVal{$subsys}) {
2538                push @{$retVal{$subsys}}, $role;
2539            } else {
2540                $retVal{$subsys} = [$role];
2541            }
2542          }          }
2543          # Return the hash.          # Return the hash.
2544          return %retVal;          return %retVal;
2545  }  }
2546    
2547    =head3 SubsystemList
2548    
2549    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2550    
2551    Return a list containing the names of the subsystems in which the specified
2552    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2553    subsystem names, not the roles.
2554    
2555    =over 4
2556    
2557    =item featureID
2558    
2559    ID of the feature whose subsystem names are desired.
2560    
2561    =item RETURN
2562    
2563    Returns a list of the names of the subsystems in which the feature participates.
2564    
2565    =back
2566    
2567    =cut
2568    #: Return Type @;
2569    sub SubsystemList {
2570        # Get the parameters.
2571        my ($self, $featureID) = @_;
2572        # Get the list of names.
2573        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2574                                    [$featureID], 'HasSSCell(from-link)');
2575        # Return the result.
2576        return @retVal;
2577    }
2578    
2579  =head3 RelatedFeatures  =head3 RelatedFeatures
2580    
2581  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2353  Line 2736 
2736  sub GetAll {  sub GetAll {
2737          # Get the parameters.          # Get the parameters.
2738          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2739          # Create the query.      # Call the ERDB method.
2740          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2741          # 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;  
                 $fetched++;  
         }  
2742          # Return the resulting list.          # Return the resulting list.
2743          return @retVal;          return @retVal;
2744  }  }
# Line 2624  Line 2994 
2994      return %retVal;      return %retVal;
2995  }  }
2996    
2997    =head3 MyGenomes
2998    
2999    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3000    
3001    Return a list of the genomes to be included in the Sprout.
3002    
3003    This method is provided for use during the Sprout load. It presumes the Genome load file has
3004    already been created. (It will be in the Sprout data directory and called either C<Genome>
3005    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3006    IDs.
3007    
3008    =over 4
3009    
3010    =item dataDir
3011    
3012    Directory containing the Sprout load files.
3013    
3014    =back
3015    
3016    =cut
3017    #: Return Type @;
3018    sub MyGenomes {
3019        # Get the parameters.
3020        my ($dataDir) = @_;
3021        # Compute the genome file name.
3022        my $genomeFileName = LoadFileName($dataDir, "Genome");
3023        # Extract the genome IDs from the files.
3024        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3025        # Return the result.
3026        return @retVal;
3027    }
3028    
3029    =head3 LoadFileName
3030    
3031    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3032    
3033    Return the name of the load file for the specified table in the specified data
3034    directory.
3035    
3036    =over 4
3037    
3038    =item dataDir
3039    
3040    Directory containing the Sprout load files.
3041    
3042    =item tableName
3043    
3044    Name of the table whose load file is desired.
3045    
3046    =item RETURN
3047    
3048    Returns the name of the file containing the load data for the specified table, or
3049    C<undef> if no load file is present.
3050    
3051    =back
3052    
3053    =cut
3054    #: Return Type $;
3055    sub LoadFileName {
3056        # Get the parameters.
3057        my ($dataDir, $tableName) = @_;
3058        # Declare the return variable.
3059        my $retVal;
3060        # Check for the various file names.
3061        if (-e "$dataDir/$tableName") {
3062            $retVal = "$dataDir/$tableName";
3063        } elsif (-e "$dataDir/$tableName.dtx") {
3064            $retVal = "$dataDir/$tableName.dtx";
3065        }
3066        # Return the result.
3067        return $retVal;
3068    }
3069    
3070  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3071    
3072  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2699  Line 3142 
3142      return $retVal;      return $retVal;
3143  }  }
3144    
3145    =head3 AddProperty
3146    
3147    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3148    
3149    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3150    be added to almost any object. In Sprout, they can only be added to features. In
3151    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3152    pair. If the particular key/value pair coming in is not already in the database, a new
3153    B<Property> record is created to hold it.
3154    
3155    =over 4
3156    
3157    =item peg
3158    
3159    ID of the feature to which the attribute is to be replied.
3160    
3161    =item key
3162    
3163    Name of the attribute (key).
3164    
3165    =item value
3166    
3167    Value of the attribute.
3168    
3169    =item url
3170    
3171    URL or text citation from which the property was obtained.
3172    
3173    =back
3174    
3175    =cut
3176    #: Return Type ;
3177    sub AddProperty {
3178        # Get the parameters.
3179        my ($self, $featureID, $key, $value, $url) = @_;
3180        # Declare the variable to hold the desired property ID.
3181        my $propID;
3182        # Attempt to find a property record for this key/value pair.
3183        my @properties = $self->GetFlat(['Property'],
3184                                       "Property(property-name) = ? AND Property(property-value) = ?",
3185                                       [$key, $value], 'Property(id)');
3186        if (@properties) {
3187            # Here the property is already in the database. We save its ID.
3188            $propID = $properties[0];
3189            # Here the property value does not exist. We need to generate an ID. It will be set
3190            # to a number one greater than the maximum value in the database. This call to
3191            # GetAll will stop after one record.
3192            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3193                                            1);
3194            $propID = $maxProperty[0]->[0] + 1;
3195            # Insert the new property value.
3196            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3197        }
3198        # Now we connect the incoming feature to the property.
3199        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3200    }
3201    
3202    
3203    
3204  1;  1;

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.22

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3