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

Diff of /Sprout/Sprout.pm

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

revision 1.15, Wed Jun 22 21:30:45 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 420  Line 432 
432      # Loop through the incoming table names.      # Loop through the incoming table names.
433      for my $tableName (@{$tableList}) {      for my $tableName (@{$tableList}) {
434          # Find the table's file.          # Find the table's file.
435          my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436          if (! -e $fileName) {          if (! $fileName) {
437              $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438          }          } else {
439          # Attempt to load this table.          # Attempt to load this table.
440          my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);          my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441          # Accumulate the resulting statistics.          # Accumulate the resulting statistics.
442          $retVal->Accumulate($result);          $retVal->Accumulate($result);
443      }      }
444        }
445      # Return the statistics.      # Return the statistics.
446      return $retVal;      return $retVal;
447  }  }
# Line 570  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 613  Line 626 
626          push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$beg$dir$len";
627      }      }
628      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
629      return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 1506  Line 1519 
1519      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1520      # Declare the return variable.      # Declare the return variable.
1521      my @retVal = ();      my @retVal = ();
1522      # Our first task is to find out the nature of the coupling.      # Our first task is to find out the nature of the coupling: whether or not
1523        # it exists, its score, and whether the features are stored in the same
1524        # order as the ones coming in.
1525      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1526      # Only proceed if a coupling exists.      # Only proceed if a coupling exists.
1527      if ($couplingID) {      if ($couplingID) {
1528          # Determine the ordering to place on the evidence items. If we're          # Determine the ordering to place on the evidence items. If we're
1529          # inverted, we want to see feature 2 before feature 1; otherwise,          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1530          # we want the reverse.          # we want feature 1 before feature 2 (normal).
1531            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1532          my $ordering = ($inverted ? "DESC" : "");          my $ordering = ($inverted ? "DESC" : "");
1533          # Get the coupling evidence.          # Get the coupling evidence.
1534          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1535                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1536                                            [$couplingID],                                            [$couplingID],
1537                                            ['PCH(used)', 'UsesAsEvidence(pos)']);                                            ['PCH(used)', 'UsesAsEvidence(to-link)']);
1538          # Loop through the evidence items. Each piece of evidence is represented by two          # 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          # 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          # evidence link. If at some point we want to generalize to couplings with
# Line 1526  Line 1542 
1542          while (@evidenceList > 0) {          while (@evidenceList > 0) {
1543              my $peg1Data = shift @evidenceList;              my $peg1Data = shift @evidenceList;
1544              my $peg2Data = shift @evidenceList;              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], $peg1Data->[0]];              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1547          }          }
1548            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1549      }      }
     # TODO: code  
1550      # Return the result.      # Return the result.
1551      return @retVal;      return @retVal;
1552  }  }
# Line 1575  Line 1592 
1592      # Find the coupling data.      # Find the coupling data.
1593      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1594                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1595                                   [$retVal], "ParticipatesInCoupling(from-link), Coupling(score)");                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1596      # Check to see if we found anything.      # Check to see if we found anything.
1597      if (!@pegs) {      if (!@pegs) {
1598            Trace("No coupling found.") if T(Coupling => 4);
1599          # No coupling, so undefine the return value.          # No coupling, so undefine the return value.
1600          $retVal = undef;          $retVal = undef;
1601      } else {      } else {
1602          # We have a coupling! Get the score and check for inversion.          # We have a coupling! Get the score and check for inversion.
1603          $score = $pegs[0]->[1];          $score = $pegs[0]->[1];
1604          $inverted = ($pegs[0]->[0] eq $peg1);          my $firstFound = $pegs[0]->[0];
1605            $inverted = ($firstFound ne $peg1);
1606            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1607      }      }
1608      # Return the result.      # Return the result.
1609      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
# Line 1688  Line 1708 
1708          if ($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} = uc $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. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
1718              # case.              # case.
1719              $line =~ /^\s*(.*?)(\s|\n)/;              $line =~ /^\s*(.*?)(\s|\n)/;
1720              $sequence .= $1;              $sequence .= $1;
# Line 1702  Line 1722 
1722      }      }
1723      # Flush out the last sequence (if any).      # Flush out the last sequence (if any).
1724      if ($sequence) {      if ($sequence) {
1725          $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1726      }      }
1727      # Close the file.      # Close the file.
1728      close FASTAFILE;      close FASTAFILE;
# Line 2028  Line 2048 
2048      # Get the parameters.      # Get the parameters.
2049      my ($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 2219  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 2413  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 2423  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 2440  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, $userID); >>
# Line 2864  Line 3005 
3005      return %retVal;      return %retVal;
3006  }  }
3007    
3008    =head3 MyGenomes
3009    
3010    C<< my @genomes = Sprout::MyGenomes($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
# Line 2996  Line 3210 
3210      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3211  }  }
3212    
3213    
3214    
3215  1;  1;

Legend:
Removed from v.1.15  
changed lines
  Added in v.1.26

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3