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

Diff of /Sprout/Sprout.pm

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

revision 1.17, Mon Jun 27 20:00:55 2005 UTC revision 1.30, Wed Sep 14 13:13:25 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$len";
627      }      }
628      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
629      return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
630  }  }
631    
632  =head3 ParseLocation  =head3 ParseLocation
# Line 752  Line 765 
765          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
766          # before putting it in the return value.          # before putting it in the return value.
767          my ($start, $stop);          my ($start, $stop);
768            Tracer("Parsed location is $beg$dir$len.") if T(SDNA => 4);
769          if ($dir eq "+") {          if ($dir eq "+") {
770              $start = $beg;              $start = $beg;
771              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
772          } else {          } else {
773              $start = $beg + $len + 1;              $start = $beg - $len + 1;
774              $stop = $beg;              $stop = $beg;
775          }          }
776            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
777          my $query = $self->Get(['IsMadeUpOf','Sequence'],          my $query = $self->Get(['IsMadeUpOf','Sequence'],
778              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
779              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 785 
785                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
786                                     'IsMadeUpOf(len)']);                                     'IsMadeUpOf(len)']);
787              my $stopPosition = $startPosition + $sequenceLength;              my $stopPosition = $startPosition + $sequenceLength;
788                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
789              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
790              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
791              my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;
792                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
793              # Add the relevant data to the location data.              # Add the relevant data to the location data.
794              $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
795          }          }
796          # Add this location's data to the return string. Note that we may need to reverse it.          # Add this location's data to the return string. Note that we may need to reverse it.
797          if ($dir eq '+') {          if ($dir eq '+') {
798              $retVal .= $locationDNA;              $retVal .= $locationDNA;
799          } else {          } else {
800              $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
             $retVal .= $locationDNA;  
801          }          }
802      }      }
803      # Return the result.      # Return the result.
# Line 1506  Line 1522 
1522      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1523      # Declare the return variable.      # Declare the return variable.
1524      my @retVal = ();      my @retVal = ();
1525      # Our first task is to find out the nature of the coupling.      # Our first task is to find out the nature of the coupling: whether or not
1526        # it exists, its score, and whether the features are stored in the same
1527        # order as the ones coming in.
1528      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1529      # Only proceed if a coupling exists.      # Only proceed if a coupling exists.
1530      if ($couplingID) {      if ($couplingID) {
1531          # Determine the ordering to place on the evidence items. If we're          # Determine the ordering to place on the evidence items. If we're
1532          # inverted, we want to see feature 2 before feature 1; otherwise,          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1533          # we want the reverse.          # we want feature 1 before feature 2 (normal).
1534            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1535          my $ordering = ($inverted ? "DESC" : "");          my $ordering = ($inverted ? "DESC" : "");
1536          # Get the coupling evidence.          # Get the coupling evidence.
1537          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
# Line 1526  Line 1545 
1545          while (@evidenceList > 0) {          while (@evidenceList > 0) {
1546              my $peg1Data = shift @evidenceList;              my $peg1Data = shift @evidenceList;
1547              my $peg2Data = shift @evidenceList;              my $peg2Data = shift @evidenceList;
1548                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1549              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1550          }          }
1551            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1552      }      }
     # TODO: code  
1553      # Return the result.      # Return the result.
1554      return @retVal;      return @retVal;
1555  }  }
# Line 1578  Line 1598 
1598                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1599      # Check to see if we found anything.      # Check to see if we found anything.
1600      if (!@pegs) {      if (!@pegs) {
1601            Trace("No coupling found.") if T(Coupling => 4);
1602          # No coupling, so undefine the return value.          # No coupling, so undefine the return value.
1603          $retVal = undef;          $retVal = undef;
1604      } else {      } else {
1605          # We have a coupling! Get the score and check for inversion.          # We have a coupling! Get the score and check for inversion.
1606          $score = $pegs[0]->[1];          $score = $pegs[0]->[1];
1607          $inverted = ($pegs[0]->[0] eq $peg1);          my $firstFound = $pegs[0]->[0];
1608            $inverted = ($firstFound ne $peg1);
1609            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1610      }      }
1611      # Return the result.      # Return the result.
1612      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
# Line 1688  Line 1711 
1711          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1712              # Here we have a new header. Store the current sequence if we have one.              # Here we have a new header. Store the current sequence if we have one.
1713              if ($id) {              if ($id) {
1714                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1715              }              }
1716              # Clear the sequence accumulator and save the new ID.              # Clear the sequence accumulator and save the new ID.
1717              ($id, $sequence) = ("$prefix$1", "");              ($id, $sequence) = ("$prefix$1", "");
1718          } else {          } else {
1719              # 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.
1720              # 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
1721              # case.              # case.
1722              $line =~ /^\s*(.*?)(\s|\n)/;              $line =~ /^\s*(.*?)(\s|\n)/;
1723              $sequence .= $1;              $sequence .= $1;
# Line 1702  Line 1725 
1725      }      }
1726      # Flush out the last sequence (if any).      # Flush out the last sequence (if any).
1727      if ($sequence) {      if ($sequence) {
1728          $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1729      }      }
1730      # Close the file.      # Close the file.
1731      close FASTAFILE;      close FASTAFILE;
# Line 2028  Line 2051 
2051      # Get the parameters.      # Get the parameters.
2052      my ($self, $entityName, $entityID) = @_;      my ($self, $entityName, $entityID) = @_;
2053      # Check for the entity instance.      # Check for the entity instance.
2054        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2055      my $testInstance = $self->GetEntity($entityName, $entityID);      my $testInstance = $self->GetEntity($entityName, $entityID);
2056      # Return an existence indicator.      # Return an existence indicator.
2057      my $retVal = ($testInstance ? 1 : 0);      my $retVal = ($testInstance ? 1 : 0);
# Line 2219  Line 2243 
2243      return @retVal;      return @retVal;
2244  }  }
2245    
2246    =head3 GetProperties
2247    
2248    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2249    
2250    Return a list of the properties with the specified characteristics.
2251    
2252    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2253    will also be associated with genomes.) A property value is represented by a 4-tuple of
2254    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2255    
2256    =over 4
2257    
2258    =item fid
2259    
2260    ID of the feature possessing the property.
2261    
2262    =item key
2263    
2264    Name or key of the property.
2265    
2266    =item value
2267    
2268    Value of the property.
2269    
2270    =item url
2271    
2272    URL of the document that indicated the property should have this particular value, or an
2273    empty string if no such document exists.
2274    
2275    =back
2276    
2277    The parameters act as a filter for the desired data. Any non-null parameter will
2278    automatically match all the tuples returned. So, specifying just the I<$fid> will
2279    return all the properties of the specified feature; similarly, specifying the I<$key>
2280    and I<$value> parameters will return all the features having the specified property
2281    value.
2282    
2283    A single property key can have many values, representing different ideas about the
2284    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2285    virulent, and another may declare that it is not virulent. A query about the virulence of
2286    C<fig|83333.1.peg.10> would be coded as
2287    
2288        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2289    
2290    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2291    not to be filtered. The tuples returned would be
2292    
2293        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2294        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2295    
2296    =cut
2297    #: Return Type @@;
2298    sub GetProperties {
2299        # Get the parameters.
2300        my ($self, @parms) = @_;
2301        # Declare the return variable.
2302        my @retVal = ();
2303        # Now we need to create a WHERE clause that will get us the data we want. First,
2304        # we create a list of the columns containing the data for each parameter.
2305        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2306                        'Property(property-value)', 'HasProperty(evidence)');
2307        # Now we build the WHERE clause and the list of parameter values.
2308        my @where = ();
2309        my @values = ();
2310        for (my $i = 0; $i <= $#colNames; $i++) {
2311            my $parm = $parms[$i];
2312            if (defined $parm && ($parm ne '')) {
2313                push @where, "$colNames[$i] = ?";
2314                push @values, $parm;
2315            }
2316        }
2317        # Format the WHERE clause.
2318        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2319        # Ask for all the propertie values with the desired characteristics.
2320        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2321        while (my $valueObject = $query->Fetch()) {
2322            my @tuple = $valueObject->Values(\@colNames);
2323            push @retVal, \@tuple;
2324        }
2325        # Return the result.
2326        return @retVal;
2327    }
2328    
2329  =head3 FeatureProperties  =head3 FeatureProperties
2330    
2331  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2413  Line 2520 
2520  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2521    
2522  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
2523  to the role the feature performs.  to the roles the feature performs.
2524    
2525  =over 4  =over 4
2526    
# Line 2423  Line 2530 
2530    
2531  =item RETURN  =item RETURN
2532    
2533  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.
2534    
2535  =back  =back
2536    
2537  =cut  =cut
2538  #: Return Type %;  #: Return Type %@;
2539  sub SubsystemsOf {  sub SubsystemsOf {
2540      # Get the parameters.      # Get the parameters.
2541      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
# Line 2440  Line 2547 
2547      my %retVal = ();      my %retVal = ();
2548      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
2549      for my $record (@subsystems) {      for my $record (@subsystems) {
2550          $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2551            if (exists $retVal{$subsys}) {
2552                push @{$retVal{$subsys}}, $role;
2553            } else {
2554                $retVal{$subsys} = [$role];
2555            }
2556      }      }
2557      # Return the hash.      # Return the hash.
2558      return %retVal;      return %retVal;
# Line 2896  Line 3008 
3008      return %retVal;      return %retVal;
3009  }  }
3010    
3011    =head3 MyGenomes
3012    
3013    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3014    
3015    Return a list of the genomes to be included in the Sprout.
3016    
3017    This method is provided for use during the Sprout load. It presumes the Genome load file has
3018    already been created. (It will be in the Sprout data directory and called either C<Genome>
3019    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3020    IDs.
3021    
3022    =over 4
3023    
3024    =item dataDir
3025    
3026    Directory containing the Sprout load files.
3027    
3028    =back
3029    
3030    =cut
3031    #: Return Type @;
3032    sub MyGenomes {
3033        # Get the parameters.
3034        my ($dataDir) = @_;
3035        # Compute the genome file name.
3036        my $genomeFileName = LoadFileName($dataDir, "Genome");
3037        # Extract the genome IDs from the files.
3038        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3039        # Return the result.
3040        return @retVal;
3041    }
3042    
3043    =head3 LoadFileName
3044    
3045    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3046    
3047    Return the name of the load file for the specified table in the specified data
3048    directory.
3049    
3050    =over 4
3051    
3052    =item dataDir
3053    
3054    Directory containing the Sprout load files.
3055    
3056    =item tableName
3057    
3058    Name of the table whose load file is desired.
3059    
3060    =item RETURN
3061    
3062    Returns the name of the file containing the load data for the specified table, or
3063    C<undef> if no load file is present.
3064    
3065    =back
3066    
3067    =cut
3068    #: Return Type $;
3069    sub LoadFileName {
3070        # Get the parameters.
3071        my ($dataDir, $tableName) = @_;
3072        # Declare the return variable.
3073        my $retVal;
3074        # Check for the various file names.
3075        if (-e "$dataDir/$tableName") {
3076            $retVal = "$dataDir/$tableName";
3077        } elsif (-e "$dataDir/$tableName.dtx") {
3078            $retVal = "$dataDir/$tableName.dtx";
3079        }
3080        # Return the result.
3081        return $retVal;
3082    }
3083    
3084  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3085    
3086  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3028  Line 3213 
3213      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3214  }  }
3215    
3216    
3217    
3218  1;  1;

Legend:
Removed from v.1.17  
changed lines
  Added in v.1.30

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3