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

Diff of /Sprout/Sprout.pm

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

revision 1.16, Fri Jun 24 21:45:45 2005 UTC revision 1.28, Wed Sep 14 13:01:40 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 756  Line 769 
769              $start = $beg;              $start = $beg;
770              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
771          } else {          } else {
772              $start = $beg + $len + 1;              $start = $beg - $len + 1;
773              $stop = $beg;              $stop = $beg;
774          }          }
775          my $query = $self->Get(['IsMadeUpOf','Sequence'],          my $query = $self->Get(['IsMadeUpOf','Sequence'],
# Line 780  Line 793 
793          if ($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 .= $locationDNA;  
797          }          }
798      }      }
799      # Return the result.      # Return the result.
# Line 1506  Line 1518 
1518      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
1519      # Declare the return variable.      # Declare the return variable.
1520      my @retVal = ();      my @retVal = ();
1521      # Our first task is to find out the nature of the coupling.      # Our first task is to find out the nature of the coupling: whether or not
1522        # it exists, its score, and whether the features are stored in the same
1523        # order as the ones coming in.
1524      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1525      # Only proceed if a coupling exists.      # Only proceed if a coupling exists.
1526      if ($couplingID) {      if ($couplingID) {
1527          # Determine the ordering to place on the evidence items. If we're          # Determine the ordering to place on the evidence items. If we're
1528          # inverted, we want to see feature 2 before feature 1; otherwise,          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1529          # we want the reverse.          # we want feature 1 before feature 2 (normal).
1530            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1531          my $ordering = ($inverted ? "DESC" : "");          my $ordering = ($inverted ? "DESC" : "");
1532          # Get the coupling evidence.          # Get the coupling evidence.
1533          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1534                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",                                            "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1535                                            [$couplingID],                                            [$couplingID],
1536                                            ['PCH(used)', 'UsesAsEvidence(pos)']);                                            ['PCH(used)', 'UsesAsEvidence(to-link)']);
1537          # 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
1538          # 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
1539          # 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 1541 
1541          while (@evidenceList > 0) {          while (@evidenceList > 0) {
1542              my $peg1Data = shift @evidenceList;              my $peg1Data = shift @evidenceList;
1543              my $peg2Data = shift @evidenceList;              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], $peg1Data->[0]];              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1546          }          }
1547            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1548      }      }
     # TODO: code  
1549      # Return the result.      # Return the result.
1550      return @retVal;      return @retVal;
1551  }  }
# Line 1575  Line 1591 
1591      # Find the coupling data.      # Find the coupling data.
1592      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],      my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1593                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",                                   "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1594                                   [$retVal], "ParticipatesInCoupling(from-link), Coupling(score)");                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1595      # Check to see if we found anything.      # Check to see if we found anything.
1596      if (!@pegs) {      if (!@pegs) {
1597            Trace("No coupling found.") if T(Coupling => 4);
1598          # No coupling, so undefine the return value.          # No coupling, so undefine the return value.
1599          $retVal = undef;          $retVal = undef;
1600      } else {      } else {
1601          # We have a coupling! Get the score and check for inversion.          # We have a coupling! Get the score and check for inversion.
1602          $score = $pegs[0]->[1];          $score = $pegs[0]->[1];
1603          $inverted = ($pegs[0]->[0] eq $peg1);          my $firstFound = $pegs[0]->[0];
1604            $inverted = ($firstFound ne $peg1);
1605            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1606      }      }
1607      # Return the result.      # Return the result.
1608      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
# Line 1688  Line 1707 
1707          if ($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} = uc $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. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
1717              # case.              # case.
1718              $line =~ /^\s*(.*?)(\s|\n)/;              $line =~ /^\s*(.*?)(\s|\n)/;
1719              $sequence .= $1;              $sequence .= $1;
# Line 1702  Line 1721 
1721      }      }
1722      # Flush out the last sequence (if any).      # Flush out the last sequence (if any).
1723      if ($sequence) {      if ($sequence) {
1724          $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1725      }      }
1726      # Close the file.      # Close the file.
1727      close FASTAFILE;      close FASTAFILE;
# Line 2028  Line 2047 
2047      # Get the parameters.      # Get the parameters.
2048      my ($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 2219  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 2413  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 2423  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) = @_;
# Line 2440  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} = [$role];
2551            }
2552      }      }
2553      # Return the hash.      # Return the hash.
2554      return %retVal;      return %retVal;
# Line 2896  Line 3004 
3004      return %retVal;      return %retVal;
3005  }  }
3006    
3007    =head3 MyGenomes
3008    
3009    C<< my @genomes = Sprout::MyGenomes($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
# Line 3028  Line 3209 
3209      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });      $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3210  }  }
3211    
3212    
3213    
3214  1;  1;

Legend:
Removed from v.1.16  
changed lines
  Added in v.1.28

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3