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

Diff of /Sprout/Sprout.pm

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

revision 1.20, Wed Aug 24 19:31:20 2005 UTC revision 1.40, Wed Oct 12 03:12:24 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 98  Line 100 
100                                                          # database connection port                                                          # 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 105  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, $xmlFileName);
# Line 615  Line 622 
622          }          }
623          # Remember this specifier for the adjacent-segment test the next time through.          # Remember this specifier for the adjacent-segment test the next time through.
624          ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);          ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
625            # Compute the initial base pair.
626            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
627          # Add the specifier to the list.          # Add the specifier to the list.
628          push @retVal, "${contigID}_$beg$dir$len";          push @retVal, "${contigID}_$start$dir$len";
629      }      }
630      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
631      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 650  Line 659 
659      shift if UNIVERSAL::isa($_[0],__PACKAGE__);      shift if UNIVERSAL::isa($_[0],__PACKAGE__);
660      my ($location) = @_;      my ($location) = @_;
661      # Parse it into segments.      # Parse it into segments.
662      $location =~ /^(.*)_(\d*)([+-_])(\d*)$/;      $location =~ /^(.+)_(\d+)([+\-_])(\d+)$/;
663      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);      my ($contigID, $start, $dir, $len) = ($1, $2, $3, $4);
664      # If the direction is an underscore, convert it to a + or -.      # If the direction is an underscore, convert it to a + or -.
665      if ($dir eq "_") {      if ($dir eq "_") {
# Line 758  Line 767 
767          # the start point is the ending. Note that in the latter case we must reverse the DNA string          # the start point is the ending. Note that in the latter case we must reverse the DNA string
768          # before putting it in the return value.          # before putting it in the return value.
769          my ($start, $stop);          my ($start, $stop);
770            Trace("Parse of \"$location\" is $beg$dir$len.") if T(SDNA => 4);
771          if ($dir eq "+") {          if ($dir eq "+") {
772              $start = $beg;              $start = $beg;
773              $stop = $beg + $len - 1;              $stop = $beg + $len - 1;
774          } else {          } else {
775              $start = $beg + $len + 1;              $start = $beg - $len + 1;
776              $stop = $beg;              $stop = $beg;
777          }          }
778            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
779          my $query = $self->Get(['IsMadeUpOf','Sequence'],          my $query = $self->Get(['IsMadeUpOf','Sequence'],
780              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .              "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
781              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",              " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 776  Line 787 
787                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
788                                     'IsMadeUpOf(len)']);                                     'IsMadeUpOf(len)']);
789              my $stopPosition = $startPosition + $sequenceLength;              my $stopPosition = $startPosition + $sequenceLength;
790                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
791              # Figure out the start point and length of the relevant section.              # Figure out the start point and length of the relevant section.
792              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);              my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
793              my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition < $stop ? $stopPosition : $stop) + 1 - $startPosition - $pos1;
794                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
795              # Add the relevant data to the location data.              # Add the relevant data to the location data.
796              $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
797          }          }
798          # Add this location's data to the return string. Note that we may need to reverse it.          # Add this location's data to the return string. Note that we may need to reverse it.
799          if ($dir eq '+') {          if ($dir eq '+') {
800              $retVal .= $locationDNA;              $retVal .= $locationDNA;
801          } else {          } else {
802              $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
             $retVal .= $locationDNA;  
803          }          }
804      }      }
805      # Return the result.      # Return the result.
# Line 857  Line 869 
869      # Set it from the sequence data, if any.      # Set it from the sequence data, if any.
870      if ($sequence) {      if ($sequence) {
871          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);          my ($start, $len) = $sequence->Values(['IsMadeUpOf(start-position)', 'IsMadeUpOf(len)']);
872          $retVal = $start + $len;          $retVal = $start + $len - 1;
873        }
874        # Return the result.
875        return $retVal;
876    }
877    
878    =head3 ClusterPEGs
879    
880    C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>
881    
882    Cluster the PEGs in a list according to the cluster coding scheme of the specified
883    subsystem. In order for this to work properly, the subsystem object must have
884    been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.
885    This causes the cluster numbers to be pulled into the subsystem's color hash.
886    If a PEG is not found in the color hash, it will not appear in the output
887    sequence.
888    
889    =over 4
890    
891    =item sub
892    
893    Sprout subsystem object for the relevant subsystem, from the L</get_subsystem>
894    method.
895    
896    =item pegs
897    
898    Reference to the list of PEGs to be clustered.
899    
900    =item RETURN
901    
902    Returns a list of the PEGs, grouped into smaller lists by cluster number.
903    
904    =back
905    
906    =cut
907    #: Return Type $@@;
908    sub ClusterPEGs {
909        # Get the parameters.
910        my ($self, $sub, $pegs) = @_;
911        # Declare the return variable.
912        my $retVal = [];
913        # Loop through the PEGs, creating arrays for each cluster.
914        for my $pegID (@{$pegs}) {
915            my $clusterNumber = $sub->get_cluster_number($pegID);
916            # Only proceed if the PEG is in a cluster.
917            if ($clusterNumber >= 0) {
918                # Push this PEG onto the sub-list for the specified cluster number.
919                push @{$retVal->[$clusterNumber]}, $pegID;
920            }
921      }      }
922      # Return the result.      # Return the result.
923      return $retVal;      return $retVal;
# Line 1007  Line 1067 
1067    
1068  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1069    
1070  C<< my @descriptors = $sprout->FeatureAnnotations($featureID); >>  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>
1071    
1072  Return the annotations of a feature.  Return the annotations of a feature.
1073    
# Line 1017  Line 1077 
1077    
1078  ID of the feature whose annotations are desired.  ID of the feature whose annotations are desired.
1079    
1080    =item rawFlag
1081    
1082    If TRUE, the annotation timestamps will be returned in raw form; otherwise, they
1083    will be returned in human-readable form.
1084    
1085  =item RETURN  =item RETURN
1086    
1087  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.  Returns a list of annotation descriptors. Each descriptor is a hash with the following fields.
1088    
1089  * B<featureID> ID of the relevant feature.  * B<featureID> ID of the relevant feature.
1090    
1091  * B<timeStamp> time the annotation was made, in user-friendly format.  * B<timeStamp> time the annotation was made.
1092    
1093  * B<user> ID of the user who made the annotation  * B<user> ID of the user who made the annotation
1094    
# Line 1035  Line 1100 
1100  #: Return Type @%;  #: Return Type @%;
1101  sub FeatureAnnotations {  sub FeatureAnnotations {
1102      # Get the parameters.      # Get the parameters.
1103      my ($self, $featureID) = @_;      my ($self, $featureID, $rawFlag) = @_;
1104      # Create a query to get the feature's annotations and the associated users.      # Create a query to get the feature's annotations and the associated users.
1105      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],      my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1106                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);                             "IsTargetOfAnnotation(from-link) = ?", [$featureID]);
# Line 1048  Line 1113 
1113              $annotation->Values(['IsTargetOfAnnotation(from-link)',              $annotation->Values(['IsTargetOfAnnotation(from-link)',
1114                                   'Annotation(time)', 'MadeAnnotation(from-link)',                                   'Annotation(time)', 'MadeAnnotation(from-link)',
1115                                   'Annotation(annotation)']);                                   'Annotation(annotation)']);
1116            # Convert the time, if necessary.
1117            if (! $rawFlag) {
1118                $timeStamp = FriendlyTimestamp($timeStamp);
1119            }
1120          # Assemble them into a hash.          # Assemble them into a hash.
1121          my $annotationHash = { featureID => $featureID,          my $annotationHash = { featureID => $featureID,
1122                                 timeStamp => FriendlyTimestamp($timeStamp),                                 timeStamp => $timeStamp,
1123                                 user => $user, text => $text };                                 user => $user, text => $text };
1124          # Add it to the return list.          # Add it to the return list.
1125          push @retVal, $annotationHash;          push @retVal, $annotationHash;
# Line 1254  Line 1323 
1323          my $query = $self->Get(['IsBidirectionalBestHitOf'],          my $query = $self->Get(['IsBidirectionalBestHitOf'],
1324                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",                                 "IsBidirectionalBestHitOf(from-link) = ? AND IsBidirectionalBestHitOf(genome) = ?",
1325                                 [$featureID, $genomeID]);                                 [$featureID, $genomeID]);
1326          # Look for the best hit.          # Peel off the BBHs found.
1327          my $bbh = $query->Fetch;          my @found = ();
1328          if ($bbh) {          while (my $bbh = $query->Fetch) {
1329              my ($targetFeature) = $bbh->Value('IsBidirectionalBestHitOf(to-link)');              push @found, $bbh->Value('IsBidirectionalBestHitOf(to-link)');
             $retVal{$featureID} = $targetFeature;  
1330          }          }
1331            $retVal{$featureID} = \@found;
1332      }      }
1333      # Return the mapping.      # Return the mapping.
1334      return \%retVal;      return \%retVal;
# Line 1521  Line 1590 
1590          # Determine the ordering to place on the evidence items. If we're          # Determine the ordering to place on the evidence items. If we're
1591          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,          # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1592          # we want feature 1 before feature 2 (normal).          # we want feature 1 before feature 2 (normal).
1593            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1594          my $ordering = ($inverted ? "DESC" : "");          my $ordering = ($inverted ? "DESC" : "");
1595          # Get the coupling evidence.          # Get the coupling evidence.
1596          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],          my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
# Line 1534  Line 1604 
1604          while (@evidenceList > 0) {          while (@evidenceList > 0) {
1605              my $peg1Data = shift @evidenceList;              my $peg1Data = shift @evidenceList;
1606              my $peg2Data = shift @evidenceList;              my $peg2Data = shift @evidenceList;
1607                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1608              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];              push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1609          }          }
1610            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1611      }      }
1612      # Return the result.      # Return the result.
1613      return @retVal;      return @retVal;
# Line 1585  Line 1657 
1657                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);                                   [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1658      # Check to see if we found anything.      # Check to see if we found anything.
1659      if (!@pegs) {      if (!@pegs) {
1660            Trace("No coupling found.") if T(Coupling => 4);
1661          # No coupling, so undefine the return value.          # No coupling, so undefine the return value.
1662          $retVal = undef;          $retVal = undef;
1663      } else {      } else {
1664          # We have a coupling! Get the score and check for inversion.          # We have a coupling! Get the score and check for inversion.
1665          $score = $pegs[0]->[1];          $score = $pegs[0]->[1];
1666          $inverted = ($pegs[0]->[0] eq $peg1);          my $firstFound = $pegs[0]->[0];
1667            $inverted = ($firstFound ne $peg1);
1668            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1669      }      }
1670      # Return the result.      # Return the result.
1671      return ($retVal, $inverted, $score);      return ($retVal, $inverted, $score);
# Line 1695  Line 1770 
1770          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {          if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1771              # Here we have a new header. Store the current sequence if we have one.              # Here we have a new header. Store the current sequence if we have one.
1772              if ($id) {              if ($id) {
1773                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1774              }              }
1775              # Clear the sequence accumulator and save the new ID.              # Clear the sequence accumulator and save the new ID.
1776              ($id, $sequence) = ("$prefix$1", "");              ($id, $sequence) = ("$prefix$1", "");
1777          } else {          } else {
1778              # 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.
1779              # 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
1780              # case.              # case.
1781              $line =~ /^\s*(.*?)(\s|\n)/;              $line =~ /^\s*(.*?)(\s|\n)/;
1782              $sequence .= $1;              $sequence .= $1;
# Line 1709  Line 1784 
1784      }      }
1785      # Flush out the last sequence (if any).      # Flush out the last sequence (if any).
1786      if ($sequence) {      if ($sequence) {
1787          $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1788      }      }
1789      # Close the file.      # Close the file.
1790      close FASTAFILE;      close FASTAFILE;
# Line 2035  Line 2110 
2110      # Get the parameters.      # Get the parameters.
2111      my ($self, $entityName, $entityID) = @_;      my ($self, $entityName, $entityID) = @_;
2112      # Check for the entity instance.      # Check for the entity instance.
2113        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2114      my $testInstance = $self->GetEntity($entityName, $entityID);      my $testInstance = $self->GetEntity($entityName, $entityID);
2115      # Return an existence indicator.      # Return an existence indicator.
2116      my $retVal = ($testInstance ? 1 : 0);      my $retVal = ($testInstance ? 1 : 0);
# Line 3135  Line 3211 
3211    
3212  sub FriendlyTimestamp {  sub FriendlyTimestamp {
3213      my ($timeValue) = @_;      my ($timeValue) = @_;
3214      my $retVal = strftime("%a %b %e %H:%M:%S %Y", localtime($timeValue));      my $retVal = localtime($timeValue);
3215      return $retVal;      return $retVal;
3216  }  }
3217    

Legend:
Removed from v.1.20  
changed lines
  Added in v.1.40

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3