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

Diff of /Sprout/Sprout.pm

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

revision 1.40, Wed Oct 12 03:12:24 2005 UTC revision 1.57, Sat May 13 03:10:15 2006 UTC
# Line 62  Line 62 
62    
63  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)  * B<xmlFileName> name of the XML file containing the database definition (default C<SproutDBD.xml>)
64    
65  * B<userData> user name and password, delimited by a slash (default C<root/>)  * B<userData> user name and password, delimited by a slash (default same as SEED)
66    
67  * B<port> connection port (default C<0>)  * B<port> connection port (default C<0>)
68    
69    * B<sock> connection socket (default same as SEED)
70    
71  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)  * B<maxSegmentLength> maximum number of residues per feature segment, (default C<4500>)
72    
73  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
# Line 92  Line 94 
94                                                          # database type                                                          # database type
95                         dataDir      => $FIG_Config::sproutData,                         dataDir      => $FIG_Config::sproutData,
96                                                          # data file directory                                                          # data file directory
97                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",                         xmlFileName  => "$FIG_Config::fig/SproutDBD.xml",
98                                                          # database definition file name                                                          # database definition file name
99                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
100                                                          # user name and password                                                          # user name and password
101                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
102                                                          # database connection port                                                          # database connection port
103                           sock         => $FIG_Config::dbsock,
104                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
105                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
106                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 111  Line 114 
114      my $dbh;      my $dbh;
115      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
116          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
117                                  $password, $optionTable->{port});                                  $password, $optionTable->{port}, undef, $optionTable->{sock});
118      }      }
119      # Create the ERDB object.      # Create the ERDB object.
120      my $xmlFileName = "$optionTable->{xmlFileName}";      my $xmlFileName = "$optionTable->{xmlFileName}";
# Line 389  Line 392 
392    
393  =head3 LoadUpdate  =head3 LoadUpdate
394    
395  C<< my %stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>
396    
397  Load updates to one or more database tables. This method enables the client to make changes to one  Load updates to one or more database tables. This method enables the client to make changes to one
398  or two tables without reloading the whole database. For each table, there must be a corresponding  or two tables without reloading the whole database. For each table, there must be a corresponding
# Line 610  Line 613 
613          if ($prevContig eq $contigID && $dir eq $prevDir) {          if ($prevContig eq $contigID && $dir eq $prevDir) {
614              # Here the new segment is in the same direction on the same contig. Insure the              # Here the new segment is in the same direction on the same contig. Insure the
615              # new segment's beginning is next to the old segment's end.              # new segment's beginning is next to the old segment's end.
616              if (($dir eq "-" && $beg == $prevBeg - $prevLen) ||              if ($dir eq "-" && $beg + $len == $prevBeg) {
617                  ($dir eq "+" && $beg == $prevBeg + $prevLen)) {                  # Here we're merging two backward blocks, so we keep the new begin point
618                  # Here we need to merge two segments. Adjust the beginning and length values                  # and adjust the length.
619                  # to include both segments.                  $len += $prevLen;
620                    # Pop the old segment off. The new one will replace it later.
621                    pop @retVal;
622                } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {
623                    # Here we need to merge two forward blocks. Adjust the beginning and
624                    # length values to include both segments.
625                  $beg = $prevBeg;                  $beg = $prevBeg;
626                  $len += $prevLen;                  $len += $prevLen;
627                  # Pop the old segment off. The new one will replace it later.                  # Pop the old segment off. The new one will replace it later.
# Line 735  Line 743 
743  should be of the form returned by L</featureLocation> when in a list context. In other words,  should be of the form returned by L</featureLocation> when in a list context. In other words,
744  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.  each location is of the form I<contigID>C<_>I<begin>I<dir>I<end>.
745    
746    For example, the following would return the DNA sequence for contig C<83333.1:NC_000913>
747    between positions 1401 and 1532, inclusive.
748    
749        my $sequence = $sprout->DNASeq('83333.1:NC_000913_1401_1532');
750    
751  =over 4  =over 4
752    
753  =item locationList  =item locationList
754    
755  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<end> (see  List of location specifiers, each in the form I<contigID>C<_>I<begin>I<dir>I<len> or
756  L</FeatureLocation> for more about this format).  I<contigID>C<_>I<begin>C<_>I<end> (see L</FeatureLocation> for more about this format).
757    
758  =item RETURN  =item RETURN
759    
# Line 1148  Line 1161 
1161    
1162  =item RETURN  =item RETURN
1163    
1164  Returns a hash mapping the functional assignment IDs to user IDs.  Returns a hash mapping the user IDs to functional assignment IDs.
1165    
1166  =back  =back
1167    
# Line 1158  Line 1171 
1171      # Get the parameters.      # Get the parameters.
1172      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1173      # Get all of the feature's annotations.      # Get all of the feature's annotations.
1174      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation'],      my @query = $self->GetAll(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1175                              "IsTargetOfAnnotation(from-link) = ?",                              "IsTargetOfAnnotation(from-link) = ?",
1176                              [$featureID], ['Annotation(time)', 'Annotation(annotation)']);                              [$featureID], ['Annotation(time)', 'Annotation(annotation)',
1177                                               'MadeAnnotation(from-link)']);
1178      # Declare the return hash.      # Declare the return hash.
1179      my %retVal;      my %retVal;
     # Declare a hash for insuring we only make one assignment per user.  
     my %timeHash = ();  
1180      # Now we sort the assignments by timestamp in reverse.      # Now we sort the assignments by timestamp in reverse.
1181      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;      my @sortedQuery = sort { -($a->[0] <=> $b->[0]) } @query;
1182      # Loop until we run out of annotations.      # Loop until we run out of annotations.
1183      for my $annotation (@sortedQuery) {      for my $annotation (@sortedQuery) {
1184          # Get the annotation fields.          # Get the annotation fields.
1185          my ($timeStamp, $text) = @{$annotation};          my ($timeStamp, $text, $user) = @{$annotation};
1186          # Check to see if this is a functional assignment.          # Check to see if this is a functional assignment.
1187          my ($user, $function) = _ParseAssignment($text);          my ($actualUser, $function) = _ParseAssignment($user, $text);
1188          if ($user && ! exists $timeHash{$user}) {          if ($actualUser && ! exists $retVal{$actualUser}) {
1189              # Here it is a functional assignment and there has been no              # Here it is a functional assignment and there has been no
1190              # previous assignment for this user, so we stuff it in the              # previous assignment for this user, so we stuff it in the
1191              # return hash.              # return hash.
1192              $retVal{$function} = $user;              $retVal{$actualUser} = $function;
             # Insure we don't assign to this user again.  
             $timeHash{$user} = 1;  
1193          }          }
1194      }      }
1195      # Return the hash of assignments found.      # Return the hash of assignments found.
# Line 1195  Line 1205 
1205  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1206  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1207  assignment is a type of annotation. The format of an assignment is described in  assignment is a type of annotation. The format of an assignment is described in
1208  L</ParseLocation>. Its worth noting that we cannot filter on the content of the  L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1209  annotation itself because it's a text field; however, this is not a big problem because  annotation itself because it's a text field; however, this is not a big problem because
1210  most features only have a small number of annotations.  most features only have a small number of annotations.
1211    
# Line 1257  Line 1267 
1267              }              }
1268          }          }
1269          # Build a query for all of the feature's annotations, sorted by date.          # Build a query for all of the feature's annotations, sorted by date.
1270          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1271                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1272                                 [$featureID]);                                 [$featureID]);
1273          my $timeSelected = 0;          my $timeSelected = 0;
1274          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1275          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
1276              # Get the annotation text.              # Get the annotation text.
1277              my ($text, $time) = $annotation->Values(['Annotation(annotation)','Annotation(time)']);              my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1278                                                         'Annotation(time)', 'MadeAnnotation(from-link)']);
1279              # Check to see if this is a functional assignment for a trusted user.              # Check to see if this is a functional assignment for a trusted user.
1280              my ($user, $function) = _ParseAssignment($text);              my ($actualUser, $function) = _ParseAssignment($user, $text);
1281              if ($user) {              Trace("Assignment user is $actualUser, text is $function.") if T(4);
1282                if ($actualUser) {
1283                  # Here it is a functional assignment. Check the time and the user                  # Here it is a functional assignment. Check the time and the user
1284                  # name. The time must be recent and the user must be trusted.                  # name. The time must be recent and the user must be trusted.
1285                  if ((exists $trusteeTable{$user}) && ($time > $timeSelected)) {                  if ((exists $trusteeTable{$actualUser}) && ($time > $timeSelected)) {
1286                      $retVal = $function;                      $retVal = $function;
1287                      $timeSelected = $time;                      $timeSelected = $time;
1288                  }                  }
# Line 1286  Line 1298 
1298      return $retVal;      return $retVal;
1299  }  }
1300    
1301    =head3 FunctionsOf
1302    
1303    C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>
1304    
1305    Return the functional assignments of a particular feature.
1306    
1307    The functional assignment is handled differently depending on the type of feature. If
1308    the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional
1309    assignment is a type of annotation. The format of an assignment is described in
1310    L</ParseAssignment>. Its worth noting that we cannot filter on the content of the
1311    annotation itself because it's a text field; however, this is not a big problem because
1312    most features only have a small number of annotations.
1313    
1314    If the feature is B<not> identified by a FIG ID, then the functional assignment
1315    information is taken from the B<ExternalAliasFunc> table. If the table does
1316    not contain an entry for the feature, an empty list is returned.
1317    
1318    =over 4
1319    
1320    =item featureID
1321    
1322    ID of the feature whose functional assignments are desired.
1323    
1324    =item RETURN
1325    
1326    Returns a list of 2-tuples, each consisting of a user ID and the text of an assignment by
1327    that user.
1328    
1329    =back
1330    
1331    =cut
1332    #: Return Type @@;
1333    sub FunctionsOf {
1334        # Get the parameters.
1335        my ($self, $featureID) = @_;
1336        # Declare the return value.
1337        my @retVal = ();
1338        # Determine the ID type.
1339        if ($featureID =~ m/^fig\|/) {
1340            # Here we have a FIG feature ID. We must build the list of trusted
1341            # users.
1342            my %trusteeTable = ();
1343            # Build a query for all of the feature's annotations, sorted by date.
1344            my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1345                                   "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1346                                   [$featureID]);
1347            my $timeSelected = 0;
1348            # Loop until we run out of annotations.
1349            while (my $annotation = $query->Fetch()) {
1350                # Get the annotation text.
1351                my ($text, $time, $user) = $annotation->Values(['Annotation(annotation)',
1352                                                                'Annotation(time)',
1353                                                                'MadeAnnotation(user)']);
1354                # Check to see if this is a functional assignment for a trusted user.
1355                my ($actualUser, $function) = _ParseAssignment($user, $text);
1356                if ($actualUser) {
1357                    # Here it is a functional assignment.
1358                    push @retVal, [$actualUser, $function];
1359                }
1360            }
1361        } else {
1362            # Here we have a non-FIG feature ID. In this case the user ID does not
1363            # matter. We simply get the information from the External Alias Function
1364            # table.
1365            my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,
1366                                                     ['ExternalAliasFunc(func)']);
1367            push @retVal, map { ['master', $_] } @assignments;
1368        }
1369        # Return the assignments found.
1370        return @retVal;
1371    }
1372    
1373  =head3 BBHList  =head3 BBHList
1374    
1375  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>
# Line 1406  Line 1490 
1490      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1491      if ($genomeData) {      if ($genomeData) {
1492          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1493          ($retVal) = $genomeData->Value('complete');          ($retVal) = $genomeData->Value('Genome(complete)');
1494      }      }
1495      # Return the result.      # Return the result.
1496      return $retVal;      return $retVal;
# Line 1446  Line 1530 
1530    
1531  C<< my $genomeID = $sprout->GenomeOf($featureID); >>  C<< my $genomeID = $sprout->GenomeOf($featureID); >>
1532    
1533  Return the genome that contains a specified feature.  Return the genome that contains a specified feature or contig.
1534    
1535  =over 4  =over 4
1536    
1537  =item featureID  =item featureID
1538    
1539  ID of the feature whose genome is desired.  ID of the feature or contig whose genome is desired.
1540    
1541  =item RETURN  =item RETURN
1542    
1543  Returns the ID of the genome for the specified feature. If the feature is not found, returns  Returns the ID of the genome for the specified feature or contig. If the feature or contig is not
1544  an undefined value.  found, returns an undefined value.
1545    
1546  =back  =back
1547    
# Line 1466  Line 1550 
1550  sub GenomeOf {  sub GenomeOf {
1551      # Get the parameters.      # Get the parameters.
1552      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1553      # Create a query to find the genome associated with the feature.      # Create a query to find the genome associated with the incoming ID.
1554      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ?", [$featureID]);      my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",
1555                               [$featureID, $featureID]);
1556      # Declare the return value.      # Declare the return value.
1557      my $retVal;      my $retVal;
1558      # Get the genome ID.      # Get the genome ID.
# Line 2604  Line 2689 
2689                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                      ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
2690      # Create the return value.      # Create the return value.
2691      my %retVal = ();      my %retVal = ();
2692        # Build a hash to weed out duplicates. Sometimes the same PEG and role appears
2693        # in two spreadsheet cells.
2694        my %dupHash = ();
2695      # Loop through the results, adding them to the hash.      # Loop through the results, adding them to the hash.
2696      for my $record (@subsystems) {      for my $record (@subsystems) {
2697            # Get this subsystem and role.
2698          my ($subsys, $role) = @{$record};          my ($subsys, $role) = @{$record};
2699          if (exists $retVal{$subsys}) {          # Insure it's the first time for both.
2700            my $dupKey = "$subsys\n$role";
2701            if (! exists $dupHash{"$subsys\n$role"}) {
2702                $dupHash{$dupKey} = 1;
2703              push @{$retVal{$subsys}}, $role;              push @{$retVal{$subsys}}, $role;
         } else {  
             $retVal{$subsys} = [$role];  
2704          }          }
2705      }      }
2706      # Return the hash.      # Return the hash.
# Line 2649  Line 2739 
2739      return @retVal;      return @retVal;
2740  }  }
2741    
2742    
2743    
2744  =head3 RelatedFeatures  =head3 RelatedFeatures
2745    
2746  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 3140  Line 3232 
3232      return $retVal;      return $retVal;
3233  }  }
3234    
3235    =head3 DeleteGenome
3236    
3237    C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>
3238    
3239    Delete a genome from the database.
3240    
3241    =over 4
3242    
3243    =item genomeID
3244    
3245    ID of the genome to delete
3246    
3247    =item testFlag
3248    
3249    If TRUE, then the DELETE statements will be traced, but no deletions will occur.
3250    
3251    =item RETURN
3252    
3253    Returns a statistics object describing the rows deleted.
3254    
3255    =back
3256    
3257    =cut
3258    #: Return Type $%;
3259    sub DeleteGenome {
3260        # Get the parameters.
3261        my ($self, $genomeID, $testFlag) = @_;
3262        # Perform the delete for the genome's features.
3263        my $retVal = $self->{_erdb}->Delete('Feature', "fig|$genomeID.%", $testFlag);
3264        # Perform the delete for the primary genome data.
3265        my $stats = $self->{_erdb}->Delete('Genome', $genomeID, $testFlag);
3266        $retVal->Accumulate($stats);
3267        # Return the result.
3268        return $retVal;
3269    }
3270    
3271  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3272    
3273  =head3 ParseAssignment  =head3 ParseAssignment
# Line 3150  Line 3278 
3278    
3279  A functional assignment is always of the form  A functional assignment is always of the form
3280    
3281      I<XXXX>C<\nset >I<YYYY>C< function to\n>I<ZZZZZ>      C<set >I<YYYY>C< function to\n>I<ZZZZZ>
3282    
3283  where I<XXXX> is the B<assigning user>, I<YYYY> is the B<user>, and I<ZZZZ> is the  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
3284  actual functional role. In most cases, the user and the assigning user will be the  the user and the assigning user (from MadeAnnotation) will be the same, but that is
3285  same, but that is not always the case.  not always the case.
3286    
3287    In addition, the functional role may contain extra data that is stripped, such as
3288    terminating spaces or a comment separated from the rest of the text by a tab.
3289    
3290  This is a static method.  This is a static method.
3291    
3292  =over 4  =over 4
3293    
3294    =item user
3295    
3296    Name of the assigning user.
3297    
3298  =item text  =item text
3299    
3300  Text of the annotation.  Text of the annotation.
# Line 3175  Line 3310 
3310    
3311  sub _ParseAssignment {  sub _ParseAssignment {
3312      # Get the parameters.      # Get the parameters.
3313      my ($text) = @_;      my ($user, $text) = @_;
3314      # Declare the return value.      # Declare the return value.
3315      my @retVal = ();      my @retVal = ();
3316      # Check to see if this is a functional assignment.      # Check to see if this is a functional assignment.
3317      my ($user, $type, $function) = split(/\n/, $text);      my ($type, $function) = split(/\n/, $text);
3318      if ($type =~ m/^set ([^ ]+) function to$/i) {      if ($type =~ m/^set function to$/i) {
3319          # Here it is, so we return the user name (which is in $1), the functional role text,          # Here we have an assignment without a user, so we use the incoming user ID.
3320          # and the assigning user.          @retVal = ($user, $function);
3321          @retVal = ($1, $function, $user);      } elsif ($type =~ m/^set (\S+) function to$/i) {
3322            # Here we have an assignment with a user that is passed back to the caller.
3323            @retVal = ($1, $function);
3324        }
3325        # If we have an assignment, we need to clean the function text. There may be
3326        # extra junk at the end added as a note from the user.
3327        if (@retVal) {
3328            $retVal[1] =~ s/(\t\S)?\s*$//;
3329      }      }
3330      # Return the result list.      # Return the result list.
3331      return @retVal;      return @retVal;
# Line 3273  Line 3415 
3415  }  }
3416    
3417    
   
3418  1;  1;

Legend:
Removed from v.1.40  
changed lines
  Added in v.1.57

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3