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

Diff of /Sprout/Sprout.pm

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

revision 1.101, Mon Aug 20 23:29:24 2007 UTC revision 1.118, Sat Sep 20 14:32:34 2008 UTC
# Line 1  Line 1 
1  package Sprout;  package Sprout;
2    
     require Exporter;  
     use ERDB;  
     @ISA = qw(Exporter ERDB);  
3      use Data::Dumper;      use Data::Dumper;
4      use strict;      use strict;
5      use DBKernel;      use DBKernel;
# Line 17  Line 14 
14      use BasicLocation;      use BasicLocation;
15      use CustomAttributes;      use CustomAttributes;
16      use RemoteCustomAttributes;      use RemoteCustomAttributes;
17        use CGI;
18        use WikiTools;
19        use BioWords;
20        use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
23    
# Line 29  Line 30 
30  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>  on the constructor. For example, the following invocation specifies a PostgreSQL database named I<GenDB>
31  whose definition and data files are in a co-directory named F<Data>.  whose definition and data files are in a co-directory named F<Data>.
32    
33  C<< my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' }); >>      my $sprout = Sprout->new('GenDB', { dbType => 'pg', dataDir => '../Data', xmlFileName => '../Data/SproutDBD.xml' });
34    
35  Once you have a sprout object, you may use it to re-create the database, load the tables from  Once you have a sprout object, you may use it to re-create the database, load the tables from
36  tab-delimited flat files and perform queries. Several special methods are provided for common  tab-delimited flat files and perform queries. Several special methods are provided for common
37  query tasks. For example, L</genomes> lists the IDs of all the genomes in the database and  query tasks. For example, L</Genomes> lists the IDs of all the genomes in the database and
38  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
39    
40  The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.  The Sprout object is a subclass of the ERDB object and inherits all its properties and methods.
41    
# Line 46  Line 47 
47    
48  =head3 new  =head3 new
49    
50  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
51    
52  This is the constructor for a sprout object. It connects to the database and loads the  This is the constructor for a sprout object. It connects to the database and loads the
53  database definition into memory. The positional first parameter specifies the name of the  database definition into memory. The positional first parameter specifies the name of the
# Line 80  Line 81 
81    
82  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
83    
84    * B<host> name of the database host
85    
86  =back  =back
87    
88  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
89  I<fig> with a password of I<admin>. The database load files are in the directory  I<fig> with a password of I<admin>. The database load files are in the directory
90  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
91    
92  C<< my $sprout = Sprout->new('Sprout', { userData =>; 'fig/admin', dataDir => '/usr/fig/SproutData' }); >>      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
93    
94  =cut  =cut
95    
# Line 105  Line 108 
108                                                          # data file directory                                                          # data file directory
109                         xmlFileName  => "$dbd_dir/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
110                                                          # database definition file name                                                          # database definition file name
111                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
112                                                          # user name and password                                                          # user name and password
113                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::sproutPort,
114                                                          # database connection port                                                          # database connection port
115                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::sproutSock,
116                         host         => $FIG_Config::dbhost,                         host         => $FIG_Config::sprout_host,
117                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
118                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
119                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 123  Line 126 
126      # Connect to the database.      # Connect to the database.
127      my $dbh;      my $dbh;
128      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
129            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
130          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
131                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
132      }      }
# Line 149  Line 153 
153      return $retVal;      return $retVal;
154  }  }
155    
156    =head3 CoreGenomes
157    
158        my @genomes = $sprout->CoreGenomes($scope);
159    
160    Return the IDs of NMPDR genomes in the specified scope.
161    
162    =over 4
163    
164    =item scope
165    
166    Scope of the desired genomes. C<core> covers the original core genomes,
167    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
168    genomes in the system.
169    
170    =item RETURN
171    
172    Returns a list of the IDs for the genomes in the specified scope.
173    
174    =back
175    
176    =cut
177    
178    sub CoreGenomes {
179        # Get the parameters.
180        my ($self, $scope) = @_;
181        # Declare the return variable.
182        my @retVal = ();
183        # If we want all genomes, then this is easy.
184        if ($scope eq 'all') {
185            @retVal = $self->Genomes();
186        } else {
187            # Here we're dealing with groups. Get the hash of all the
188            # genome groups.
189            my %groups = $self->GetGroups();
190            # Loop through the groups, keeping the ones that we want.
191            for my $group (keys %groups) {
192                # Decide if we want to keep this group.
193                my $keepGroup = 0;
194                if ($scope eq 'nmpdr') {
195                    # NMPDR mode: keep all groups.
196                    $keepGroup = 1;
197                } elsif ($scope eq 'core') {
198                    # CORE mode. Only keep real core groups.
199                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
200                        $keepGroup = 1;
201                    }
202                }
203                # Add this group if we're keeping it.
204                if ($keepGroup) {
205                    push @retVal, @{$groups{$group}};
206                }
207            }
208        }
209        # Return the result.
210        return @retVal;
211    }
212    
213    =head3 SuperGroup
214    
215        my $superGroup = $sprout->SuperGroup($groupName);
216    
217    Return the name of the super-group containing the specified NMPDR genome
218    group. If no appropriate super-group can be found, an error will be
219    thrown.
220    
221    =over 4
222    
223    =item groupName
224    
225    Name of the group whose super-group is desired.
226    
227    =item RETURN
228    
229    Returns the name of the super-group containing the incoming group.
230    
231    =back
232    
233    =cut
234    
235    sub SuperGroup {
236        # Get the parameters.
237        my ($self, $groupName) = @_;
238        # Declare the return variable.
239        my $retVal;
240        # Get the group hash.
241        my %groupHash = $self->CheckGroupFile();
242        # Find the super-group genus.
243        $groupName =~ /([A-Z]\w+)/;
244        my $nameThing = $1;
245        # See if it's directly in the group hash.
246        if (exists $groupHash{$nameThing}) {
247            # Yes, then it's our result.
248            $retVal = $nameThing;
249        } else {
250            # No, so we have to search.
251            for my $superGroup (keys %groupHash) {
252                # Get this super-group's item list.
253                my $list = $groupHash{$superGroup}->{contents};
254                # Search it.
255                if (grep { $_->[0] eq $nameThing } @{$list}) {
256                    $retVal = $superGroup;
257                }
258            }
259            # Make sure we found something.
260            if (! $retVal) {
261                Confess("No super-group found for \"$groupName\".");
262            }
263        }
264        # Return the result.
265        return $retVal;
266    }
267    
268  =head3 MaxSegment  =head3 MaxSegment
269    
270  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
271    
272  This method returns the maximum permissible length of a feature segment. The length is important  This method returns the maximum permissible length of a feature segment. The length is important
273  because it enables us to make reasonable guesses at how to find features inside a particular  because it enables us to make reasonable guesses at how to find features inside a particular
# Line 168  Line 284 
284    
285  =head3 MaxSequence  =head3 MaxSequence
286    
287  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
288    
289  This method returns the maximum permissible length of a contig sequence. A contig is broken  This method returns the maximum permissible length of a contig sequence. A contig is broken
290  into sequences in order to save memory resources. In particular, when manipulating features,  into sequences in order to save memory resources. In particular, when manipulating features,
# Line 183  Line 299 
299    
300  =head3 Load  =head3 Load
301    
302  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
303    
304  Load the database from files in the data directory, optionally re-creating the tables.  Load the database from files in the data directory, optionally re-creating the tables.
305    
# Line 223  Line 339 
339    
340  =head3 LoadUpdate  =head3 LoadUpdate
341    
342  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
343    
344  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
345  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 269  Line 385 
385              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
386          } else {          } else {
387              # Attempt to load this table.              # Attempt to load this table.
388              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
389              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
390              $retVal->Accumulate($result);              $retVal->Accumulate($result);
391          }          }
# Line 280  Line 396 
396    
397  =head3 GenomeCounts  =head3 GenomeCounts
398    
399  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
400    
401  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete  Count the number of genomes in each domain. If I<$complete> is TRUE, only complete
402  genomes will be included in the counts.  genomes will be included in the counts.
# Line 325  Line 441 
441    
442  =head3 ContigCount  =head3 ContigCount
443    
444  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
445    
446  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
447    
# Line 352  Line 468 
468      return $retVal;      return $retVal;
469  }  }
470    
471  =head3 GeneMenu  =head3 GenomeMenu
472    
473  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >>      my $html = $sprout->GenomeMenu(%options);
474    
475  Return an HTML select menu of genomes. Each genome will be an option in the menu,  Generate a genome selection control with the specified name and options.
476  and will be displayed by name with the ID and a contig count attached. The selection  This control is almost but not quite the same as the genome control in the
477  value will be the genome ID. The genomes will be sorted by genus/species name.  B<SearchHelper> class. Eventually, the two will be combined.
478    
479  =over 4  =over 4
480    
481  =item attributes  =item options
482    
483  Reference to a hash mapping attributes to values for the SELECT tag generated.  Optional parameters for the control (see below).
484    
485  =item filterString  =item RETURN
486    
487  A filter string for use in selecting the genomes. The filter string must conform  Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
 to the rules for the C<< ERDB->Get >> method.  
488    
489  =item params  =back
490    
491  Reference to a list of values to be substituted in for the parameter marks in  The valid options are as follows.
 the filter string.  
492    
493  =item selected (optional)  =over 4
494    
495  ID of the genome to be initially selected.  =item name
496    
497    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
498    Terrible things will happen if you have two controls with the same name on the same page.
499    
500  =item fast (optional)  =item filter
501    
502  If specified and TRUE, the contig counts will be omitted to improve performance.  If specified, a filter for the list of genomes to display. The filter should be in the form of a
503    list reference. The first element of the list should be the filter string, and the remaining elements
504    the filter parameters.
505    
506    =item multiSelect
507    
508    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
509    
510    =item size
511    
512    Number of rows to display in the control. The default is C<10>
513    
514    =item id
515    
516    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
517    unless this ID is unique.
518    
519    =item selected
520    
521    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
522    default is none.
523    
524    =item class
525    
526    If specified, a style class to assign to the genome control.
527    
528    =back
529    
530    =cut
531    
532    sub GenomeMenu {
533        # Get the parameters.
534        my ($self, %options) = @_;
535        # Get the control's name and ID.
536        my $menuName = $options{name} || $options{id} || 'myGenomeControl';
537        my $menuID = $options{id} || $menuName;
538        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
539        # Compute the IDs for the status display.
540        my $divID = "${menuID}_status";
541        my $urlID = "${menuID}_url";
542        # Compute the code to show selected genomes in the status area.
543        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
544        # Check for single-select or multi-select.
545        my $multiSelect = $options{multiSelect} || 0;
546        # Get the style data.
547        my $class = $options{class} || '';
548        # Get the list of pre-selected items.
549        my $selections = $options{selected} || [];
550        if (ref $selections ne 'ARRAY') {
551            $selections = [ split /\s*,\s*/, $selections ];
552        }
553        my %selected = map { $_ => 1 } @{$selections};
554        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
555        # string or a list reference.
556        my $filterParms = $options{filter} || "";
557        if (! ref $filterParms) {
558            $filterParms = [split /\t|\\t/, $filterParms];
559        }
560        my $filterString = shift @{$filterParms};
561        # Get a list of all the genomes in group order. In fact, we only need them ordered
562        # by name (genus,species,strain), but putting primary-group in front enables us to
563        # take advantage of an existing index.
564        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
565                                       $filterParms,
566                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
567        # Create a hash to organize the genomes by group. Each group will contain a list of
568        # 2-tuples, the first element being the genome ID and the second being the genome
569        # name.
570        my %gHash = ();
571        for my $genome (@genomeList) {
572            # Get the genome data.
573            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
574            # Compute its name. This is the genus, species, strain (if any), and the contig count.
575            my $name = "$genus $species ";
576            $name .= "$strain " if $strain;
577            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
578            # Now we get the domain. The domain tells us the display style of the organism.
579            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
580            # Now compute the display group. This is normally the primary group, but if the
581            # organism is supporting, we blank it out.
582            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
583            # Push the genome into the group's list. Note that we use the real group
584            # name for the hash key here, not the display group name.
585            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
586        }
587        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
588        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
589        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
590        # that aren't "other". At some point, we will want to make this less complicated.
591        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
592                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
593        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
594        # Remember the number of NMPDR groups.
595        my $nmpdrGroupCount = scalar @groups;
596        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
597        # of the domains found.
598        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
599        my @domains = ();
600        for my $genomeData (@otherGenomes) {
601            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
602            if (exists $gHash{$domain}) {
603                push @{$gHash{$domain}}, $genomeData;
604            } else {
605                $gHash{$domain} = [$genomeData];
606                push @domains, $domain;
607            }
608        }
609        # Add the domain groups at the end of the main group list. The main group list will now
610        # contain all the categories we need to display the genomes.
611        push @groups, sort @domains;
612        # Delete the supporting group.
613        delete $gHash{$FIG_Config::otherGroup};
614        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
615        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
616        # and use that to make the selections.
617        my $nmpdrCount = 0;
618        # Create the type counters.
619        my $groupCount = 1;
620        # Get the number of rows to display.
621        my $rows = $options{size} || 10;
622        # If we're multi-row, create an onChange event.
623        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
624        # Set up the multiple-select flag.
625        my $multipleTag = ($multiSelect ? " multiple" : "" );
626        # Set up the style class.
627        my $classTag = ($class ? " class=\"$class\"" : "" );
628        # Create the SELECT tag and stuff it into the output array.
629        my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
630        # Loop through the groups.
631        for my $group (@groups) {
632            # Get the genomes in the group.
633            for my $genome (@{$gHash{$group}}) {
634                # If this is an NMPDR organism, we add an extra style and count it.
635                my $nmpdrStyle = "";
636                if ($nmpdrGroupCount > 0) {
637                    $nmpdrCount++;
638                    $nmpdrStyle = " Core";
639                }
640                # Get the organism ID, name, contig count, and domain.
641                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
642                # See if we're pre-selected.
643                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
644                # Compute the display name.
645                my $nameString = "$name ($genomeID$contigCount)";
646                # Generate the option tag.
647                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
648                push @lines, "    $optionTag";
649            }
650            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
651            # groups.
652            $nmpdrGroupCount--;
653        }
654        # Close the SELECT tag.
655        push @lines, "</SELECT>";
656        if ($rows > 1) {
657            # We're in a non-compact mode, so we need to add some selection helpers. First is
658            # the search box. This allows the user to type text and change which genomes are
659            # displayed. For multiple-select mode, we include a button that selects the displayed
660            # genes. For single-select mode, we use a plain label instead.
661            my $searchThingName = "${menuID}_SearchThing";
662            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
663                                                 : "Show genomes containing");
664            push @lines, "<br />$searchThingLabel&nbsp;" .
665                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
666                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
667            # For multi-select mode, we also have buttons to set and clear selections.
668            if ($multiSelect) {
669                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
670                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
671                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
672            }
673            # Add a hidden field we can use to generate organism page hyperlinks.
674            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
675            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
676            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
677        }
678        # Assemble all the lines into a string.
679        my $retVal = join("\n", @lines, "");
680        # Return the result.
681        return $retVal;
682    }
683    
684    
685    =head3 Stem
686    
687        my $stem = $sprout->Stem($word);
688    
689    Return the stem of the specified word, or C<undef> if the word is not
690    stemmable. Note that even if the word is stemmable, the stem may be
691    the same as the original word.
692    
693    =over 4
694    
695    =item word
696    
697    Word to convert into a stem.
698    
699  =item RETURN  =item RETURN
700    
701  Returns an HTML select menu with the specified genomes as selectable options.  Returns a stem of the word (which may be the word itself), or C<undef> if
702    the word is not stemmable.
703    
704  =back  =back
705    
706  =cut  =cut
707    
708  sub GeneMenu {  sub Stem {
709      # Get the parameters.      # Get the parameters.
710      my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;      my ($self, $word) = @_;
711      my $slowMode = ! $fast;      # Get the stemmer object.
712      # Default to nothing selected. This prevents an execution warning if "$selected"      my $stemmer = $self->{stemmer};
713      # is undefined.      if (! defined $stemmer) {
714      $selected = "" unless defined $selected;          # We don't have one pre-built, so we build and save it now.
715      Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);          $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
716      # Start the menu.                                   stops => "$FIG_Config::sproutData/StopWords.txt",
717      my $retVal = "<select " .                                   cache => 1);
718          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .          $self->{stemmer} = $stemmer;
         ">\n";  
     # Get the genomes.  
     my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',  
                                                                      'Genome(genus)',  
                                                                      'Genome(species)',  
                                                                      'Genome(unique-characterization)']);  
     # Sort them by name.  
     my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;  
     # Loop through the genomes, creating the option tags.  
     for my $genomeData (@sorted) {  
         # Get the data for this genome.  
         my ($genomeID, $genus, $species, $strain) = @{$genomeData};  
         # Get the contig count.  
         my $contigInfo = "";  
         if ($slowMode) {  
             my $count = $self->ContigCount($genomeID);  
             my $counting = ($count == 1 ? "contig" : "contigs");  
             $contigInfo = "[$count $counting]";  
         }  
         # Find out if we're selected.  
         my $selectOption = ($selected eq $genomeID ? " selected" : "");  
         # Build the option tag.  
         $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";  
719      }      }
720      # Close the SELECT tag.      # Try to stem the word.
721      $retVal .= "</select>\n";      my $retVal = $stemmer->Process($word);
722      # Return the result.      # Return the result.
723      return $retVal;      return $retVal;
724  }  }
725    
726    
727  =head3 Build  =head3 Build
728    
729  C<< $sprout->Build(); >>      $sprout->Build();
730    
731  Build the database. The database will be cleared and the tables re-created from the metadata.  Build the database. The database will be cleared and the tables re-created from the metadata.
732  This method is useful when a database is brand new or when the database definition has  This method is useful when a database is brand new or when the database definition has
# Line 452  Line 743 
743    
744  =head3 Genomes  =head3 Genomes
745    
746  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
747    
748  Return a list of all the genome IDs.  Return a list of all the genome IDs.
749    
# Line 469  Line 760 
760    
761  =head3 GenusSpecies  =head3 GenusSpecies
762    
763  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
764    
765  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
766    
# Line 501  Line 792 
792    
793  =head3 FeaturesOf  =head3 FeaturesOf
794    
795  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
796    
797  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
798    
# Line 546  Line 837 
837    
838  =head3 FeatureLocation  =head3 FeatureLocation
839    
840  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
841    
842  Return the location of a feature in its genome's contig segments. In a list context, this method  Return the location of a feature in its genome's contig segments. In a list context, this method
843  will return a list of the locations. In a scalar context, it will return the locations as a space-  will return a list of the locations. In a scalar context, it will return the locations as a space-
# Line 570  Line 861 
861  =item RETURN  =item RETURN
862    
863  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
864  context and as a comma-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
865    wasn't found.
866    
867  =back  =back
868    
# Line 579  Line 871 
871  sub FeatureLocation {  sub FeatureLocation {
872      # Get the parameters.      # Get the parameters.
873      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
874        # Declare the return variable.
875        my @retVal = ();
876      # Get the feature record.      # Get the feature record.
877      my $object = $self->GetEntity('Feature', $featureID);      my $object = $self->GetEntity('Feature', $featureID);
878      Confess("Feature $featureID not found.") if ! defined($object);      # Only proceed if we found it.
879        if (defined $object) {
880      # Get the location string.      # Get the location string.
881      my $locString = $object->PrimaryValue('Feature(location-string)');      my $locString = $object->PrimaryValue('Feature(location-string)');
882      # Create the return list.      # Create the return list.
883      my @retVal = split /\s*,\s*/, $locString;          @retVal = split /\s*,\s*/, $locString;
884        }
885      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
886      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
887  }  }
888    
889  =head3 ParseLocation  =head3 ParseLocation
890    
891  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
892    
893  Split a location specifier into the contig ID, the starting point, the direction, and the  Split a location specifier into the contig ID, the starting point, the direction, and the
894  length.  length.
# Line 638  Line 934 
934    
935  =head3 PointLocation  =head3 PointLocation
936    
937  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
938    
939  Return the offset into the specified location of the specified point on the contig. If  Return the offset into the specified location of the specified point on the contig. If
940  the specified point is before the location, a negative value will be returned. If it is  the specified point is before the location, a negative value will be returned. If it is
# Line 690  Line 986 
986    
987  =head3 DNASeq  =head3 DNASeq
988    
989  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
990    
991  This method returns the DNA sequence represented by a list of locations. The list of locations  This method returns the DNA sequence represented by a list of locations. The list of locations
992  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,
# Line 774  Line 1070 
1070    
1071  =head3 AllContigs  =head3 AllContigs
1072    
1073  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1074    
1075  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1076    
# Line 804  Line 1100 
1100    
1101  =head3 GenomeLength  =head3 GenomeLength
1102    
1103  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1104    
1105  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1106    
# Line 839  Line 1135 
1135    
1136  =head3 FeatureCount  =head3 FeatureCount
1137    
1138  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1139    
1140  Return the number of features of the specified type in the specified genome.  Return the number of features of the specified type in the specified genome.
1141    
# Line 874  Line 1170 
1170    
1171  =head3 GenomeAssignments  =head3 GenomeAssignments
1172    
1173  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1174    
1175  Return a list of a genome's assigned features. The return hash will contain each  Return a list of a genome's assigned features. The return hash will contain each
1176  assigned feature of the genome mapped to the text of its most recent functional  assigned feature of the genome mapped to the text of its most recent functional
# Line 917  Line 1213 
1213    
1214  =head3 ContigLength  =head3 ContigLength
1215    
1216  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1217    
1218  Compute the length of a contig.  Compute the length of a contig.
1219    
# Line 956  Line 1252 
1252    
1253  =head3 ClusterPEGs  =head3 ClusterPEGs
1254    
1255  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1256    
1257  Cluster the PEGs in a list according to the cluster coding scheme of the specified  Cluster the PEGs in a list according to the cluster coding scheme of the specified
1258  subsystem. In order for this to work properly, the subsystem object must have  subsystem. In order for this to work properly, the subsystem object must have
1259  been used recently to retrieve the PEGs using the B<get_pegs_from_cell> method.  been used recently to retrieve the PEGs using the B<get_pegs_from_cell> or
1260  This causes the cluster numbers to be pulled into the subsystem's color hash.  B<get_row> methods. This causes the cluster numbers to be pulled into the
1261  If a PEG is not found in the color hash, it will not appear in the output  subsystem's color hash. If a PEG is not found in the color hash, it will not
1262  sequence.  appear in the output sequence.
1263    
1264  =over 4  =over 4
1265    
# Line 1004  Line 1300 
1300    
1301  =head3 GenesInRegion  =head3 GenesInRegion
1302    
1303  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1304    
1305  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1306    
# Line 1085  Line 1381 
1381    
1382  =head3 GeneDataInRegion  =head3 GeneDataInRegion
1383    
1384  C<< my @featureList = $sprout->GenesInRegion($contigID, $start, $stop); >>      my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1385    
1386  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1387    
# Line 1156  Line 1452 
1452    
1453  =head3 FType  =head3 FType
1454    
1455  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1456    
1457  Return the type of a feature.  Return the type of a feature.
1458    
# Line 1186  Line 1482 
1482    
1483  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1484    
1485  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1486    
1487  Return the annotations of a feature.  Return the annotations of a feature.
1488    
# Line 1249  Line 1545 
1545    
1546  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1547    
1548  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1549    
1550  Return all of the functional assignments for a particular feature. The data is returned as a  Return all of the functional assignments for a particular feature. The data is returned as a
1551  hash of functional assignments to user IDs. A functional assignment is a type of annotation,  hash of functional assignments to user IDs. A functional assignment is a type of annotation,
# Line 1304  Line 1600 
1600    
1601  =head3 FunctionOf  =head3 FunctionOf
1602    
1603  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1604    
1605  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1606    
# Line 1317  Line 1613 
1613  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1614  is trusted.  is trusted.
1615    
1616  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1617  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1618    
1619  =over 4  =over 4
1620    
# Line 1345  Line 1640 
1640      my ($self, $featureID, $userID) = @_;      my ($self, $featureID, $userID) = @_;
1641      # Declare the return value.      # Declare the return value.
1642      my $retVal;      my $retVal;
1643      # Determine the ID type.      # Find a FIG ID for this feature.
1644      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1645        # Only proceed if we have an ID.
1646        if ($fid) {
1647          # Here we have a FIG feature ID.          # Here we have a FIG feature ID.
1648          if (!$userID) {          if (!$userID) {
1649              # Use the primary assignment.              # Use the primary assignment.
1650              ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);              ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1651          } else {          } else {
1652              # We must build the list of trusted users.              # We must build the list of trusted users.
1653              my %trusteeTable = ();              my %trusteeTable = ();
# Line 1376  Line 1673 
1673              # 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.
1674              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1675                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1676                                     [$featureID]);                                     [$fid]);
1677              my $timeSelected = 0;              my $timeSelected = 0;
1678              # Loop until we run out of annotations.              # Loop until we run out of annotations.
1679              while (my $annotation = $query->Fetch()) {              while (my $annotation = $query->Fetch()) {
# Line 1396  Line 1693 
1693                  }                  }
1694              }              }
1695          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1696      }      }
1697      # Return the assignment found.      # Return the assignment found.
1698      return $retVal;      return $retVal;
# Line 1408  Line 1700 
1700    
1701  =head3 FunctionsOf  =head3 FunctionsOf
1702    
1703  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1704    
1705  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1706    
# Line 1419  Line 1711 
1711  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
1712  most features only have a small number of annotations.  most features only have a small number of annotations.
1713    
 If the feature is B<not> identified by a FIG ID, then the functional assignment  
 information is taken from the B<ExternalAliasFunc> table. If the table does  
 not contain an entry for the feature, an empty list is returned.  
   
1714  =over 4  =over 4
1715    
1716  =item featureID  =item featureID
# Line 1443  Line 1731 
1731      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1732      # Declare the return value.      # Declare the return value.
1733      my @retVal = ();      my @retVal = ();
1734      # Determine the ID type.      # Convert to a FIG ID.
1735      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1736        # Only proceed if we found one.
1737        if ($fid) {
1738          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID. We must build the list of trusted
1739          # users.          # users.
1740          my %trusteeTable = ();          my %trusteeTable = ();
1741          # 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.
1742          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1743                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1744                                 [$featureID]);                                 [$fid]);
1745          my $timeSelected = 0;          my $timeSelected = 0;
1746          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1747          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1466  Line 1756 
1756                  push @retVal, [$actualUser, $function];                  push @retVal, [$actualUser, $function];
1757              }              }
1758          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         my @assignments = $self->GetEntityValues('ExternalAliasFunc', $featureID,  
                                                  ['ExternalAliasFunc(func)']);  
         push @retVal, map { ['master', $_] } @assignments;  
1759      }      }
1760      # Return the assignments found.      # Return the assignments found.
1761      return @retVal;      return @retVal;
# Line 1480  Line 1763 
1763    
1764  =head3 BBHList  =head3 BBHList
1765    
1766  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1767    
1768  Return a hash mapping the features in a specified list to their bidirectional best hits  Return a hash mapping the features in a specified list to their bidirectional best hits
1769  on a specified target genome.  on a specified target genome.
# Line 1530  Line 1813 
1813    
1814  =head3 SimList  =head3 SimList
1815    
1816  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1817    
1818  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1819    
# Line 1566  Line 1849 
1849    
1850  =head3 IsComplete  =head3 IsComplete
1851    
1852  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1853    
1854  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1855    
# Line 1602  Line 1885 
1885    
1886  =head3 FeatureAliases  =head3 FeatureAliases
1887    
1888  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1889    
1890  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1891    
# Line 1632  Line 1915 
1915    
1916  =head3 GenomeOf  =head3 GenomeOf
1917    
1918  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1919    
1920  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1921    
# Line 1660  Line 1943 
1943      if ($featureID =~ /^fig\|(\d+\.\d+)/) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1944          $retVal = $1;          $retVal = $1;
1945      } else {      } else {
1946          Confess("Invalid feature ID $featureID.");          # Find the feature by alias.
1947            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1948            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1949                $retVal = $1;
1950            }
1951      }      }
1952      # Return the value found.      # Return the value found.
1953      return $retVal;      return $retVal;
# Line 1668  Line 1955 
1955    
1956  =head3 CoupledFeatures  =head3 CoupledFeatures
1957    
1958  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1959    
1960  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1961  functionally coupled if they tend to be clustered on the same chromosome.  functionally coupled if they tend to be clustered on the same chromosome.
# Line 1715  Line 2002 
2002    
2003  =head3 CouplingEvidence  =head3 CouplingEvidence
2004    
2005  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2006    
2007  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
2008    
# Line 1777  Line 2064 
2064    
2065  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2066    
2067  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2068    
2069  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2070    
# Line 1816  Line 2103 
2103    
2104  =head3 GetBoundaries  =head3 GetBoundaries
2105    
2106  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2107    
2108  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2109  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1880  Line 2167 
2167    
2168  =head3 ReadFasta  =head3 ReadFasta
2169    
2170  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2171    
2172  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by  Read sequence data from a FASTA-format file. Each sequence in a FASTA file is represented by
2173  one or more lines of data. The first line begins with a > character and contains an ID.  one or more lines of data. The first line begins with a > character and contains an ID.
# Line 1946  Line 2233 
2233    
2234  =head3 FormatLocations  =head3 FormatLocations
2235    
2236  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2237    
2238  Insure that a list of feature locations is in the Sprout format. The Sprout feature location  Insure that a list of feature locations is in the Sprout format. The Sprout feature location
2239  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward  format is I<contig>_I<beg*len> where I<*> is C<+> for a forward gene and C<-> for a backward
# Line 2011  Line 2298 
2298    
2299  =head3 DumpData  =head3 DumpData
2300    
2301  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2302    
2303  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.  Dump all the tables to tab-delimited DTX files. The files will be stored in the data directory.
2304    
# Line 2028  Line 2315 
2315    
2316  =head3 XMLFileName  =head3 XMLFileName
2317    
2318  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2319    
2320  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2321    
# Line 2039  Line 2326 
2326      return $self->{_xmlName};      return $self->{_xmlName};
2327  }  }
2328    
2329    =head3 GetGenomeNameData
2330    
2331        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2332    
2333    Return the genus, species, and unique characterization for a genome. This
2334    is similar to L</GenusSpecies>, with the exception that it returns the
2335    values in three seperate fields.
2336    
2337    =over 4
2338    
2339    =item genomeID
2340    
2341    ID of the genome whose name data is desired.
2342    
2343    =item RETURN
2344    
2345    Returns a three-element list, consisting of the genus, species, and strain
2346    of the specified genome. If the genome is not found, an error occurs.
2347    
2348    =back
2349    
2350    =cut
2351    
2352    sub GetGenomeNameData {
2353        # Get the parameters.
2354        my ($self, $genomeID) = @_;
2355        # Get the desired values.
2356        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2357                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2358        # Throw an error if they were not found.
2359        if (! defined $genus) {
2360            Confess("Genome $genomeID not found in database.");
2361        }
2362        # Return the results.
2363        return ($genus, $species, $strain);
2364    }
2365    
2366    =head3 GetGenomeByNameData
2367    
2368        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2369    
2370    Return a list of the IDs of the genomes with the specified genus,
2371    species, and strain. In almost every case, there will be either zero or
2372    one IDs returned; however, two or more IDs could be returned if there are
2373    multiple versions of the genome in the database.
2374    
2375    =over 4
2376    
2377    =item genus
2378    
2379    Genus of the desired genome.
2380    
2381    =item species
2382    
2383    Species of the desired genome.
2384    
2385    =item strain
2386    
2387    Strain (unique characterization) of the desired genome. This may be an empty
2388    string, in which case it is presumed that the desired genome has no strain
2389    specified.
2390    
2391    =item RETURN
2392    
2393    Returns a list of the IDs of the genomes having the specified genus, species, and
2394    strain.
2395    
2396    =back
2397    
2398    =cut
2399    
2400    sub GetGenomeByNameData {
2401        # Get the parameters.
2402        my ($self, $genus, $species, $strain) = @_;
2403        # Try to find the genomes.
2404        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2405                                    [$genus, $species, $strain], 'Genome(id)');
2406        # Return the result.
2407        return @retVal;
2408    }
2409    
2410  =head3 Insert  =head3 Insert
2411    
2412  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2413    
2414  Insert an entity or relationship instance into the database. The entity or relationship of interest  Insert an entity or relationship instance into the database. The entity or relationship of interest
2415  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 2050  Line 2418 
2418  list references. For example, the following line inserts an inactive PEG feature named  list references. For example, the following line inserts an inactive PEG feature named
2419  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2420    
2421  C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2422    
2423  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2424  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2425    
2426  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2427    
2428  =over 4  =over 4
2429    
# Line 2080  Line 2448 
2448    
2449  =head3 Annotate  =head3 Annotate
2450    
2451  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2452    
2453  Annotate a feature. This inserts an Annotation record into the database and links it to the  Annotate a feature. This inserts an Annotation record into the database and links it to the
2454  specified feature and user.  specified feature and user.
# Line 2134  Line 2502 
2502    
2503  =head3 AssignFunction  =head3 AssignFunction
2504    
2505  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2506    
2507  This method assigns a function to a feature. Functions are a special type of annotation. The general  This method assigns a function to a feature. Functions are a special type of annotation. The general
2508  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2194  Line 2562 
2562    
2563  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2564    
2565  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2566    
2567  Returns a list of features with the specified alias. The alias is parsed to determine  Returns a list of features with the specified alias. The alias is parsed to determine
2568  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6  the type of the alias. A string of digits is a GenBack ID and a string of exactly 6
# Line 2236  Line 2604 
2604    
2605  =head3 FeatureTranslation  =head3 FeatureTranslation
2606    
2607  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2608    
2609  Return the translation of a feature.  Return the translation of a feature.
2610    
# Line 2264  Line 2632 
2632    
2633  =head3 Taxonomy  =head3 Taxonomy
2634    
2635  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2636    
2637  Return the taxonomy of the specified genome. This will be in the form of a list  Return the taxonomy of the specified genome. This will be in the form of a list
2638  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,  containing the various classifications in order from domain (eg. C<Bacteria>, C<Archaea>,
2639  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2640    
2641  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2642    
2643  =over 4  =over 4
2644    
# Line 2305  Line 2673 
2673    
2674  =head3 CrudeDistance  =head3 CrudeDistance
2675    
2676  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2677    
2678  Returns a crude estimate of the distance between two genomes. The distance is construed so  Returns a crude estimate of the distance between two genomes. The distance is construed so
2679  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.  that it will be 0 for genomes with identical taxonomies and 1 for genomes from different domains.
# Line 2357  Line 2725 
2725    
2726  =head3 RoleName  =head3 RoleName
2727    
2728  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2729    
2730  Return the descriptive name of the role with the specified ID. In general, a role  Return the descriptive name of the role with the specified ID. In general, a role
2731  will only have a descriptive name if it is coded as an EC number.  will only have a descriptive name if it is coded as an EC number.
# Line 2391  Line 2759 
2759    
2760  =head3 RoleDiagrams  =head3 RoleDiagrams
2761    
2762  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2763    
2764  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2765    
# Line 2419  Line 2787 
2787      return @retVal;      return @retVal;
2788  }  }
2789    
 =head3 GetProperties  
   
 C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>  
   
 Return a list of the properties with the specified characteristics.  
   
 Properties are the Sprout analog of the FIG attributes. The call is  
 passed directly to the CustomAttributes or RemoteCustomAttributes object  
 contained in this object.  
   
 This method returns a series of tuples that match the specified criteria. Each tuple  
 will contain an object ID, a key, and one or more values. The parameters to this  
 method therefore correspond structurally to the values expected in each tuple. In  
 addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any  
 of the parameters. So, for example,  
   
     my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);  
   
 would return something like  
   
     ['fig}100226.1.peg.1004', 'structure', 1, 2]  
     ['fig}100226.1.peg.1004', 'structure1', 1, 2]  
     ['fig}100226.1.peg.1004', 'structure2', 1, 2]  
     ['fig}100226.1.peg.1004', 'structureA', 1, 2]  
   
 Use of C<undef> in any position acts as a wild card (all values). You can also specify  
 a list reference in the ID column. Thus,  
   
     my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');  
   
 would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its  
 features.  
   
 In addition to values in multiple sections, a single attribute key can have multiple  
 values, so even  
   
     my @attributeList = $sprout->GetProperties($peg, 'virulent');  
   
 which has no wildcard in the key or the object ID, may return multiple tuples.  
   
 =over 4  
   
 =item objectID  
   
 ID of object whose attributes are desired. If the attributes are desired for multiple  
 objects, this parameter can be specified as a list reference. If the attributes are  
 desired for all objects, specify C<undef> or an empty string. Finally, you can specify  
 attributes for a range of object IDs by putting a percent sign (C<%>) at the end.  
   
 =item key  
   
 Attribute key name. A value of C<undef> or an empty string will match all  
 attribute keys. If the values are desired for multiple keys, this parameter can be  
 specified as a list reference. Finally, you can specify attributes for a range of  
 keys by putting a percent sign (C<%>) at the end.  
   
 =item values  
   
 List of the desired attribute values, section by section. If C<undef>  
 or an empty string is specified, all values in that section will match. A  
 generic match can be requested by placing a percent sign (C<%>) at the end.  
 In that case, all values that match up to and not including the percent sign  
 will match. You may also specify a regular expression enclosed  
 in slashes. All values that match the regular expression will be returned. For  
 performance reasons, only values have this extra capability.  
   
 =item RETURN  
   
 Returns a list of tuples. The first element in the tuple is an object ID, the  
 second is an attribute key, and the remaining elements are the sections of  
 the attribute value. All of the tuples will match the criteria set forth in  
 the parameter list.  
   
 =back  
   
 =cut  
   
 sub GetProperties {  
     # Get the parameters.  
     my ($self, @parms) = @_;  
     # Declare the return variable.  
     my @retVal = $self->{_ca}->GetAttributes(@parms);  
     # Return the result.  
     return @retVal;  
 }  
   
2790  =head3 FeatureProperties  =head3 FeatureProperties
2791    
2792  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2793    
2794  Return a list of the properties for the specified feature. Properties are key-value pairs  Return a list of the properties for the specified feature. Properties are key-value pairs
2795  that specify special characteristics of the feature. For example, a property could indicate  that specify special characteristics of the feature. For example, a property could indicate
# Line 2546  Line 2828 
2828    
2829  =head3 DiagramName  =head3 DiagramName
2830    
2831  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2832    
2833  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2834    
# Line 2574  Line 2856 
2856    
2857  =head3 PropertyID  =head3 PropertyID
2858    
2859  C<< my $id = $sprout->PropertyID($propName, $propValue); >>      my $id = $sprout->PropertyID($propName, $propValue);
2860    
2861  Return the ID of the specified property name and value pair, if the  Return the ID of the specified property name and value pair, if the
2862  pair exists. Only a small subset of the FIG attributes are stored as  pair exists. Only a small subset of the FIG attributes are stored as
# Line 2611  Line 2893 
2893    
2894  =head3 MergedAnnotations  =head3 MergedAnnotations
2895    
2896  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2897    
2898  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2899  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2660  Line 2942 
2942    
2943  =head3 RoleNeighbors  =head3 RoleNeighbors
2944    
2945  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2946    
2947  Returns a list of the roles that occur in the same diagram as the specified role. Because  Returns a list of the roles that occur in the same diagram as the specified role. Because
2948  diagrams and roles are in a many-to-many relationship with each other, the list is  diagrams and roles are in a many-to-many relationship with each other, the list is
# Line 2703  Line 2985 
2985    
2986  =head3 FeatureLinks  =head3 FeatureLinks
2987    
2988  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
2989    
2990  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are  Return a list of the web hyperlinks associated with a feature. The web hyperlinks are
2991  to external websites describing either the feature itself or the organism containing it  to external websites describing either the feature itself or the organism containing it
# Line 2734  Line 3016 
3016    
3017  =head3 SubsystemsOf  =head3 SubsystemsOf
3018    
3019  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3020    
3021  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
3022  to the roles the feature performs.  to the roles the feature performs.
# Line 2782  Line 3064 
3064    
3065  =head3 SubsystemList  =head3 SubsystemList
3066    
3067  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3068    
3069  Return a list containing the names of the subsystems in which the specified  Return a list containing the names of the subsystems in which the specified
3070  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2805  Line 3087 
3087  sub SubsystemList {  sub SubsystemList {
3088      # Get the parameters.      # Get the parameters.
3089      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3090      # Get the list of names.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3091      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",      # the Sprout database!
3092        my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3093                                  [$featureID], 'HasRoleInSubsystem(to-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3094      # Return the result, sorted.      # Return the result, sorted.
3095      return sort @retVal;      return sort @retVal;
# Line 2814  Line 3097 
3097    
3098  =head3 GenomeSubsystemData  =head3 GenomeSubsystemData
3099    
3100  C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3101    
3102  Return a hash mapping genome features to their subsystem roles.  Return a hash mapping genome features to their subsystem roles.
3103    
# Line 2839  Line 3122 
3122      # Declare the return variable.      # Declare the return variable.
3123      my %retVal = ();      my %retVal = ();
3124      # Get a list of the genome features that participate in subsystems. For each      # Get a list of the genome features that participate in subsystems. For each
3125      # feature we get its spreadsheet cells and the corresponding roles.      # feature we get its subsystem ID and the corresponding roles.
3126      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3127                               "HasFeature(from-link) = ?", [$genomeID],                               "HasFeature(from-link) = ?", [$genomeID],
3128                               ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3129      # Now we get a list of the spreadsheet cells and their associated subsystems. Subsystems      # Now we get a list of valid subsystems. These are the subsystems connected to the genome with
3130      # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the      # a non-negative variant code.
3131      # list. We use it at the beginning to get all the spreadsheet cells for the genome and      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3132      # again at the end to filter out participation in subsystems with a negative variant code.                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3133      my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],                                                  [$genomeID], 'ParticipatesIn(to-link)');
3134                                   "IsGenomeOf(from-link) = ? AND ParticipatesIn(variant-code) >= 0 AND ParticipatesIn(from-link) = ?",      # We loop through @roleData to build the hash.
                                  [$genomeID, $genomeID], ['HasSSCell(to-link)', 'HasSSCell(from-link)']);  
     # Now "@roleData" lists the spreadsheet cell and role for each of the genome's features.  
     # "@cellData" lists the subsystem name for each of the genome's spreadsheet cells. We  
     # link these two lists together to create the result. First, we want a hash mapping  
     # spreadsheet cells to subsystem names.  
     my %subHash = map { $_->[0] => $_->[1] } @cellData;  
     # We loop through @cellData to build the hash.  
3135      for my $roleEntry (@roleData) {      for my $roleEntry (@roleData) {
3136          # Get the data for this feature and cell.          # Get the data for this feature and cell.
3137          my ($fid, $cellID, $role) = @{$roleEntry};          my ($fid, $role, $subsys) = @{$roleEntry};
3138          # Check for a subsystem name.          Trace("Subsystem for $fid is $subsys.") if T(4);
3139          my $subsys = $subHash{$cellID};          # Check the subsystem;
3140          if ($subsys) {          if ($subs{$subsys}) {
3141                Trace("Subsystem found.") if T(4);
3142              # Insure this feature has an entry in the return hash.              # Insure this feature has an entry in the return hash.
3143              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3144              # Merge in this new data.              # Merge in this new data.
# Line 2874  Line 3151 
3151    
3152  =head3 RelatedFeatures  =head3 RelatedFeatures
3153    
3154  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3155    
3156  Return a list of the features which are bi-directional best hits of the specified feature and  Return a list of the features which are bi-directional best hits of the specified feature and
3157  have been assigned the specified function by the specified user. If no such features exists,  have been assigned the specified function by the specified user. If no such features exists,
# Line 2925  Line 3202 
3202    
3203  =head3 TaxonomySort  =head3 TaxonomySort
3204    
3205  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3206    
3207  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3208  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 2960  Line 3237 
3237          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3238                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3239          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3240          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3241      }      }
3242      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3243      my @retVal = ();      my @retVal = ();
# Line 2973  Line 3250 
3250    
3251  =head3 Protein  =head3 Protein
3252    
3253  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3254    
3255  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3256    
# Line 3059  Line 3336 
3336    
3337  =head3 LoadInfo  =head3 LoadInfo
3338    
3339  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3340    
3341  Return the name of the directory from which data is to be loaded and a list of the relation  Return the name of the directory from which data is to be loaded and a list of the relation
3342  names. This information is useful when trying to analyze what needs to be put where in order  names. This information is useful when trying to analyze what needs to be put where in order
# Line 3080  Line 3357 
3357    
3358  =head3 BBHMatrix  =head3 BBHMatrix
3359    
3360  C<< my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets); >>      my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3361    
3362  Find all the bidirectional best hits for the features of a genome in a  Find all the bidirectional best hits for the features of a genome in a
3363  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3134  Line 3411 
3411    
3412  =head3 SimMatrix  =head3 SimMatrix
3413    
3414  C<< my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets); >>      my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3415    
3416  Find all the similarities for the features of a genome in a  Find all the similarities for the features of a genome in a
3417  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3204  Line 3481 
3481    
3482  =head3 LowBBHs  =head3 LowBBHs
3483    
3484  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3485    
3486  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3487  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3248  Line 3525 
3525    
3526  =head3 Sims  =head3 Sims
3527    
3528  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3529    
3530  Get a list of similarities for a specified feature. Similarity information is not kept in the  Get a list of similarities for a specified feature. Similarity information is not kept in the
3531  Sprout database; rather, they are retrieved from a network server. The similarities are  Sprout database; rather, they are retrieved from a network server. The similarities are
# Line 3314  Line 3591 
3591    
3592  =head3 IsAllGenomes  =head3 IsAllGenomes
3593    
3594  C<< my $flag = $sprout->IsAllGenomes(\@list, \@checkList); >>      my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3595    
3596  Return TRUE if all genomes in the second list are represented in the first list at  Return TRUE if all genomes in the second list are represented in the first list at
3597  least one. Otherwise, return FALSE. If the second list is omitted, the first list is  least one. Otherwise, return FALSE. If the second list is omitted, the first list is
# Line 3363  Line 3640 
3640    
3641  =head3 GetGroups  =head3 GetGroups
3642    
3643  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3644    
3645  Return a hash mapping each group to the IDs of the genomes in the group.  Return a hash mapping each group to the IDs of the genomes in the group.
3646  A list of groups may be specified, in which case only those groups will be  A list of groups may be specified, in which case only those groups will be
# Line 3395  Line 3672 
3672                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3673          # Loop through the genomes found.          # Loop through the genomes found.
3674          for my $genome (@genomes) {          for my $genome (@genomes) {
3675              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3676              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3677              my $genomeID = shift @groups;              push @{$retVal{$group}}, $genomeID;
             # Loop through the groups, adding the genome ID to each group's  
             # list.  
             for my $group (@groups) {  
                 Tracer::AddToListMap(\%retVal, $group, $genomeID);  
             }  
3678          }          }
3679      }      }
3680      # Return the hash we just built.      # Return the hash we just built.
# Line 3411  Line 3683 
3683    
3684  =head3 MyGenomes  =head3 MyGenomes
3685    
3686  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3687    
3688  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3689    
# Line 3443  Line 3715 
3715    
3716  =head3 LoadFileName  =head3 LoadFileName
3717    
3718  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3719    
3720  Return the name of the load file for the specified table in the specified data  Return the name of the load file for the specified table in the specified data
3721  directory.  directory.
# Line 3484  Line 3756 
3756    
3757  =head3 DeleteGenome  =head3 DeleteGenome
3758    
3759  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3760    
3761  Delete a genome from the database.  Delete a genome from the database.
3762    
# Line 3520  Line 3792 
3792    
3793  =head3 Fix  =head3 Fix
3794    
3795  C<< my %fixedHash = Sprout::Fix(%groupHash); >>      my %fixedHash = $sprout->Fix(%groupHash);
3796    
3797  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3798  Groups with the same primary name will be combined. The primary name is the  The groups will be combined into the appropriate super-groups.
 first capitalized word in the group name.  
3799    
3800  =over 4  =over 4
3801    
# Line 3542  Line 3813 
3813    
3814  sub Fix {  sub Fix {
3815      # Get the parameters.      # Get the parameters.
3816      my (%groupHash) = @_;      my ($self, %groupHash) = @_;
3817      # Create the result hash.      # Create the result hash.
3818      my %retVal = ();      my %retVal = ();
3819      # Copy over the genomes.      # Copy over the genomes.
3820      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3821          # Make a safety copy of the group ID.          # Get the super-group name.
3822          my $realGroupID = $groupID;          my $realGroupID = $self->SuperGroup($groupID);
3823          # Yank the primary name.          # Append this group's genomes into the result hash
3824          if ($groupID =~ /([A-Z]\w+)/) {          # using the super-group name.
3825              $realGroupID = $1;          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
         }  
         # Append this group's genomes into the result hash.  
         Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});  
3826      }      }
3827      # Return the result hash.      # Return the result hash.
3828      return %retVal;      return %retVal;
# Line 3562  Line 3830 
3830    
3831  =head3 GroupPageName  =head3 GroupPageName
3832    
3833  C<< my $name = $sprout->GroupPageName($group); >>      my $name = $sprout->GroupPageName($group);
3834    
3835  Return the name of the page for the specified NMPDR group.  Return the name of the page for the specified NMPDR group.
3836    
# Line 3584  Line 3852 
3852  sub GroupPageName {  sub GroupPageName {
3853      # Get the parameters.      # Get the parameters.
3854      my ($self, $group) = @_;      my ($self, $group) = @_;
     # Declare the return variable.  
     my $retVal;  
3855      # Check for the group file data.      # Check for the group file data.
3856      if (! defined $self->{groupHash}) {      my %superTable = $self->CheckGroupFile();
         # Read the group file.  
         my %groupData = Sprout::ReadGroupFile($self->{_options}->{dataDir} . "/groups.tbl");  
         # Store it in our object.  
         $self->{groupHash} = \%groupData;  
     }  
3857      # Compute the real group name.      # Compute the real group name.
3858      my $realGroup = $group;      my $realGroup = $self->SuperGroup($group);
3859      if ($group =~ /([A-Z]\w+)/) {      # Get the associated page name.
3860          $realGroup = $1;      my $retVal = "../content/$superTable{$realGroup}->{page}";
     }  
     # Return the page name.  
     $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1];  
3861      # Return the result.      # Return the result.
3862      return $retVal;      return $retVal;
3863  }  }
3864    
 =head3 ReadGroupFile  
   
 C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>  
   
 Read in the data from the specified group file. The group file contains information  
 about each of the NMPDR groups.  
   
 =over 4  
   
 =item name  
   
 Name of the group.  
   
 =item page  
3865    
3866  Name of the group's page on the web site (e.g. C<campy.php> for  =head3 AddProperty
 Campylobacter)  
   
 =item genus  
3867    
3868  Genus of the group      $sprout->AddProperty($featureID, $key, @values);
3869    
3870  =item species  Add a new attribute value (Property) to a feature.
   
 Species of the group, or an empty string if the group is for an entire  
 genus. If the group contains more than one species, the species names  
 should be separated by commas.  
3871    
3872  =back  =over 4
3873    
3874  The parameters to this method are as follows  =item peg
3875    
3876  =over 4  ID of the feature to which the attribute is to be added.
3877    
3878  =item groupFile  =item key
3879    
3880  Name of the file containing the group data.  Name of the attribute (key).
3881    
3882  =item RETURN  =item values
3883    
3884  Returns a hash keyed on group name. The value of each hash  Values of the attribute.
3885    
3886  =back  =back
3887    
3888  =cut  =cut
3889    #: Return Type ;
3890  sub ReadGroupFile {  sub AddProperty {
3891      # Get the parameters.      # Get the parameters.
3892      my ($groupFileName) = @_;      my ($self, $featureID, $key, @values) = @_;
3893      # Declare the return variable.      # Add the property using the attached attributes object.
3894      my %retVal;      $self->{_ca}->AddAttribute($featureID, $key, @values);
     # Read the group file.  
     my @groupLines = Tracer::GetFile($groupFileName);  
     for my $groupLine (@groupLines) {  
         my ($name, $page, $genus, $species) = split(/\t/, $groupLine);  
         $retVal{$name} = [$page, $genus, $species];  
     }  
     # Return the result.  
     return %retVal;  
3895  }  }
3896    
3897  =head3 AddProperty  =head3 CheckGroupFile
3898    
3899  C<< my  = $sprout->AddProperty($featureID, $key, @values); >>      my %groupData = $sprout->CheckGroupFile();
3900    
3901  Add a new attribute value (Property) to a feature.  Get the group file hash. The group file hash describes the relationship
3902    between a group and the super-group to which it belongs for purposes of
3903    display. The super-group name is computed from the first capitalized word
3904    in the actual group name. For each super-group, the group file contains
3905    the page name and a list of the species expected to be in the group.
3906    Each species is specified by a genus and a species name. A species name
3907    of C<0> implies an entire genus.
3908    
3909    This method returns a hash from super-group names to a hash reference. Each
3910    resulting hash reference contains the following fields.
3911    
3912  =over 4  =over 4
3913    
3914  =item peg  =item page
3915    
3916  ID of the feature to which the attribute is to be added.  The super-group's web page in the NMPDR.
3917    
3918  =item key  =item contents
3919    
3920  Name of the attribute (key).  A list of 2-tuples, each containing a genus name followed by a species name
3921    (or 0, indicating all species). This list indicates which organisms belong
3922  =item values  in the super-group.
   
 Values of the attribute.  
3923    
3924  =back  =back
3925    
3926  =cut  =cut
3927  #: Return Type ;  
3928  sub AddProperty {  sub CheckGroupFile {
3929      # Get the parameters.      # Get the parameters.
3930      my ($self, $featureID, $key, @values) = @_;      my ($self) = @_;
3931      # Add the property using the attached attributes object.      # Check to see if we already have this hash.
3932      $self->{_ca}->AddAttribute($featureID, $key, @values);      if (! defined $self->{groupHash}) {
3933            # We don't, so we need to read it in.
3934            my %groupHash;
3935            # Read the group file.
3936            my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3937            # Loop through the list of sort-of groups.
3938            for my $groupLine (@groupLines) {
3939                my ($name, $page, @contents) = split /\t/, $groupLine;
3940                $groupHash{$name} = { page => $page,
3941                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3942                                    };
3943            }
3944            # Save the hash.
3945            $self->{groupHash} = \%groupHash;
3946        }
3947        # Return the result.
3948        return %{$self->{groupHash}};
3949  }  }
3950    
3951  =head2 Virtual Methods  =head2 Virtual Methods
3952    
3953  =head3 CleanKeywords  =head3 CleanKeywords
3954    
3955  C<< my $cleanedString = $sprout->CleanKeywords($searchExpression); >>      my $cleanedString = $sprout->CleanKeywords($searchExpression);
3956    
3957  Clean up a search expression or keyword list. This involves converting the periods  Clean up a search expression or keyword list. This involves converting the periods
3958  in EC numbers to underscores, converting non-leading minus signs to underscores,  in EC numbers to underscores, converting non-leading minus signs to underscores,
# Line 3727  Line 3979 
3979      # Get the parameters.      # Get the parameters.
3980      my ($self, $searchExpression) = @_;      my ($self, $searchExpression) = @_;
3981      # Perform the standard cleanup.      # Perform the standard cleanup.
3982      my $retVal = $self->ERDB::CleanKeywords($searchExpression);      my $words = $self->ERDB::CleanKeywords($searchExpression);
3983      # Fix the periods in EC and TC numbers.      # Fix the periods in EC and TC numbers.
3984      $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;      $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
3985      # Fix non-trailing periods.      # Fix non-trailing periods.
3986      $retVal =~ s/\.(\w)/_$1/g;      $words =~ s/\.(\w)/_$1/g;
3987      # Fix non-leading minus signs.      # Fix non-leading minus signs.
3988      $retVal =~ s/(\w)[\-]/$1_/g;      $words =~ s/(\w)[\-]/$1_/g;
3989      # Fix the vertical bars and colons      # Fix the vertical bars and colons
3990      $retVal =~ s/(\w)[|:](\w)/$1'$2/g;      $words =~ s/(\w)[|:](\w)/$1'$2/g;
3991        # Now split up the list so that each keyword is in its own string. We keep the delimiters
3992        # because they may contain boolean expression data.
3993        my @words = split /([^A-Za-z'0-9_]+)/, $words;
3994        # We'll convert the stemmable words into stems and re-assemble the result.
3995        my $retVal = "";
3996        for my $word (@words) {
3997            my $stem = $self->Stem($word);
3998            if (defined $stem) {
3999                $retVal .= $stem;
4000            } else {
4001                $retVal .= $word;
4002            }
4003        }
4004        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4005      # Return the result.      # Return the result.
4006      return $retVal;      return $retVal;
4007  }  }
# Line 3750  Line 4016 
4016    
4017  A functional assignment is always of the form  A functional assignment is always of the form
4018    
4019      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4020        ZZZZ
4021    
4022  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,  where I<YYYY> is the B<user>, and I<ZZZZ> is the actual functional role. In most cases,
4023  the user and the assigning user (from MadeAnnotation) will be the same, but that is  the user and the assigning user (from MadeAnnotation) will be the same, but that is
# Line 3805  Line 4072 
4072    
4073  =head3 _CheckFeature  =head3 _CheckFeature
4074    
4075  C<< my $flag = $sprout->_CheckFeature($fid); >>      my $flag = $sprout->_CheckFeature($fid);
4076    
4077  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4078    
# Line 3864  Line 4131 
4131  }  }
4132    
4133    
4134    =head3 Hint
4135    
4136        my $htmlText = SearchHelper::Hint($wikiPage, $hintText);
4137    
4138    Return the HTML for a small question mark that displays the specified hint text when it is clicked.
4139    This HTML can be put in forms to provide a useful hinting mechanism.
4140    
4141    =over 4
4142    
4143    =item wikiPage
4144    
4145    Name of the wiki page to be popped up when the hint mark is clicked.
4146    
4147    =item hintText
4148    
4149    Text to display for the hint. It is raw html, but may not contain any double quotes.
4150    
4151    =item RETURN
4152    
4153    Returns the html for the hint facility. The resulting html shows a small button-like thing that
4154    uses the standard FIG popup technology.
4155    
4156    =back
4157    
4158    =cut
4159    
4160    sub Hint {
4161        # Get the parameters.
4162        my ($wikiPage, $hintText) = @_;
4163        # Escape the single quotes in the hint text.
4164        my $quotedText = $hintText;
4165        $quotedText =~ s/'/\\'/g;
4166        # Convert the wiki page name to a URL.
4167        my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4168        $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";
4169        # Compute the mouseover script.
4170        my $mouseOver = "doTooltip(this, '$quotedText')";
4171        # Create the html.
4172        my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";
4173        # Return it.
4174        return $retVal;
4175    }
4176    
4177  1;  1;

Legend:
Removed from v.1.101  
changed lines
  Added in v.1.118

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3