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

Diff of /Sprout/Sprout.pm

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

revision 1.105, Wed Jan 30 22:14:02 2008 UTC revision 1.122, Mon Jan 19 21:46:21 2009 UTC
# Line 4  Line 4 
4      use strict;      use strict;
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use ERDBQuery;
8      use ERDBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
# Line 14  Line 14 
14      use BasicLocation;      use BasicLocation;
15      use CustomAttributes;      use CustomAttributes;
16      use RemoteCustomAttributes;      use RemoteCustomAttributes;
17        use CGI qw(-nosticky);
18        use WikiTools;
19        use BioWords;
20      use base qw(ERDB);      use base qw(ERDB);
21    
22  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
# Line 38  Line 41 
41    
42  =cut  =cut
43    
 #: Constructor SFXlate->new_sprout_only();  
   
44  =head2 Public Methods  =head2 Public Methods
45    
46  =head3 new  =head3 new
# Line 54  Line 55 
55    
56  =item dbName  =item dbName
57    
58  Name of the database.  Name of the database. If omitted, the default Sprout database name is used.
59    
60  =item options  =item options
61    
# Line 88  Line 89 
89    
90      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });      my $sprout = Sprout->new('Sprout', { userData => 'fig/admin', dataDir => '/usr/fig/SproutData' });
91    
92    In order to work properly with [[ERDBGeneratorPl]], the constructor has an alternate
93    form.
94    
95        my $sprout = Sprout->new(dbd => $filename);
96    
97    Where I<$fileName> is the name of the DBD file. This enables us to specify an alternate
98    DBD for the loader, which is important when the database format changes.
99    
100  =cut  =cut
101    
102  sub new {  sub new {
103      # Get the parameters.      # Get the parameters.
104      my ($class, $dbName, $options) = @_;      my ($class, $dbName, $options) = @_;
105        # Check for the alternate signature, and default the database name if it is missing.
106        if ($dbName eq 'dbd') {
107            $dbName = $FIG_Config::sproutDB;
108            $options = { xmlFileName => $options };
109        } elsif (! defined $dbName) {
110            $dbName = $FIG_Config::sproutDB;
111        } elsif (ref $dbName eq 'HASH') {
112            $options = $dbName;
113            $dbName = $FIG_Config::sproutDB;
114        }
115      # Compute the DBD directory.      # Compute the DBD directory.
116      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :      my $dbd_dir = (defined($FIG_Config::dbd_dir) ? $FIG_Config::dbd_dir :
117                                                    $FIG_Config::fig );                                                    $FIG_Config::fig );
# Line 105  Line 124 
124                                                          # data file directory                                                          # data file directory
125                         xmlFileName  => "$dbd_dir/SproutDBD.xml",                         xmlFileName  => "$dbd_dir/SproutDBD.xml",
126                                                          # database definition file name                                                          # database definition file name
127                         userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",                         userData     => "$FIG_Config::sproutUser/$FIG_Config::sproutPass",
128                                                          # user name and password                                                          # user name and password
129                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::sproutPort,
130                                                          # database connection port                                                          # database connection port
131                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::sproutSock,
132                         host         => $FIG_Config::sprout_host,                         host         => $FIG_Config::sprout_host,
133                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
134                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
# Line 135  Line 154 
154      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
155      # Set up space for the group file data.      # Set up space for the group file data.
156      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
157      # Set up space for the genome hash. We use this to identify NMPDR genomes.      # Set up space for the genome hash. We use this to identify NMPDR genomes
158      $retVal->{genomeHash} = undef;      # and remember genome data.
159      # Connect to the attributes.      $retVal->{genomeHash} = {};
160        $retVal->{genomeHashFilled} = 0;
161        # Remember the data directory name.
162        $retVal->{dataDir} = $dataDir;
163        # Return it.
164        return $retVal;
165    }
166    
167    =head3 ca
168    
169        my $ca = $sprout->ca():;
170    
171    Return the [[CustomAttributesPm]] object for retrieving object
172    properties.
173    
174    =cut
175    
176    sub ca {
177        # Get the parameters.
178        my ($self) = @_;
179        # Do we already have an attribute object?
180        my $retVal = $self->{_ca};
181        if (! defined $retVal) {
182            # No, create one. How we do it depends on the configuration.
183      if ($FIG_Config::attrURL) {      if ($FIG_Config::attrURL) {
184          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);          Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
185          $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);              $retVal = RemoteCustomAttributes->new($FIG_Config::attrURL);
186      } elsif ($FIG_Config::attrDbName) {      } elsif ($FIG_Config::attrDbName) {
187          Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);          Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
188          my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));          my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
189          $retVal->{_ca} = CustomAttributes->new(user => $user);              $retVal = CustomAttributes->new(user => $user);
190      }      }
191      # Return it.          # Save it for next time.
192            $self->{_ca} = $retVal;
193        }
194        # Return the result.
195        return $retVal;
196    }
197    
198    =head3 CoreGenomes
199    
200        my @genomes = $sprout->CoreGenomes($scope);
201    
202    Return the IDs of NMPDR genomes in the specified scope.
203    
204    =over 4
205    
206    =item scope
207    
208    Scope of the desired genomes. C<core> covers the original core genomes,
209    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
210    genomes in the system.
211    
212    =item RETURN
213    
214    Returns a list of the IDs for the genomes in the specified scope.
215    
216    =back
217    
218    =cut
219    
220    sub CoreGenomes {
221        # Get the parameters.
222        my ($self, $scope) = @_;
223        # Declare the return variable.
224        my @retVal = ();
225        # If we want all genomes, then this is easy.
226        if ($scope eq 'all') {
227            @retVal = $self->Genomes();
228        } else {
229            # Here we're dealing with groups. Get the hash of all the
230            # genome groups.
231            my %groups = $self->GetGroups();
232            # Loop through the groups, keeping the ones that we want.
233            for my $group (keys %groups) {
234                # Decide if we want to keep this group.
235                my $keepGroup = 0;
236                if ($scope eq 'nmpdr') {
237                    # NMPDR mode: keep all groups.
238                    $keepGroup = 1;
239                } elsif ($scope eq 'core') {
240                    # CORE mode. Only keep real core groups.
241                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
242                        $keepGroup = 1;
243                    }
244                }
245                # Add this group if we're keeping it.
246                if ($keepGroup) {
247                    push @retVal, @{$groups{$group}};
248                }
249            }
250        }
251        # Return the result.
252        return @retVal;
253    }
254    
255    =head3 SuperGroup
256    
257        my $superGroup = $sprout->SuperGroup($groupName);
258    
259    Return the name of the super-group containing the specified NMPDR genome
260    group. If no appropriate super-group can be found, an error will be
261    thrown.
262    
263    =over 4
264    
265    =item groupName
266    
267    Name of the group whose super-group is desired.
268    
269    =item RETURN
270    
271    Returns the name of the super-group containing the incoming group.
272    
273    =back
274    
275    =cut
276    
277    sub SuperGroup {
278        # Get the parameters.
279        my ($self, $groupName) = @_;
280        # Declare the return variable.
281        my $retVal;
282        # Get the group hash.
283        my %groupHash = $self->CheckGroupFile();
284        # Find the super-group genus.
285        $groupName =~ /([A-Z]\w+)/;
286        my $nameThing = $1;
287        # See if it's directly in the group hash.
288        if (exists $groupHash{$nameThing}) {
289            # Yes, then it's our result.
290            $retVal = $nameThing;
291        } else {
292            # No, so we have to search.
293            for my $superGroup (keys %groupHash) {
294                # Get this super-group's item list.
295                my $list = $groupHash{$superGroup}->{contents};
296                # Search it.
297                if (grep { $_->[0] eq $nameThing } @{$list}) {
298                    $retVal = $superGroup;
299                }
300            }
301            # Make sure we found something.
302            if (! $retVal) {
303                Confess("No super-group found for \"$groupName\".");
304            }
305        }
306        # Return the result.
307      return $retVal;      return $retVal;
308  }  }
309    
# Line 196  Line 353 
353  The files are loaded based on the presumption that each line of the file is a record in the  The files are loaded based on the presumption that each line of the file is a record in the
354  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside  relation, and the individual fields are delimited by tabs. Tab and new-line characters inside
355  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must  fields must be represented by the escape sequences C<\t> and C<\n>, respectively. The fields must
356  be presented in the order given in the relation tables produced by the L</ShowMetaData> method.  be presented in the order given in the relation tables produced by the database documentation.
357    
358  =over 4  =over 4
359    
# Line 353  Line 510 
510      return $retVal;      return $retVal;
511  }  }
512    
513  =head3 GeneMenu  =head3 GenomeMenu
514    
515        my $html = $sprout->GenomeMenu(%options);
516    
517    Generate a genome selection control with the specified name and options.
518    This control is almost but not quite the same as the genome control in the
519    B<SearchHelper> class. Eventually, the two will be combined.
520    
521      my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected);  =over 4
522    
523    =item options
524    
525    Optional parameters for the control (see below).
526    
527    =item RETURN
528    
529    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
530    
531  Return an HTML select menu of genomes. Each genome will be an option in the menu,  =back
532  and will be displayed by name with the ID and a contig count attached. The selection  
533  value will be the genome ID. The genomes will be sorted by genus/species name.  The valid options are as follows.
534    
535  =over 4  =over 4
536    
537  =item attributes  =item name
538    
539  Reference to a hash mapping attributes to values for the SELECT tag generated.  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
540    Terrible things will happen if you have two controls with the same name on the same page.
541    
542  =item filterString  =item filter
543    
544  A filter string for use in selecting the genomes. The filter string must conform  If specified, a filter for the list of genomes to display. The filter should be in the form of a
545  to the rules for the C<< ERDB->Get >> method.  list reference, a string, or a hash reference. If it is a list reference, the first element
546    of the list should be the filter string, and the remaining elements the filter parameters. If it is a
547    string, it will be split into a list at each included tab. If it is a hash reference, it should be
548    a hash that maps genomes which should be included to a TRUE value.
549    
550  =item params  =item multiSelect
551    
552  Reference to a list of values to be substituted in for the parameter marks in  If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
 the filter string.  
553    
554  =item selected (optional)  =item size
555    
556  ID of the genome to be initially selected.  Number of rows to display in the control. The default is C<10>
557    
558  =item fast (optional)  =item id
559    
560  If specified and TRUE, the contig counts will be omitted to improve performance.  ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
561    unless this ID is unique.
562    
563  =item RETURN  =item selected
564    
565  Returns an HTML select menu with the specified genomes as selectable options.  A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
566    default is none.
567    
568    =item class
569    
570    If specified, a style class to assign to the genome control.
571    
572  =back  =back
573    
574  =cut  =cut
575    
576  sub GeneMenu {  sub GenomeMenu {
577      # Get the parameters.      # Get the parameters.
578      my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;      my ($self, %options) = @_;
579      my $slowMode = ! $fast;      # Get the control's name and ID.
580      # Default to nothing selected. This prevents an execution warning if "$selected"      my $menuName = $options{name} || $options{id} || 'myGenomeControl';
581      # is undefined.      my $menuID = $options{id} || $menuName;
582      $selected = "" unless defined $selected;      Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
583      Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);      # Compute the IDs for the status display.
584      # Start the menu.      my $divID = "${menuID}_status";
585      my $retVal = "<select " .      my $urlID = "${menuID}_url";
586          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      # Compute the code to show selected genomes in the status area.
587          ">\n";      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', $FIG_Config::genome_control_cap)";
588      # Get the genomes.      # Check for single-select or multi-select.
589      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',      my $multiSelect = $options{multiSelect} || 0;
590                                                                       'Genome(genus)',      # Get the style data.
591                                                                       'Genome(species)',      my $class = $options{class} || '';
592                                                                       'Genome(unique-characterization)']);      # Get the list of pre-selected items.
593      # Sort them by name.      my $selections = $options{selected} || [];
594      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;      if (ref $selections ne 'ARRAY') {
595      # Loop through the genomes, creating the option tags.          $selections = [ split /\s*,\s*/, $selections ];
596      for my $genomeData (@sorted) {      }
597          # Get the data for this genome.      my %selected = map { $_ => 1 } @{$selections};
598          my ($genomeID, $genus, $species, $strain) = @{$genomeData};      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
599          # Get the contig count.      # string, a hash reference, or a list reference.
600          my $contigInfo = "";      my ($filterHash, $filterString);
601          if ($slowMode) {      my $filterParms = $options{filter} || "";
602              my $count = $self->ContigCount($genomeID);      if (ref $filterParms eq 'HASH') {
603              my $counting = ($count == 1 ? "contig" : "contigs");          $filterHash = $filterParms;
604              $contigInfo = "[$count $counting]";          $filterParms = [];
605          }          $filterString = "";
606          # Find out if we're selected.      } else {
607          my $selectOption = ($selected eq $genomeID ? " selected" : "");          if (! ref $filterParms) {
608          # Build the option tag.              $filterParms = [split /\t|\\t/, $filterParms];
609          $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";          }
610            $filterString = shift @{$filterParms};
611        }
612        # Check for possible subsystem filtering. If there is one, we will tack the
613        # relationship onto the object name list.
614        my @objectNames = qw(Genome);
615        if ($filterString =~ /ParticipatesIn\(/) {
616            push @objectNames, 'ParticipatesIn';
617        }
618        # Get a list of all the genomes in group order. In fact, we only need them ordered
619        # by name (genus,species,strain), but putting primary-group in front enables us to
620        # take advantage of an existing index.
621        my @genomeList = $self->GetAll(\@objectNames, "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
622                                       $filterParms,
623                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
624        # Apply the hash filter (if any).
625        if (defined $filterHash) {
626            @genomeList = grep { $filterHash->{$_->[1]} } @genomeList;
627        }
628        # Create a hash to organize the genomes by group. Each group will contain a list of
629        # 2-tuples, the first element being the genome ID and the second being the genome
630        # name.
631        my %gHash = ();
632        for my $genome (@genomeList) {
633            # Get the genome data.
634            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
635            # Compute its name. This is the genus, species, strain (if any), and the contig count.
636            my $name = "$genus $species ";
637            $name .= "$strain " if $strain;
638            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
639            # Now we get the domain. The domain tells us the display style of the organism.
640            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
641            # Now compute the display group. This is normally the primary group, but if the
642            # organism is supporting, we blank it out.
643            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
644            # Push the genome into the group's list. Note that we use the real group
645            # name for the hash key here, not the display group name.
646            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
647        }
648        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
649        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
650        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
651        # that aren't "other". At some point, we will want to make this less complicated.
652        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
653                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
654        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
655        # Remember the number of NMPDR groups.
656        my $nmpdrGroupCount = scalar @groups;
657        # Are there any supporting genomes?
658        if (exists $gHash{$FIG_Config::otherGroup}) {
659            # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
660            # of the domains found.
661            my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
662            my @domains = ();
663            for my $genomeData (@otherGenomes) {
664                my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
665                if (exists $gHash{$domain}) {
666                    push @{$gHash{$domain}}, $genomeData;
667                } else {
668                    $gHash{$domain} = [$genomeData];
669                    push @domains, $domain;
670                }
671            }
672            # Add the domain groups at the end of the main group list. The main group list will now
673            # contain all the categories we need to display the genomes.
674            push @groups, sort @domains;
675            # Delete the supporting group.
676            delete $gHash{$FIG_Config::otherGroup};
677        }
678        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
679        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
680        # and use that to make the selections.
681        my $nmpdrCount = 0;
682        # Create the type counters.
683        my $groupCount = 1;
684        # Get the number of rows to display.
685        my $rows = $options{size} || 10;
686        # If we're multi-row, create an onChange event.
687        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
688        # Set up the multiple-select flag.
689        my $multipleTag = ($multiSelect ? " multiple" : "" );
690        # Set up the style class.
691        my $classTag = ($class ? " class=\"$class\"" : "" );
692        # Create the SELECT tag and stuff it into the output array.
693        my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
694        # Loop through the groups.
695        for my $group (@groups) {
696            # Get the genomes in the group.
697            for my $genome (@{$gHash{$group}}) {
698                # If this is an NMPDR organism, we add an extra style and count it.
699                my $nmpdrStyle = "";
700                if ($nmpdrGroupCount > 0) {
701                    $nmpdrCount++;
702                    $nmpdrStyle = " Core";
703                }
704                # Get the organism ID, name, contig count, and domain.
705                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
706                # See if we're pre-selected.
707                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
708                # Compute the display name.
709                my $nameString = "$name ($genomeID$contigCount)";
710                # Generate the option tag.
711                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
712                push @lines, "    $optionTag";
713            }
714            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
715            # groups.
716            $nmpdrGroupCount--;
717      }      }
718      # Close the SELECT tag.      # Close the SELECT tag.
719      $retVal .= "</select>\n";      push @lines, "</SELECT>";
720        if ($rows > 1) {
721            # We're in a non-compact mode, so we need to add some selection helpers. First is
722            # the search box. This allows the user to type text and change which genomes are
723            # displayed. For multiple-select mode, we include a button that selects the displayed
724            # genes. For single-select mode, we use a plain label instead.
725            my $searchThingName = "${menuID}_SearchThing";
726            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
727                                                 : "Show genomes containing");
728            push @lines, "<br />$searchThingLabel&nbsp;" .
729                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
730                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
731            # For multi-select mode, we also have buttons to set and clear selections.
732            if ($multiSelect) {
733                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll(getElementById('$menuID')); $showSelect\" />";
734                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll(getElementById('$menuID')); $showSelect\" />";
735                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome(getElementById('$menuID'), $nmpdrCount, true); $showSelect;\" />";
736            }
737            # Add a hidden field we can use to generate organism page hyperlinks.
738            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
739            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
740            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
741        }
742        # Assemble all the lines into a string.
743        my $retVal = join("\n", @lines, "");
744        # Return the result.
745        return $retVal;
746    }
747    
748    
749    =head3 Stem
750    
751        my $stem = $sprout->Stem($word);
752    
753    Return the stem of the specified word, or C<undef> if the word is not
754    stemmable. Note that even if the word is stemmable, the stem may be
755    the same as the original word.
756    
757    =over 4
758    
759    =item word
760    
761    Word to convert into a stem.
762    
763    =item RETURN
764    
765    Returns a stem of the word (which may be the word itself), or C<undef> if
766    the word is not stemmable.
767    
768    =back
769    
770    =cut
771    
772    sub Stem {
773        # Get the parameters.
774        my ($self, $word) = @_;
775        # Get the stemmer object.
776        my $stemmer = $self->{stemmer};
777        if (! defined $stemmer) {
778            # We don't have one pre-built, so we build and save it now.
779            $stemmer = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
780                                     stops => "$FIG_Config::sproutData/StopWords.txt",
781                                     cache => 0);
782            $self->{stemmer} = $stemmer;
783        }
784        # Try to stem the word.
785        my $retVal = $stemmer->Process($word);
786      # Return the result.      # Return the result.
787      return $retVal;      return $retVal;
788  }  }
789    
790    
791  =head3 Build  =head3 Build
792    
793      $sprout->Build();      $sprout->Build();
# Line 492  Line 846 
846  sub GenusSpecies {  sub GenusSpecies {
847      # Get the parameters.      # Get the parameters.
848      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
849      # Get the data for the specified genome.      # Declare the return value.
850      my @values = $self->GetEntityValues('Genome', $genomeID, ['Genome(genus)', 'Genome(species)',      my $retVal;
851                                                                'Genome(unique-characterization)']);      # Get the genome data.
852      # Format the result and return it.      my $genomeData = $self->_GenomeData($genomeID);
853      my $retVal = join(' ', @values);      # Only proceed if we found the genome.
854        if (defined $genomeData) {
855            $retVal = $genomeData->PrimaryValue('Genome(scientific-name)');
856        }
857        # Return it.
858      return $retVal;      return $retVal;
859  }  }
860    
# Line 571  Line 929 
929  =item RETURN  =item RETURN
930    
931  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
932  context and as a comma-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context. An empty list means the feature
933    wasn't found.
934    
935  =back  =back
936    
# Line 580  Line 939 
939  sub FeatureLocation {  sub FeatureLocation {
940      # Get the parameters.      # Get the parameters.
941      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
942        # Declare the return variable.
943        my @retVal = ();
944      # Get the feature record.      # Get the feature record.
945      my $object = $self->GetEntity('Feature', $featureID);      my $object = $self->GetEntity('Feature', $featureID);
946      Confess("Feature $featureID not found.") if ! defined($object);      # Only proceed if we found it.
947        if (defined $object) {
948      # Get the location string.      # Get the location string.
949      my $locString = $object->PrimaryValue('Feature(location-string)');      my $locString = $object->PrimaryValue('Feature(location-string)');
950      # Create the return list.      # Create the return list.
951      my @retVal = split /\s*,\s*/, $locString;          @retVal = split /\s*,\s*/, $locString;
952        }
953      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
954      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
955  }  }
# Line 829  Line 1192 
1192      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1193      # Declare the return variable.      # Declare the return variable.
1194      my $retVal = 0;      my $retVal = 0;
1195      # Get the genome's contig sequence lengths.      # Get the genome data.
1196      my @lens = $self->GetFlat(['HasContig', 'IsMadeUpOf'], 'HasContig(from-link) = ?',      my $genomeData = $self->_GenomeData($genomeID);
1197                         [$genomeID], 'IsMadeUpOf(len)');      # Only proceed if it exists.
1198      # Sum the lengths.      if (defined $genomeData) {
1199      map { $retVal += $_ } @lens;          $retVal = $genomeData->PrimaryValue('Genome(dna-size)');
1200        }
1201      # Return the result.      # Return the result.
1202      return $retVal;      return $retVal;
1203  }  }
# Line 1318  Line 1682 
1682  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG  the specified user and FIG are considered trusted. If the user ID is omitted, only FIG
1683  is trusted.  is trusted.
1684    
1685  If the feature is B<not> identified by a FIG ID, then the functional assignment  If the feature is B<not> identified by a FIG ID, then we search the aliases for it.
1686  information is taken from the B<ExternalAliasFunc> table. If the table does  If no matching alias is found, we return an undefined value.
 not contain an entry for the feature, an undefined value is returned.  
1687    
1688  =over 4  =over 4
1689    
# Line 1346  Line 1709 
1709      my ($self, $featureID, $userID) = @_;      my ($self, $featureID, $userID) = @_;
1710      # Declare the return value.      # Declare the return value.
1711      my $retVal;      my $retVal;
1712      # Determine the ID type.      # Find a FIG ID for this feature.
1713      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1714        # Only proceed if we have an ID.
1715        if ($fid) {
1716          # Here we have a FIG feature ID.          # Here we have a FIG feature ID.
1717          if (!$userID) {          if (!$userID) {
1718              # Use the primary assignment.              # Use the primary assignment.
1719              ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);              ($retVal) = $self->GetEntityValues('Feature', $fid, ['Feature(assignment)']);
1720          } else {          } else {
1721              # We must build the list of trusted users.              # We must build the list of trusted users.
1722              my %trusteeTable = ();              my %trusteeTable = ();
# Line 1377  Line 1742 
1742              # 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.
1743              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],              my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1744                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                     "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1745                                     [$featureID]);                                     [$fid]);
1746              my $timeSelected = 0;              my $timeSelected = 0;
1747              # Loop until we run out of annotations.              # Loop until we run out of annotations.
1748              while (my $annotation = $query->Fetch()) {              while (my $annotation = $query->Fetch()) {
# Line 1397  Line 1762 
1762                  }                  }
1763              }              }
1764          }          }
     } else {  
         # Here we have a non-FIG feature ID. In this case the user ID does not  
         # matter. We simply get the information from the External Alias Function  
         # table.  
         ($retVal) = $self->GetEntityValues('ExternalAliasFunc', $featureID, ['ExternalAliasFunc(func)']);  
1765      }      }
1766      # Return the assignment found.      # Return the assignment found.
1767      return $retVal;      return $retVal;
# Line 1420  Line 1780 
1780  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
1781  most features only have a small number of annotations.  most features only have a small number of annotations.
1782    
 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.  
   
1783  =over 4  =over 4
1784    
1785  =item featureID  =item featureID
# Line 1444  Line 1800 
1800      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1801      # Declare the return value.      # Declare the return value.
1802      my @retVal = ();      my @retVal = ();
1803      # Determine the ID type.      # Convert to a FIG ID.
1804      if ($featureID =~ m/^fig\|/) {      my ($fid) = $self->FeaturesByAlias($featureID);
1805        # Only proceed if we found one.
1806        if ($fid) {
1807          # 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
1808          # users.          # users.
1809          my %trusteeTable = ();          my %trusteeTable = ();
1810          # 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.
1811          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],          my $query = $self->Get(['IsTargetOfAnnotation', 'Annotation', 'MadeAnnotation'],
1812                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",                                 "IsTargetOfAnnotation(from-link) = ? ORDER BY Annotation(time) DESC",
1813                                 [$featureID]);                                 [$fid]);
1814          my $timeSelected = 0;          my $timeSelected = 0;
1815          # Loop until we run out of annotations.          # Loop until we run out of annotations.
1816          while (my $annotation = $query->Fetch()) {          while (my $annotation = $query->Fetch()) {
# Line 1467  Line 1825 
1825                  push @retVal, [$actualUser, $function];                  push @retVal, [$actualUser, $function];
1826              }              }
1827          }          }
     } 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;  
1828      }      }
1829      # Return the assignments found.      # Return the assignments found.
1830      return @retVal;      return @retVal;
# Line 1513  Line 1864 
1864      # Loop through the incoming features.      # Loop through the incoming features.
1865      for my $featureID (@{$featureList}) {      for my $featureID (@{$featureList}) {
1866          # Ask the server for the feature's best hit.          # Ask the server for the feature's best hit.
1867          my @bbhData = FIGRules::BBHData($featureID);          my $bbhData = FIGRules::BBHData($featureID);
1868          # Peel off the BBHs found.          # Peel off the BBHs found.
1869          my @found = ();          my @found = ();
1870          for my $bbh (@bbhData) {          for my $bbh (@$bbhData) {
1871              my $fid = $bbh->[0];              my $fid = $bbh->[0];
1872              my $bbGenome = $self->GenomeOf($fid);              my $bbGenome = $self->GenomeOf($fid);
1873              if ($bbGenome eq $genomeID) {              if ($bbGenome eq $genomeID) {
# Line 1555  Line 1906 
1906      # Get the parameters.      # Get the parameters.
1907      my ($self, $featureID, $count) = @_;      my ($self, $featureID, $count) = @_;
1908      # Ask for the best hits.      # Ask for the best hits.
1909      my @lists = FIGRules::BBHData($featureID);      my $lists = FIGRules::BBHData($featureID);
1910      # Create the return value.      # Create the return value.
1911      my %retVal = ();      my %retVal = ();
1912      for my $tuple (@lists) {      for my $tuple (@$lists) {
1913          $retVal{$tuple->[0]} = $tuple->[1];          $retVal{$tuple->[0]} = $tuple->[1];
1914      }      }
1915      # Return the result.      # Return the result.
# Line 1592  Line 1943 
1943      # Declare the return variable.      # Declare the return variable.
1944      my $retVal;      my $retVal;
1945      # Get the genome's data.      # Get the genome's data.
1946      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->_GenomeData($genomeID);
1947      if ($genomeData) {      # Only proceed if it exists.
1948        if (defined $genomeData) {
1949          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1950          $retVal = $genomeData->PrimaryValue('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1951      }      }
# Line 1661  Line 2013 
2013      if ($featureID =~ /^fig\|(\d+\.\d+)/) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
2014          $retVal = $1;          $retVal = $1;
2015      } else {      } else {
2016          Confess("Invalid feature ID $featureID.");          # Find the feature by alias.
2017            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
2018            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
2019                $retVal = $1;
2020            }
2021      }      }
2022      # Return the value found.      # Return the value found.
2023      return $retVal;      return $retVal;
# Line 1705  Line 2061 
2061              $retVal{$featureID2} = $score;              $retVal{$featureID2} = $score;
2062          }          }
2063      }      }
     # Functional coupling is reflexive. If we found at least one coupled feature, we must add  
     # the incoming feature as well.  
     if (keys %retVal) {  
         $retVal{$featureID} = 9999;  
     }  
2064      # Return the hash.      # Return the hash.
2065      return %retVal;      return %retVal;
2066  }  }
# Line 2066  Line 2417 
2417  sub GetGenomeNameData {  sub GetGenomeNameData {
2418      # Get the parameters.      # Get the parameters.
2419      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
2420        # Declare the return variables.
2421        my ($genus, $species, $strain);
2422        # Get the genome's data.
2423        my $genomeData = $self->_GenomeData($genomeID);
2424        # Only proceed if the genome exists.
2425        if (defined $genomeData) {
2426      # Get the desired values.      # Get the desired values.
2427      my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>          ($genus, $species, $strain) = $genomeData->Values(['Genome(genus)',
2428                                                              [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);                                                             'Genome(species)',
2429      # Throw an error if they were not found.                                                             'Genome(unique-characterization)']);
2430      if (! defined $genus) {      } else {
2431            # Throw an error because they were not found.
2432          Confess("Genome $genomeID not found in database.");          Confess("Genome $genomeID not found in database.");
2433      }      }
2434      # Return the results.      # Return the results.
# Line 2371  Line 2729 
2729  sub Taxonomy {  sub Taxonomy {
2730      # Get the parameters.      # Get the parameters.
2731      my ($self, $genome) = @_;      my ($self, $genome) = @_;
     # Find the specified genome's taxonomy string.  
     my ($list) = $self->GetEntityValues('Genome', $genome, ['Genome(taxonomy)']);  
2732      # Declare the return variable.      # Declare the return variable.
2733      my @retVal = ();      my @retVal = ();
2734      # If we found the genome, return its taxonomy string.      # Get the genome data.
2735      if ($list) {      my $genomeData = $self->_GenomeData($genome);
2736          @retVal = split /\s*;\s*/, $list;      # Only proceed if it exists.
2737        if (defined $genomeData) {
2738            # Create the taxonomy from the taxonomy string.
2739            @retVal = split /\s*;\s*/, $genomeData->PrimaryValue('Genome(taxonomy)');
2740      } else {      } else {
2741            # Genome doesn't exist, so emit a warning.
2742          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);          Trace("Genome \"$genome\" does not have a taxonomy in the database.\n") if T(0);
2743      }      }
2744      # Return the value found.      # Return the value found.
# Line 2423  Line 2783 
2783      }      }
2784      my @taxA = $self->Taxonomy($genomeA);      my @taxA = $self->Taxonomy($genomeA);
2785      my @taxB = $self->Taxonomy($genomeB);      my @taxB = $self->Taxonomy($genomeB);
2786      # Initialize the distance to 1. We'll reduce it each time we find a match between the      # Compute the distance.
2787      # taxonomies.      my $retVal = FIGRules::CrudeDistanceFormula(\@taxA, \@taxB);
     my $retVal = 1.0;  
     # Initialize the subtraction amount. This amount determines the distance reduction caused  
     # by a mismatch at the current level.  
     my $v = 0.5;  
     # Loop through the taxonomies.  
     for (my $i = 0; ($i < @taxA) && ($i < @taxB) && ($taxA[$i] eq $taxB[$i]); $i++) {  
         $retVal -= $v;  
         $v /= 2;  
     }  
2788      return $retVal;      return $retVal;
2789  }  }
2790    
# Line 2501  Line 2852 
2852      return @retVal;      return @retVal;
2853  }  }
2854    
 =head3 GetProperties  
   
     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;  
 }  
   
2855  =head3 FeatureProperties  =head3 FeatureProperties
2856    
2857      my @properties = $sprout->FeatureProperties($featureID);      my @properties = $sprout->FeatureProperties($featureID);
# Line 2615  Line 2880 
2880      # Get the parameters.      # Get the parameters.
2881      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2882      # Get the properties.      # Get the properties.
2883      my @attributes = $self->{_ca}->GetAttributes($featureID);      my @attributes = $self->ca->GetAttributes($featureID);
2884      # Strip the feature ID off each tuple.      # Strip the feature ID off each tuple.
2885      my @retVal = ();      my @retVal = ();
2886      for my $attributeRow (@attributes) {      for my $attributeRow (@attributes) {
# Line 2887  Line 3152 
3152  sub SubsystemList {  sub SubsystemList {
3153      # Get the parameters.      # Get the parameters.
3154      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3155      # Get the list of names.      # Get the list of names. We do a join to the Subsystem table because we have missing subsystems in
3156      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",      # the Sprout database!
3157        my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3158                                  [$featureID], 'HasRoleInSubsystem(to-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3159      # Return the result, sorted.      # Return the result, sorted.
3160      return sort @retVal;      return sort @retVal;
# Line 2921  Line 3187 
3187      # Declare the return variable.      # Declare the return variable.
3188      my %retVal = ();      my %retVal = ();
3189      # 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
3190      # feature we get its spreadsheet cells and the corresponding roles.      # feature we get its subsystem ID and the corresponding roles.
3191      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf'],      my @roleData = $self->GetAll(['HasFeature', 'ContainsFeature', 'IsRoleOf', 'HasSSCell'],
3192                               "HasFeature(from-link) = ?", [$genomeID],                               "HasFeature(from-link) = ?", [$genomeID],
3193                               ['HasFeature(to-link)', 'IsRoleOf(to-link)', 'IsRoleOf(from-link)']);                                   ['HasFeature(to-link)', 'IsRoleOf(from-link)',  'HasSSCell(from-link)']);
3194      # 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
3195      # with an unknown variant code (-1) are skipped. Note the genome ID is at both ends of the      # a non-negative variant code.
3196      # list. We use it at the beginning to get all the spreadsheet cells for the genome and      my %subs = map { $_ => 1 } $self->GetFlat(['ParticipatesIn'],
3197      # again at the end to filter out participation in subsystems with a negative variant code.                                                  "ParticipatesIn(from-link) = ? AND ParticipatesIn(variant-code) >= 0",
3198      my @cellData = $self->GetAll(['IsGenomeOf', 'HasSSCell', 'ParticipatesIn'],                                                  [$genomeID], 'ParticipatesIn(to-link)');
3199                                   "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.  
3200      for my $roleEntry (@roleData) {      for my $roleEntry (@roleData) {
3201          # Get the data for this feature and cell.          # Get the data for this feature and cell.
3202          my ($fid, $cellID, $role) = @{$roleEntry};          my ($fid, $role, $subsys) = @{$roleEntry};
3203          # Check for a subsystem name.          Trace("Subsystem for $fid is $subsys.") if T(4);
3204          my $subsys = $subHash{$cellID};          # Check the subsystem;
3205          if ($subsys) {          if ($subs{$subsys}) {
3206                Trace("Subsystem found.") if T(4);
3207              # Insure this feature has an entry in the return hash.              # Insure this feature has an entry in the return hash.
3208              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }              if (! exists $retVal{$fid}) { $retVal{$fid} = []; }
3209              # Merge in this new data.              # Merge in this new data.
# Line 2989  Line 3249 
3249      # Get the parameters.      # Get the parameters.
3250      my ($self, $featureID, $function, $userID) = @_;      my ($self, $featureID, $function, $userID) = @_;
3251      # Get a list of the features that are BBHs of the incoming feature.      # Get a list of the features that are BBHs of the incoming feature.
3252      my @bbhFeatures = map { $_->[0] } FIGRules::BBHData($featureID);      my $bbhData = FIGRules::BBHData($featureID);
3253        my @bbhFeatures = map { $_->[0] } @$bbhData;
3254      # Now we loop through the features, pulling out the ones that have the correct      # Now we loop through the features, pulling out the ones that have the correct
3255      # functional assignment.      # functional assignment.
3256      my @retVal = ();      my @retVal = ();
# Line 3162  Line 3423 
3423    
3424  =head3 BBHMatrix  =head3 BBHMatrix
3425    
3426      my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);      my $bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3427    
3428  Find all the bidirectional best hits for the features of a genome in a  Find all the bidirectional best hits for the features of a genome in a
3429  specified list of target genomes. The return value will be a hash mapping  specified list of target genomes. The return value will be a hash mapping
# Line 3186  Line 3447 
3447    
3448  =item RETURN  =item RETURN
3449    
3450  Returns a hash mapping each feature in the original genome to a hash mapping its  Returns a reference to a hash mapping each feature in the original genome
3451  BBH pegs in the target genomes to their scores.  to a sub-hash mapping its BBH pegs in the target genomes to their scores.
3452    
3453  =back  =back
3454    
# Line 3200  Line 3461 
3461      my %retVal = ();      my %retVal = ();
3462      # Ask for the BBHs.      # Ask for the BBHs.
3463      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);      my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3464        Trace("Retrieved " . scalar(@bbhList) . " BBH results.") if T(3);
3465      # We now have a set of 4-tuples that we need to convert into a hash of hashes.      # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3466      for my $bbhData (@bbhList) {      for my $bbhData (@bbhList) {
3467          my ($peg1, $peg2, $score) = @{$bbhData};          my ($peg1, $peg2, $score) = @{$bbhData};
# Line 3210  Line 3472 
3472          }          }
3473      }      }
3474      # Return the result.      # Return the result.
3475      return %retVal;      return \%retVal;
3476  }  }
3477    
3478    
# Line 3316  Line 3578 
3578      # Create the return hash.      # Create the return hash.
3579      my %retVal = ();      my %retVal = ();
3580      # Query for the desired BBHs.      # Query for the desired BBHs.
3581      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my $bbhList = FIGRules::BBHData($featureID, $cutoff);
3582      # Form the results into the return hash.      # Form the results into the return hash.
3583      for my $pair (@bbhList) {      for my $pair (@$bbhList) {
3584          my $fid = $pair->[0];          my $fid = $pair->[0];
3585          if ($self->Exists('Feature', $fid)) {          if ($self->Exists('Feature', $fid)) {
3586              $retVal{$fid} = $pair->[1];              $retVal{$fid} = $pair->[1];
# Line 3621  Line 3883 
3883      my ($self, %groupHash) = @_;      my ($self, %groupHash) = @_;
3884      # Create the result hash.      # Create the result hash.
3885      my %retVal = ();      my %retVal = ();
     # Get the super-group table.  
     my %superTable = $self->CheckGroupFile();  
3886      # Copy over the genomes.      # Copy over the genomes.
3887      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3888          # Get the super-group name.          # Get the super-group name.
3889          my $realGroupID;          my $realGroupID = $self->SuperGroup($groupID);
3890          if ($groupID =~ /([A-Z]\w+)/) {          # Append this group's genomes into the result hash
3891              if (! defined($superTable{$1})) {          # using the super-group name.
                 Confess("Super-group name not found for group $groupID.");  
             } else {  
                 $realGroupID = $1;  
             }  
         } else {  
             Confess("Invalid group name $groupID.");  
         }  
         # Append this group's genomes into the result hash.  
3892          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
3893      }      }
3894      # Return the result hash.      # Return the result hash.
# Line 3667  Line 3919 
3919  sub GroupPageName {  sub GroupPageName {
3920      # Get the parameters.      # Get the parameters.
3921      my ($self, $group) = @_;      my ($self, $group) = @_;
     # Declare the return variable.  
     my $retVal;  
3922      # Check for the group file data.      # Check for the group file data.
3923      my %superTable = $self->CheckGroupFile();      my %superTable = $self->CheckGroupFile();
3924      # Compute the real group name.      # Compute the real group name.
3925      if ($group =~ /([A-Z]\w+)/) {      my $realGroup = $self->SuperGroup($group);
3926          my $realGroup = $1;      # Get the associated page name.
3927          if (! defined($superTable{$1})) {      my $retVal = "../content/$superTable{$realGroup}->{page}";
             Confess("No super-group found for \"$group\".");  
         } else {  
             $retVal = "../content/$superTable{$1}->{page}";  
         }  
     } else {  
         Confess("\"group\" is not a valid group name.");  
     }  
3928      # Return the result.      # Return the result.
3929      return $retVal;      return $retVal;
3930  }  }
# Line 3715  Line 3958 
3958      # Get the parameters.      # Get the parameters.
3959      my ($self, $featureID, $key, @values) = @_;      my ($self, $featureID, $key, @values) = @_;
3960      # Add the property using the attached attributes object.      # Add the property using the attached attributes object.
3961      $self->{_ca}->AddAttribute($featureID, $key, @values);      $self->ca->AddAttribute($featureID, $key, @values);
3962  }  }
3963    
3964  =head3 CheckGroupFile  =head3 CheckGroupFile
# Line 3802  Line 4045 
4045  sub CleanKeywords {  sub CleanKeywords {
4046      # Get the parameters.      # Get the parameters.
4047      my ($self, $searchExpression) = @_;      my ($self, $searchExpression) = @_;
4048      # Perform the standard cleanup.      # Get the stemmer.
4049      my $retVal = $self->ERDB::CleanKeywords($searchExpression);      my $stemmer = $self->GetStemmer();
4050      # Fix the periods in EC and TC numbers.      # Convert the search expression using the stemmer.
4051      $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;      my $retVal = $stemmer->PrepareSearchExpression($searchExpression);
4052      # Fix non-trailing periods.      Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
     $retVal =~ s/\.(\w)/_$1/g;  
     # Fix non-leading minus signs.  
     $retVal =~ s/(\w)[\-]/$1_/g;  
     # Fix the vertical bars and colons  
     $retVal =~ s/(\w)[|:](\w)/$1'$2/g;  
4053      # Return the result.      # Return the result.
4054      return $retVal;      return $retVal;
4055  }  }
4056    
4057    =head3 GetSourceObject
4058    
4059        my $source = $erdb->GetSourceObject();
4060    
4061    Return the object to be used in creating load files for this database.
4062    
4063    =cut
4064    
4065    sub GetSourceObject {
4066        # Get the parameters.
4067        my ($self) = @_;
4068        # Check to see if we already have a source object.
4069        my $retVal = $self->{_fig};
4070        if (! defined $retVal) {
4071            # No, so create one.
4072            require FIG;
4073            $retVal = FIG->new();
4074        }
4075        # Return the object.
4076        return $retVal;
4077    }
4078    
4079    =head3 SectionList
4080    
4081        my @sections = $erdb->SectionList();
4082    
4083    Return a list of the names for the different data sections used when loading this database.
4084    The default is a single string, in which case there is only one section representing the
4085    entire database.
4086    
4087    =cut
4088    
4089    sub SectionList {
4090        # Get the parameters.
4091        my ($self, $source) = @_;
4092        # Ask the BaseSproutLoader for a section list.
4093        require BaseSproutLoader;
4094        my @retVal = BaseSproutLoader::GetSectionList($self);
4095        # Return the list.
4096        return @retVal;
4097    }
4098    
4099    =head3 Loader
4100    
4101        my $groupLoader = $erdb->Loader($groupName, $options);
4102    
4103    Return an [[ERDBLoadGroupPm]] object for the specified load group. This method is used
4104    by [[ERDBGeneratorPl]] to create the load group objects. If you are not using
4105    [[ERDBGeneratorPl]], you don't need to override this method.
4106    
4107    =over 4
4108    
4109    =item groupName
4110    
4111    Name of the load group whose object is to be returned. The group name is
4112    guaranteed to be a single word with only the first letter capitalized.
4113    
4114    =item options
4115    
4116    Reference to a hash of command-line options.
4117    
4118    =item RETURN
4119    
4120    Returns an [[ERDBLoadGroupPm]] object that can be used to process the specified load group
4121    for this database.
4122    
4123    =back
4124    
4125    =cut
4126    
4127    sub Loader {
4128        # Get the parameters.
4129        my ($self, $groupName, $options) = @_;
4130        # Compute the loader name.
4131        my $loaderClass = "${groupName}SproutLoader";
4132        # Pull in its definition.
4133        require "$loaderClass.pm";
4134        # Create an object for it.
4135        my $retVal = eval("$loaderClass->new(\$self, \$options)");
4136        # Insure it worked.
4137        Confess("Could not create $loaderClass object: $@") if $@;
4138        # Return it to the caller.
4139        return $retVal;
4140    }
4141    
4142    
4143    =head3 LoadGroupList
4144    
4145        my @groups = $erdb->LoadGroupList();
4146    
4147    Returns a list of the names for this database's load groups. This method is used
4148    by [[ERDBGeneratorPl]] when the user wishes to load all table groups. The default
4149    is a single group called 'All' that loads everything.
4150    
4151    =cut
4152    
4153    sub LoadGroupList {
4154        # Return the list.
4155        return qw(Genome Subsystem Annotation Property Source Reaction Synonym Feature Drug);
4156    }
4157    
4158    =head3 LoadDirectory
4159    
4160        my $dirName = $erdb->LoadDirectory();
4161    
4162    Return the name of the directory in which load files are kept. The default is
4163    the FIG temporary directory, which is a really bad choice, but it's always there.
4164    
4165    =cut
4166    
4167    sub LoadDirectory {
4168        # Get the parameters.
4169        my ($self) = @_;
4170        # Return the directory name.
4171        return $self->{dataDir};
4172    }
4173    
4174  =head2 Internal Utility Methods  =head2 Internal Utility Methods
4175    
4176    =head3 GetStemmer
4177    
4178        my $stermmer = $sprout->GetStemmer();
4179    
4180    Return the stemmer object for this database.
4181    
4182    =cut
4183    
4184    sub GetStemmer {
4185        # Get the parameters.
4186        my ($self) = @_;
4187        # Declare the return variable.
4188        my $retVal = $self->{stemmer};
4189        if (! defined $retVal) {
4190            # We don't have one pre-built, so we build and save it now.
4191            $retVal = BioWords->new(exceptions => "$FIG_Config::sproutData/Exceptions.txt",
4192                                     stops => "$FIG_Config::sproutData/StopWords.txt",
4193                                     cache => 0);
4194            $self->{stemmer} = $retVal;
4195        }
4196        # Return the result.
4197        return $retVal;
4198    }
4199    
4200  =head3 ParseAssignment  =head3 ParseAssignment
4201    
4202  Parse annotation text to determine whether or not it is a functional assignment. If it is,  Parse annotation text to determine whether or not it is a functional assignment. If it is,
# Line 3904  Line 4283 
4283      # Get the parameters.      # Get the parameters.
4284      my ($self, $fid) = @_;      my ($self, $fid) = @_;
4285      # Insure we have a genome hash.      # Insure we have a genome hash.
4286      if (! defined $self->{genomeHash}) {      my $genomes = $self->_GenomeHash();
         my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');  
         $self->{genomeHash} = \%genomeHash;  
     }  
4287      # Get the feature's genome ID.      # Get the feature's genome ID.
4288      my ($genomeID) = FIGRules::ParseFeatureID($fid);      my ($genomeID) = FIGRules::ParseFeatureID($fid);
4289      # Return an indicator of whether or not the genome ID is in the hash.      # Return an indicator of whether or not the genome ID is in the hash.
# Line 3941  Line 4317 
4317  }  }
4318    
4319    
4320    =head3 Hint
4321    
4322        my $htmlText = SearchHelper::Hint($wikiPage, $hintText);
4323    
4324    Return the HTML for a small question mark that displays the specified hint text when it is clicked.
4325    This HTML can be put in forms to provide a useful hinting mechanism.
4326    
4327    =over 4
4328    
4329    =item wikiPage
4330    
4331    Name of the wiki page to be popped up when the hint mark is clicked.
4332    
4333    =item hintText
4334    
4335    Text to display for the hint. It is raw html, but may not contain any double quotes.
4336    
4337    =item RETURN
4338    
4339    Returns the html for the hint facility. The resulting html shows a small button-like thing that
4340    uses the standard FIG popup technology.
4341    
4342    =back
4343    
4344    =cut
4345    
4346    sub Hint {
4347        # Get the parameters.
4348        my ($wikiPage, $hintText) = @_;
4349        # Escape the single quotes in the hint text.
4350        my $quotedText = $hintText;
4351        $quotedText =~ s/'/\\'/g;
4352        # Convert the wiki page name to a URL.
4353        my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4354        $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";
4355        # Compute the mouseover script.
4356        my $mouseOver = "doTooltip(this, '$quotedText')";
4357        # Create the html.
4358        my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";
4359        # Return it.
4360        return $retVal;
4361    }
4362    
4363    =head3 _GenomeHash
4364    
4365        my $gHash = $sprout->_GenomeHash();
4366    
4367    Return a hash mapping all NMPDR genome IDs to [[ERDBObjectPm]] genome objects.
4368    
4369    =cut
4370    
4371    sub _GenomeHash {
4372        # Get the parameters.
4373        my ($self) = @_;
4374        # Do we already have a filled hash?
4375        if (! $self->{genomeHashFilled}) {
4376            # No, create it.
4377            my %gHash = map { $_->PrimaryValue('id') => $_ } $self->GetList("Genome", "", []);
4378            $self->{genomeHash} = \%gHash;
4379            # Denote we have it.
4380            $self->{genomeHashFilled} = 1;
4381        }
4382        # Return the hash.
4383        return $self->{genomeHash};
4384    }
4385    
4386    =head3 _GenomeData
4387    
4388        my $genomeData = $sprout->_GenomeData($genomeID);
4389    
4390    Return an [[ERDBObjectPm]] object for the specified genome, or an undefined
4391    value if the genome does not exist.
4392    
4393    =over 4
4394    
4395    =item genomeID
4396    
4397    ID of the desired genome.
4398    
4399    =item RETURN
4400    
4401    Returns either an [[ERDBObjectPm]] containing the genome, or an undefined value.
4402    If the genome exists, it will have been read into the genome cache.
4403    
4404    =back
4405    
4406    =cut
4407    
4408    sub _GenomeData {
4409        # Get the parameters.
4410        my ($self, $genomeID) = @_;
4411        # Are we in the genome hash?
4412        if (! exists $self->{genomeHash}->{$genomeID} && ! $self->{genomeHashFilled}) {
4413            # The genome isn't in the hash, and the hash is not complete, so we try to
4414            # read it.
4415            $self->{genomeHash}->{$genomeID} = $self->GetEntity(Genome => $genomeID);
4416        }
4417        # Return the result.
4418        return $self->{genomeHash}->{$genomeID};
4419    }
4420    
4421    =head3 _CacheGenome
4422    
4423        $sprout->_CacheGenome($genomeID, $genomeData);
4424    
4425    Store the specified genome object in the genome cache if it is already there.
4426    
4427    =over 4
4428    
4429    =item genomeID
4430    
4431    ID of the genome to store in the cache.
4432    
4433    =item genomeData
4434    
4435    An [[ERDBObjectPm]] containing at least the data for the specified genome.
4436    Note that the Genome may not be the primary object in it, so a fully-qualified
4437    field name has to be used to retrieve data from it.
4438    
4439    =back
4440    
4441    =cut
4442    
4443    sub _CacheGenome {
4444        # Get the parameters.
4445        my ($self, $genomeID, $genomeData) = @_;
4446        # Only proceed if we don't already have the genome.
4447        if (! exists $self->{genomeHash}->{$genomeID}) {
4448            $self->{genomeHash}->{$genomeID} = $genomeData;
4449        }
4450    }
4451    
4452  1;  1;

Legend:
Removed from v.1.105  
changed lines
  Added in v.1.122

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3