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

Diff of /Sprout/Sprout.pm

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

revision 1.84, Thu Sep 14 14:11:09 2006 UTC revision 1.115, Sun Sep 7 03:13:32 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;
     use Carp;  
5      use DBKernel;      use DBKernel;
6      use XML::Simple;      use XML::Simple;
7      use DBQuery;      use DBQuery;
8      use DBObject;      use ERDBObject;
9      use Tracer;      use Tracer;
10      use FIGRules;      use FIGRules;
11      use FidCheck;      use FidCheck;
12      use Stats;      use Stats;
13      use POSIX qw(strftime);      use POSIX qw(strftime);
14      use BasicLocation;      use BasicLocation;
15        use CustomAttributes;
16        use RemoteCustomAttributes;
17        use CGI;
18        use WikiTools;
19        use base qw(ERDB);
20    
21  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
22    
# Line 28  Line 29 
29  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>
30  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>.
31    
32  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' });
33    
34  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
35  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
36  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
37  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
38    
39  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.
40    
# Line 45  Line 46 
46    
47  =head3 new  =head3 new
48    
49  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
50    
51  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
52  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 79  Line 80 
80    
81  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
82    
83    * B<host> name of the database host
84    
85  =back  =back
86    
87  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
88  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
89  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
90    
91  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' });
92    
93  =cut  =cut
94    
# Line 109  Line 112 
112                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
113                                                          # database connection port                                                          # database connection port
114                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::dbsock,
115                         host         => $FIG_Config::dbhost,                         host         => $FIG_Config::sprout_host,
116                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
117                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
118                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 122  Line 125 
125      # Connect to the database.      # Connect to the database.
126      my $dbh;      my $dbh;
127      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
128            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
129          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
130                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
131      }      }
# Line 131  Line 135 
135      # Add the option table and XML file name.      # Add the option table and XML file name.
136      $retVal->{_options} = $optionTable;      $retVal->{_options} = $optionTable;
137      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
138        # Set up space for the group file data.
139        $retVal->{groupHash} = undef;
140        # Set up space for the genome hash. We use this to identify NMPDR genomes.
141        $retVal->{genomeHash} = undef;
142        # Connect to the attributes.
143        if ($FIG_Config::attrURL) {
144            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
145            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
146        } elsif ($FIG_Config::attrDbName) {
147            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
148            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
149            $retVal->{_ca} = CustomAttributes->new(user => $user);
150        }
151        # Insure we have access to the stem module.
152        WikiUse('Lingua::Stem');
153        $retVal->{stemmer} = Lingua::Stem->new();
154        $retVal->{stemmer}->stem_caching({ -level => 2 });
155      # Return it.      # Return it.
156      return $retVal;      return $retVal;
157  }  }
158    
159    =head3 CoreGenomes
160    
161        my @genomes = $sprout->CoreGenomes($scope);
162    
163    Return the IDs of NMPDR genomes in the specified scope.
164    
165    =over 4
166    
167    =item scope
168    
169    Scope of the desired genomes. C<core> covers the original core genomes,
170    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
171    genomes in the system.
172    
173    =item RETURN
174    
175    Returns a list of the IDs for the genomes in the specified scope.
176    
177    =back
178    
179    =cut
180    
181    sub CoreGenomes {
182        # Get the parameters.
183        my ($self, $scope) = @_;
184        # Declare the return variable.
185        my @retVal = ();
186        # If we want all genomes, then this is easy.
187        if ($scope eq 'all') {
188            @retVal = $self->Genomes();
189        } else {
190            # Here we're dealing with groups. Get the hash of all the
191            # genome groups.
192            my %groups = $self->GetGroups();
193            # Loop through the groups, keeping the ones that we want.
194            for my $group (keys %groups) {
195                # Decide if we want to keep this group.
196                my $keepGroup = 0;
197                if ($scope eq 'nmpdr') {
198                    # NMPDR mode: keep all groups.
199                    $keepGroup = 1;
200                } elsif ($scope eq 'core') {
201                    # CORE mode. Only keep real core groups.
202                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
203                        $keepGroup = 1;
204                    }
205                }
206                # Add this group if we're keeping it.
207                if ($keepGroup) {
208                    push @retVal, @{$groups{$group}};
209                }
210            }
211        }
212        # Return the result.
213        return @retVal;
214    }
215    
216    =head3 SuperGroup
217    
218        my $superGroup = $sprout->SuperGroup($groupName);
219    
220    Return the name of the super-group containing the specified NMPDR genome
221    group. If no appropriate super-group can be found, an error will be
222    thrown.
223    
224    =over 4
225    
226    =item groupName
227    
228    Name of the group whose super-group is desired.
229    
230    =item RETURN
231    
232    Returns the name of the super-group containing the incoming group.
233    
234    =back
235    
236    =cut
237    
238    sub SuperGroup {
239        # Get the parameters.
240        my ($self, $groupName) = @_;
241        # Declare the return variable.
242        my $retVal;
243        # Get the group hash.
244        my %groupHash = $self->CheckGroupFile();
245        # Find the super-group genus.
246        $groupName =~ /([A-Z]\w+)/;
247        my $nameThing = $1;
248        # See if it's directly in the group hash.
249        if (exists $groupHash{$nameThing}) {
250            # Yes, then it's our result.
251            $retVal = $nameThing;
252        } else {
253            # No, so we have to search.
254            for my $superGroup (keys %groupHash) {
255                # Get this super-group's item list.
256                my $list = $groupHash{$superGroup}->{contents};
257                # Search it.
258                if (grep { $_->[0] eq $nameThing } @{$list}) {
259                    $retVal = $superGroup;
260                }
261            }
262            # Make sure we found something.
263            if (! $retVal) {
264                Confess("No super-group found for \"$groupName\".");
265            }
266        }
267        # Return the result.
268        return $retVal;
269    }
270    
271  =head3 MaxSegment  =head3 MaxSegment
272    
273  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
274    
275  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
276  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 154  Line 287 
287    
288  =head3 MaxSequence  =head3 MaxSequence
289    
290  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
291    
292  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
293  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 169  Line 302 
302    
303  =head3 Load  =head3 Load
304    
305  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
306    
307  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.
308    
# Line 209  Line 342 
342    
343  =head3 LoadUpdate  =head3 LoadUpdate
344    
345  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
346    
347  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
348  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 255  Line 388 
388              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
389          } else {          } else {
390              # Attempt to load this table.              # Attempt to load this table.
391              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
392              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
393              $retVal->Accumulate($result);              $retVal->Accumulate($result);
394          }          }
# Line 266  Line 399 
399    
400  =head3 GenomeCounts  =head3 GenomeCounts
401    
402  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
403    
404  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
405  genomes will be included in the counts.  genomes will be included in the counts.
# Line 311  Line 444 
444    
445  =head3 ContigCount  =head3 ContigCount
446    
447  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
448    
449  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
450    
# Line 338  Line 471 
471      return $retVal;      return $retVal;
472  }  }
473    
474  =head3 GeneMenu  =head3 GenomeMenu
475    
476        my $html = $sprout->GenomeMenu(%options);
477    
478    Generate a genome selection control with the specified name and options.
479    This control is almost but not quite the same as the genome control in the
480    B<SearchHelper> class. Eventually, the two will be combined.
481    
482    =over 4
483    
484    =item options
485    
486    Optional parameters for the control (see below).
487    
488  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params); >>  =item RETURN
489    
490    Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
491    
492    =back
493    
494  Return an HTML select menu of genomes. Each genome will be an option in the menu,  The valid options are as follows.
 and will be displayed by name with the ID and a contig count attached. The selection  
 value will be the genome ID. The genomes will be sorted by genus/species name.  
495    
496  =over 4  =over 4
497    
498  =item attributes  =item name
499    
500    Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
501    Terrible things will happen if you have two controls with the same name on the same page.
502    
503    =item filter
504    
505    If specified, a filter for the list of genomes to display. The filter should be in the form of a
506    list reference. The first element of the list should be the filter string, and the remaining elements
507    the filter parameters.
508    
509    =item multiSelect
510    
511    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
512    
513    =item size
514    
515    Number of rows to display in the control. The default is C<10>
516    
517    =item id
518    
519    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
520    unless this ID is unique.
521    
522    =item selected
523    
524    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
525    default is none.
526    
527    =item class
528    
529    If specified, a style class to assign to the genome control.
530    
531    =back
532    
533    =cut
534    
535    sub GenomeMenu {
536        # Get the parameters.
537        my ($self, %options) = @_;
538        # Get the control's name and ID.
539        my $menuName = $options{name} || $options{id} || 'myGenomeControl';
540        my $menuID = $options{id} || $menuName;
541        Trace("Genome menu name = $menuName with ID $menuID.") if T(3);
542        # Compute the IDs for the status display.
543        my $divID = "${menuID}_status";
544        my $urlID = "${menuID}_url";
545        # Compute the code to show selected genomes in the status area.
546        my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
547        # Check for single-select or multi-select.
548        my $multiSelect = $options{multiSelect} || 0;
549        # Get the style data.
550        my $class = $options{class} || '';
551        # Get the list of pre-selected items.
552        my $selections = $options{selected} || [];
553        if (ref $selections ne 'ARRAY') {
554            $selections = [ split /\s*,\s*/, $selections ];
555        }
556        my %selected = map { $_ => 1 } @{$selections};
557        # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
558        # string or a list reference.
559        my $filterParms = $options{filter} || "";
560        if (! ref $filterParms) {
561            $filterParms = [split /\t|\\t/, $filterParms];
562        }
563        my $filterString = shift @{$filterParms};
564        # Get a list of all the genomes in group order. In fact, we only need them ordered
565        # by name (genus,species,strain), but putting primary-group in front enables us to
566        # take advantage of an existing index.
567        my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
568                                       $filterParms,
569                                       [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
570        # Create a hash to organize the genomes by group. Each group will contain a list of
571        # 2-tuples, the first element being the genome ID and the second being the genome
572        # name.
573        my %gHash = ();
574        for my $genome (@genomeList) {
575            # Get the genome data.
576            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
577            # Compute its name. This is the genus, species, strain (if any), and the contig count.
578            my $name = "$genus $species ";
579            $name .= "$strain " if $strain;
580            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
581            # Now we get the domain. The domain tells us the display style of the organism.
582            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
583            # Now compute the display group. This is normally the primary group, but if the
584            # organism is supporting, we blank it out.
585            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
586            # Push the genome into the group's list. Note that we use the real group
587            # name for the hash key here, not the display group name.
588            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
589        }
590        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
591        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
592        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
593        # that aren't "other". At some point, we will want to make this less complicated.
594        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
595                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
596        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
597        # Remember the number of NMPDR groups.
598        my $nmpdrGroupCount = scalar @groups;
599        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
600        # of the domains found.
601        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
602        my @domains = ();
603        for my $genomeData (@otherGenomes) {
604            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
605            if (exists $gHash{$domain}) {
606                push @{$gHash{$domain}}, $genomeData;
607            } else {
608                $gHash{$domain} = [$genomeData];
609                push @domains, $domain;
610            }
611        }
612        # Add the domain groups at the end of the main group list. The main group list will now
613        # contain all the categories we need to display the genomes.
614        push @groups, sort @domains;
615        # Delete the supporting group.
616        delete $gHash{$FIG_Config::otherGroup};
617        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
618        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
619        # and use that to make the selections.
620        my $nmpdrCount = 0;
621        # Create the type counters.
622        my $groupCount = 1;
623        # Get the number of rows to display.
624        my $rows = $options{size} || 10;
625        # If we're multi-row, create an onChange event.
626        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
627        # Set up the multiple-select flag.
628        my $multipleTag = ($multiSelect ? " multiple" : "" );
629        # Set up the style class.
630        my $classTag = ($class ? " class=\"$class\"" : "" );
631        # Create the SELECT tag and stuff it into the output array.
632        my @lines = ("<SELECT name=\"$menuName\" id=\"$menuID\" $onChangeTag$multipleTag$classTag size=\"$rows\">");
633        # Loop through the groups.
634        for my $group (@groups) {
635            # Get the genomes in the group.
636            for my $genome (@{$gHash{$group}}) {
637                # If this is an NMPDR organism, we add an extra style and count it.
638                my $nmpdrStyle = "";
639                if ($nmpdrGroupCount > 0) {
640                    $nmpdrCount++;
641                    $nmpdrStyle = " Core";
642                }
643                # Get the organism ID, name, contig count, and domain.
644                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
645                # See if we're pre-selected.
646                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
647                # Compute the display name.
648                my $nameString = "$name ($genomeID$contigCount)";
649                # Generate the option tag.
650                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
651                push @lines, "    $optionTag";
652            }
653            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
654            # groups.
655            $nmpdrGroupCount--;
656        }
657        # Close the SELECT tag.
658        push @lines, "</SELECT>";
659        if ($rows > 1) {
660            # We're in a non-compact mode, so we need to add some selection helpers. First is
661            # the search box. This allows the user to type text and change which genomes are
662            # displayed. For multiple-select mode, we include a button that selects the displayed
663            # genes. For single-select mode, we use a plain label instead.
664            my $searchThingName = "${menuID}_SearchThing";
665            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
666                                                 : "Show genomes containing");
667            push @lines, "<br />$searchThingLabel&nbsp;" .
668                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />" .
669                         Hint("GenomeControl", "Type here to filter the genomes displayed.") . "<br />";
670            # For multi-select mode, we also have buttons to set and clear selections.
671            if ($multiSelect) {
672                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
673                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
674                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
675            }
676            # Add a hidden field we can use to generate organism page hyperlinks.
677            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Organism;organism=\" />";
678            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
679            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
680        }
681        # Assemble all the lines into a string.
682        my $retVal = join("\n", @lines, "");
683        # Return the result.
684        return $retVal;
685    }
686    
687    
688  Reference to a hash mapping attributes to values for the SELECT tag generated.  =head3 Stem
689    
690  =item filterString      my $stem = $sprout->Stem($word);
691    
692  A filter string for use in selecting the genomes. The filter string must conform  Return the stem of the specified word, or C<undef> if the word is not
693  to the rules for the C<< ERDB->Get >> method.  stemmable. Note that even if the word is stemmable, the stem may be
694    the same as the original word.
695    
696  =item params  =over 4
697    
698    =item word
699    
700  Reference to a list of values to be substituted in for the parameter marks in  Word to convert into a stem.
 the filter string.  
701    
702  =item RETURN  =item RETURN
703    
704  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
705    the word is not stemmable.
706    
707  =back  =back
708    
709  =cut  =cut
710    
711  sub GeneMenu {  sub Stem {
712      # Get the parameters.      # Get the parameters.
713      my ($self, $attributes, $filterString, $params) = @_;      my ($self, $word) = @_;
714      # Start the menu.      # Declare the return variable.
715      my $retVal = "<select " .      my $retVal;
716          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      # See if it's stemmable.
717          ">\n";      if ($word =~ /^[A-Za-z]+$/) {
718      # Get the genomes.          # Compute the stem.
719      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',          my $stemList = $self->{stemmer}->stem($word);
720                                                                       'Genome(genus)',          my $stem = $stemList->[0];
721                                                                       'Genome(species)',          # Check to see if it's long enough.
722                                                                       'Genome(unique-characterization)']);          if (length $stem >= 3) {
723      # Sort them by name.              # Yes, keep it.
724      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;              $retVal = $stem;
725      # Loop through the genomes, creating the option tags.          } else {
726      for my $genomeData (@sorted) {              # No, use the original word.
727          # Get the data for this genome.              $retVal = $word;
728          my ($genomeID, $genus, $species, $strain) = @{$genomeData};          }
         # Get the contig count.  
         my $count = $self->ContigCount($genomeID);  
         my $counting = ($count == 1 ? "contig" : "contigs");  
         # Build the option tag.  
         $retVal .= "<option value=\"$genomeID\">$genus $species $strain ($genomeID) [$count $counting]</option>\n";  
         Trace("Option tag built for $genomeID: $genus $species $strain.") if T(3);  
729      }      }
     # Close the SELECT tag.  
     $retVal .= "</select>\n";  
730      # Return the result.      # Return the result.
731      return $retVal;      return $retVal;
732  }  }
733    
734    
735  =head3 Build  =head3 Build
736    
737  C<< $sprout->Build(); >>      $sprout->Build();
738    
739  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.
740  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 419  Line 751 
751    
752  =head3 Genomes  =head3 Genomes
753    
754  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
755    
756  Return a list of all the genome IDs.  Return a list of all the genome IDs.
757    
# Line 436  Line 768 
768    
769  =head3 GenusSpecies  =head3 GenusSpecies
770    
771  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
772    
773  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
774    
# Line 468  Line 800 
800    
801  =head3 FeaturesOf  =head3 FeaturesOf
802    
803  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
804    
805  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
806    
# Line 513  Line 845 
845    
846  =head3 FeatureLocation  =head3 FeatureLocation
847    
848  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
849    
850  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
851  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 537  Line 869 
869  =item RETURN  =item RETURN
870    
871  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
872  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
873    wasn't found.
874    
875  =back  =back
876    
877  =cut  =cut
878  #: Return Type @;  
 #: Return Type $;  
879  sub FeatureLocation {  sub FeatureLocation {
880      # Get the parameters.      # Get the parameters.
881      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
882      # Create a query for the feature locations.      # Declare the return variable.
     my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",  
                            [$featureID]);  
     # Create the return list.  
883      my @retVal = ();      my @retVal = ();
884      # Set up the variables used to determine if we have adjacent segments. This initial setup will      # Get the feature record.
885      # not match anything.      my $object = $self->GetEntity('Feature', $featureID);
886      my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);      # Only proceed if we found it.
887      # Loop through the query results, creating location specifiers.      if (defined $object) {
888      while (my $location = $query->Fetch()) {          # Get the location string.
889          # Get the location parameters.          my $locString = $object->PrimaryValue('Feature(location-string)');
890          my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',          # Create the return list.
891              'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);          @retVal = split /\s*,\s*/, $locString;
         # Check to see if we are adjacent to the previous segment.  
         if ($prevContig eq $contigID && $dir eq $prevDir) {  
             # Here the new segment is in the same direction on the same contig. Insure the  
             # new segment's beginning is next to the old segment's end.  
             if ($dir eq "-" && $beg + $len == $prevBeg) {  
                 # Here we're merging two backward blocks, so we keep the new begin point  
                 # and adjust the length.  
                 $len += $prevLen;  
                 # Pop the old segment off. The new one will replace it later.  
                 pop @retVal;  
             } elsif ($dir eq "+" && $beg == $prevBeg + $prevLen) {  
                 # Here we need to merge two forward blocks. Adjust the beginning and  
                 # length values to include both segments.  
                 $beg = $prevBeg;  
                 $len += $prevLen;  
                 # Pop the old segment off. The new one will replace it later.  
                 pop @retVal;  
             }  
         }  
         # Remember this specifier for the adjacent-segment test the next time through.  
         ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);  
         # Compute the initial base pair.  
         my $start = ($dir eq "+" ? $beg : $beg + $len - 1);  
         # Add the specifier to the list.  
         push @retVal, "${contigID}_$start$dir$len";  
892      }      }
893      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
894      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
# Line 592  Line 896 
896    
897  =head3 ParseLocation  =head3 ParseLocation
898    
899  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
900    
901  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
902  length.  length.
# Line 611  Line 915 
915  =back  =back
916    
917  =cut  =cut
918  #: Return Type @;  
919  sub ParseLocation {  sub ParseLocation {
920      # Get the parameter. Note that if we're called as an instance method, we ignore      # Get the parameter. Note that if we're called as an instance method, we ignore
921      # the first parameter.      # the first parameter.
# Line 634  Line 938 
938      return ($contigID, $start, $dir, $len);      return ($contigID, $start, $dir, $len);
939  }  }
940    
941    
942    
943  =head3 PointLocation  =head3 PointLocation
944    
945  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
946    
947  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
948  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 665  Line 971 
971  =back  =back
972    
973  =cut  =cut
974  #: Return Type $;  
975  sub PointLocation {  sub PointLocation {
976      # Get the parameter. Note that if we're called as an instance method, we ignore      # Get the parameter. Note that if we're called as an instance method, we ignore
977      # the first parameter.      # the first parameter.
# Line 688  Line 994 
994    
995  =head3 DNASeq  =head3 DNASeq
996    
997  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
998    
999  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
1000  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 772  Line 1078 
1078    
1079  =head3 AllContigs  =head3 AllContigs
1080    
1081  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1082    
1083  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1084    
# Line 802  Line 1108 
1108    
1109  =head3 GenomeLength  =head3 GenomeLength
1110    
1111  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1112    
1113  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1114    
# Line 837  Line 1143 
1143    
1144  =head3 FeatureCount  =head3 FeatureCount
1145    
1146  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1147    
1148  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.
1149    
# Line 872  Line 1178 
1178    
1179  =head3 GenomeAssignments  =head3 GenomeAssignments
1180    
1181  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1182    
1183  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
1184  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 898  Line 1204 
1204      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1205      # Declare the return variable.      # Declare the return variable.
1206      my $retVal = {};      my $retVal = {};
1207      # Query the genome's features and annotations. We'll put the oldest annotations      # Query the genome's features.
1208      # first so that the last assignment to go into the hash will be the correct one.      my $query = $self->Get(['HasFeature', 'Feature'], "HasFeature(from-link) = ?",
     my $query = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],  
                            "HasFeature(from-link) = ? ORDER BY Annotation(time)",  
1209                             [$genomeID]);                             [$genomeID]);
1210      # Loop through the annotations.      # Loop through the features.
1211      while (my $data = $query->Fetch) {      while (my $data = $query->Fetch) {
1212          # Get the feature ID and annotation text.          # Get the feature ID and assignment.
1213          my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1214                                                  'Annotation(annotation)']);          if ($assignment) {
         # Check to see if this is an assignment. Note that the user really  
         # doesn't matter to us, other than we use it to determine whether or  
         # not this is an assignment.  
         my ($user, $assignment) = _ParseAssignment('fig', $annotation);  
         if ($user) {  
             # Here it's an assignment. We put it in the return hash, overwriting  
             # any older assignment that might be present.  
1215              $retVal->{$fid} = $assignment;              $retVal->{$fid} = $assignment;
1216          }          }
1217      }      }
# Line 924  Line 1221 
1221    
1222  =head3 ContigLength  =head3 ContigLength
1223    
1224  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1225    
1226  Compute the length of a contig.  Compute the length of a contig.
1227    
# Line 963  Line 1260 
1260    
1261  =head3 ClusterPEGs  =head3 ClusterPEGs
1262    
1263  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1264    
1265  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
1266  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
1267  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
1268  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
1269  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
1270  sequence.  appear in the output sequence.
1271    
1272  =over 4  =over 4
1273    
# Line 1011  Line 1308 
1308    
1309  =head3 GenesInRegion  =head3 GenesInRegion
1310    
1311  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1312    
1313  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1314    
# Line 1040  Line 1337 
1337  =back  =back
1338    
1339  =cut  =cut
1340  #: Return Type @@;  
1341  sub GenesInRegion {  sub GenesInRegion {
1342      # Get the parameters.      # Get the parameters.
1343      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1344      # Get the maximum segment length.      # Get the maximum segment length.
1345      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1346      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1347      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1348      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1349      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1350        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1351        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1352        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1353        # of the feature's locations.
1354        my %featureMap = ();
1355        # Loop through them to do the begin/end analysis.
1356        for my $featureObject (@featureObjects) {
1357            # Get the feature's location string. This may contain multiple actual locations.
1358            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1359            my @locationSegments = split /\s*,\s*/, $locations;
1360            # Loop through the locations.
1361            for my $locationSegment (@locationSegments) {
1362                # Construct an object for the location.
1363                my $locationObject = BasicLocation->new($locationSegment);
1364                # Merge the current segment's begin and end into the min and max.
1365                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1366                my ($beg, $end);
1367                if (exists $featureMap{$fid}) {
1368                    ($beg, $end) = @{$featureMap{$fid}};
1369                    $beg = $left if $left < $beg;
1370                    $end = $right if $right > $end;
1371                } else {
1372                    ($beg, $end) = ($left, $right);
1373                }
1374                $min = $beg if $beg < $min;
1375                $max = $end if $end > $max;
1376                # Store the feature's new extent back into the hash table.
1377                $featureMap{$fid} = [$beg, $end];
1378            }
1379        }
1380        # Now we must compute the list of the IDs for the features found. We start with a list
1381        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1382        # but the result of the sort will be the same.)
1383        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1384        # Now we sort by midpoint and yank out the feature IDs.
1385        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1386        # Return it along with the min and max.
1387        return (\@retVal, $min, $max);
1388    }
1389    
1390    =head3 GeneDataInRegion
1391    
1392        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1393    
1394    List the features which overlap a specified region in a contig.
1395    
1396    =over 4
1397    
1398    =item contigID
1399    
1400    ID of the contig containing the region of interest.
1401    
1402    =item start
1403    
1404    Offset of the first residue in the region of interest.
1405    
1406    =item stop
1407    
1408    Offset of the last residue in the region of interest.
1409    
1410    =item RETURN
1411    
1412    Returns a list of B<ERDBObjects> for the desired features. Each object will
1413    contain a B<Feature> record.
1414    
1415    =back
1416    
1417    =cut
1418    
1419    sub GeneDataInRegion {
1420        # Get the parameters.
1421        my ($self, $contigID, $start, $stop) = @_;
1422        # Get the maximum segment length.
1423        my $maximumSegmentLength = $self->MaxSegment;
1424        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1425        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1426        # ERDBObject from the query.
1427        my %featuresFound = ();
1428        # Create a table of parameters for the queries. Each query looks for features travelling in
1429      # a particular direction. The query parameters include the contig ID, the feature direction,      # a particular direction. The query parameters include the contig ID, the feature direction,
1430      # the lowest possible start position, and the highest possible start position. This works      # the lowest possible start position, and the highest possible start position. This works
1431      # because each feature segment length must be no greater than the maximum segment length.      # because each feature segment length must be no greater than the maximum segment length.
# Line 1063  Line 1434 
1434      # Loop through the query parameters.      # Loop through the query parameters.
1435      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1436          # Create the query.          # Create the query.
1437          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1438              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1439              $parms);              $parms);
1440          # Loop through the feature segments found.          # Loop through the feature segments found.
1441          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1442              # Get the data about this segment.              # Get the data about this segment.
1443              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1444                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1445              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1446              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1447              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1448              # length.              # length.
1449              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1450              if ($dir eq '+') {              my $found = $loc->Overlap($start, $stop);
                 $end = $beg + $len;  
                 if ($end >= $start) {  
                     # Denote we found a useful feature.  
                     $found = 1;  
                 }  
             } elsif ($dir eq '-') {  
                 # Note we switch things around so that the beginning is to the left of the  
                 # ending.  
                 ($beg, $end) = ($beg - $len, $beg);  
                 if ($beg <= $stop) {  
                     # Denote we found a useful feature.  
                     $found = 1;  
                 }  
             }  
1451              if ($found) {              if ($found) {
1452                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1453                  # get the current entry for the specified feature.                  $featuresFound{$featureID} = $segment;
                 my ($loc1, $loc2) = (exists $featuresFound{$featureID} ? @{$featuresFound{$featureID}} :  
                                      @initialMinMax);  
                 # Merge the current segment's begin and end into the feature begin and end and the  
                 # global min and max.  
                 if ($beg < $loc1) {  
                     $loc1 = $beg;  
                     $min = $beg if $beg < $min;  
                 }  
                 if ($end > $loc2) {  
                     $loc2 = $end;  
                     $max = $end if $end > $max;  
1454                  }                  }
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1455              }              }
1456          }          }
1457      }      # Return the ERDB objects for the features found.
1458      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$featuresFound{$_}->[0] + $featuresFound{$_}->[1], $_] } keys %featuresFound;  
     # Now we sort by midpoint and yank out the feature IDs.  
     my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;  
     # Return it along with the min and max.  
     return (\@retVal, $min, $max);  
1459  }  }
1460    
1461  =head3 FType  =head3 FType
1462    
1463  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1464    
1465  Return the type of a feature.  Return the type of a feature.
1466    
# Line 1153  Line 1490 
1490    
1491  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1492    
1493  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1494    
1495  Return the annotations of a feature.  Return the annotations of a feature.
1496    
# Line 1216  Line 1553 
1553    
1554  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1555    
1556  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1557    
1558  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
1559  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 1271  Line 1608 
1608    
1609  =head3 FunctionOf  =head3 FunctionOf
1610    
1611  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1612    
1613  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1614    
1615  The functional assignment is handled differently depending on the type of feature. If  The functional assignment is handled differently depending on the type of feature. If
1616  the feature is identified by a FIG ID (begins with the string C<fig|>), then a functional  the feature is identified by a FIG ID (begins with the string C<fig|>), then the functional
1617  assignment is a type of annotation. The format of an assignment is described in  assignment is taken from the B<Feature> or C<Annotation> table, depending.
 L</ParseAssignment>. Its worth noting that we cannot filter on the content of the  
 annotation itself because it's a text field; however, this is not a big problem because  
 most features only have a small number of annotations.  
1618    
1619  Each user has an associated list of trusted users. The assignment returned will be the most  Each user has an associated list of trusted users. The assignment returned will be the most
1620  recent one by at least one of the trusted users. If no trusted user list is available, then  recent one by at least one of the trusted users. If no trusted user list is available, then
# Line 1299  Line 1633 
1633    
1634  =item userID (optional)  =item userID (optional)
1635    
1636  ID of the user whose function determination is desired. If omitted, only the latest  ID of the user whose function determination is desired. If omitted, the primary
1637  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1638    
1639  =item RETURN  =item RETURN
1640    
# Line 1317  Line 1651 
1651      my $retVal;      my $retVal;
1652      # Determine the ID type.      # Determine the ID type.
1653      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1654          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1655          # users.          if (!$userID) {
1656                # Use the primary assignment.
1657                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1658            } else {
1659                # We must build the list of trusted users.
1660          my %trusteeTable = ();          my %trusteeTable = ();
1661          # Check the user ID.          # Check the user ID.
1662          if (!$userID) {          if (!$userID) {
# Line 1361  Line 1699 
1699                  }                  }
1700              }              }
1701          }          }
1702            }
1703      } else {      } else {
1704          # Here we have a non-FIG feature ID. In this case the user ID does not          # Here we have a non-FIG feature ID. In this case the user ID does not
1705          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1373  Line 1712 
1712    
1713  =head3 FunctionsOf  =head3 FunctionsOf
1714    
1715  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1716    
1717  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1718    
# Line 1445  Line 1784 
1784    
1785  =head3 BBHList  =head3 BBHList
1786    
1787  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1788    
1789  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
1790  on a specified target genome.  on a specified target genome.
# Line 1481  Line 1820 
1820          # Peel off the BBHs found.          # Peel off the BBHs found.
1821          my @found = ();          my @found = ();
1822          for my $bbh (@bbhData) {          for my $bbh (@bbhData) {
1823              push @found, $bbh->[0];              my $fid = $bbh->[0];
1824                my $bbGenome = $self->GenomeOf($fid);
1825                if ($bbGenome eq $genomeID) {
1826                    push @found, $fid;
1827                }
1828          }          }
1829          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1830      }      }
# Line 1491  Line 1834 
1834    
1835  =head3 SimList  =head3 SimList
1836    
1837  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1838    
1839  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1840    
# Line 1527  Line 1870 
1870    
1871  =head3 IsComplete  =head3 IsComplete
1872    
1873  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1874    
1875  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1876    
# Line 1555  Line 1898 
1898      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1899      if ($genomeData) {      if ($genomeData) {
1900          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1901          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1902      }      }
1903      # Return the result.      # Return the result.
1904      return $retVal;      return $retVal;
# Line 1563  Line 1906 
1906    
1907  =head3 FeatureAliases  =head3 FeatureAliases
1908    
1909  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1910    
1911  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1912    
# Line 1586  Line 1929 
1929      # Get the parameters.      # Get the parameters.
1930      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1931      # Get the desired feature's aliases      # Get the desired feature's aliases
1932      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1933      # Return the result.      # Return the result.
1934      return @retVal;      return @retVal;
1935  }  }
1936    
1937  =head3 GenomeOf  =head3 GenomeOf
1938    
1939  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1940    
1941  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1942    
# Line 1615  Line 1958 
1958  sub GenomeOf {  sub GenomeOf {
1959      # Get the parameters.      # Get the parameters.
1960      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
     # Create a query to find the genome associated with the incoming ID.  
     my $query = $self->Get(['IsLocatedIn', 'HasContig'], "IsLocatedIn(from-link) = ? OR HasContig(to-link) = ?",  
                            [$featureID, $featureID]);  
1961      # Declare the return value.      # Declare the return value.
1962      my $retVal;      my $retVal;
1963      # Get the genome ID.      # Parse the genome ID from the feature ID.
1964      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1965          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1966        } else {
1967            # Find the feature by alias.
1968            my ($realFeatureID) = $self->FeaturesByAlias($featureID);
1969            if ($realFeatureID && $realFeatureID =~ /^fig\|(\d+\.\d+)/) {
1970                $retVal = $1;
1971            } else {
1972                # Use the external table.
1973                my ($org) = $self->GetFlat(['ExternalAliasOrg'], "ExternalAliasOrg(id) = ?",
1974                                           [$featureID], "ExternalAliasOrg(org)");
1975                if ($org) {
1976                    $retVal = $org;
1977                } else {
1978                    Confess("Invalid feature ID $featureID.");
1979                }
1980            }
1981      }      }
1982      # Return the value found.      # Return the value found.
1983      return $retVal;      return $retVal;
# Line 1630  Line 1985 
1985    
1986  =head3 CoupledFeatures  =head3 CoupledFeatures
1987    
1988  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1989    
1990  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1991  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 1652  Line 2007 
2007  sub CoupledFeatures {  sub CoupledFeatures {
2008      # Get the parameters.      # Get the parameters.
2009      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2010        # Ask the coupling server for the data.
2011      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
2012      # Create a query to retrieve the functionally-coupled features.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
2013      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
2014                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);      # Form them into a hash.
     # This value will be set to TRUE if we find at least one coupled feature.  
     my $found = 0;  
     # Create the return hash.  
2015      my %retVal = ();      my %retVal = ();
2016      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
2017      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
2018          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
2019          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
2020                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
2021          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);              $retVal{$featureID2} = $score;
2022          # Get the other feature that participates in the coupling.          }
         my ($otherFeatureID) = $self->GetFlat(['ParticipatesInCoupling'],  
                                            "ParticipatesInCoupling(to-link) = ? AND ParticipatesInCoupling(from-link) <> ?",  
                                            [$couplingID, $featureID], 'ParticipatesInCoupling(from-link)');  
         Trace("$couplingID target feature is $otherFeatureID.") if T(coupling => 4);  
         # Attach the other feature's score to its ID.  
         $retVal{$otherFeatureID} = $score;  
         $found = 1;  
2023      }      }
2024      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
2025      # the incoming feature as well.      # the incoming feature as well.
2026      if ($found) {      if (keys %retVal) {
2027          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
2028      }      }
2029      # Return the hash.      # Return the hash.
# Line 1686  Line 2032 
2032    
2033  =head3 CouplingEvidence  =head3 CouplingEvidence
2034    
2035  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
2036    
2037  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
2038    
# Line 1734  Line 2080 
2080      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2081      # Declare the return variable.      # Declare the return variable.
2082      my @retVal = ();      my @retVal = ();
2083      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2084      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2085      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2086      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2087      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2088      if ($couplingID) {              push @retVal, $rawTuple;
         # Determine the ordering to place on the evidence items. If we're  
         # inverted, we want to see feature 2 before feature 1 (descending); otherwise,  
         # we want feature 1 before feature 2 (normal).  
         Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);  
         my $ordering = ($inverted ? "DESC" : "");  
         # Get the coupling evidence.  
         my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],  
                                           "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",  
                                           [$couplingID],  
                                           ['PCH(used)', 'UsesAsEvidence(to-link)']);  
         # Loop through the evidence items. Each piece of evidence is represented by two  
         # positions in the evidence list, one for each feature on the other side of the  
         # evidence link. If at some point we want to generalize to couplings with  
         # more than two positions, this section of code will need to be re-done.  
         while (@evidenceList > 0) {  
             my $peg1Data = shift @evidenceList;  
             my $peg2Data = shift @evidenceList;  
             Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);  
             push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];  
         }  
         Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);  
     }  
     # Return the result.  
     return @retVal;  
2089  }  }
   
 =head3 GetCoupling  
   
 C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>  
   
 Return the coupling (if any) for the specified pair of PEGs. If a coupling  
 exists, we return the coupling ID along with an indicator of whether the  
 coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.  
 In the second case, we say the coupling is I<inverted>. The importance of an  
 inverted coupling is that the PEGs in the evidence will appear in reverse order.  
   
 =over 4  
   
 =item peg1  
   
 ID of the feature of interest.  
   
 =item peg2  
   
 ID of the potentially coupled feature.  
   
 =item RETURN  
   
 Returns a three-element list. The first element contains the database ID of  
 the coupling. The second element is FALSE if the coupling is stored in the  
 database in the caller specified order and TRUE if it is stored in the  
 inverted order. The third element is the coupling's score. If the coupling  
 does not exist, all three list elements will be C<undef>.  
   
 =back  
   
 =cut  
 #: Return Type $%@;  
 sub GetCoupling {  
     # Get the parameters.  
     my ($self, $peg1, $peg2) = @_;  
     # Declare the return values. We'll start with the coupling ID and undefine the  
     # flag and score until we have more information.  
     my ($retVal, $inverted, $score) = ($self->CouplingID($peg1, $peg2), undef, undef);  
     # Find the coupling data.  
     my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],  
                                  "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",  
                                  [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);  
     # Check to see if we found anything.  
     if (!@pegs) {  
         Trace("No coupling found.") if T(Coupling => 4);  
         # No coupling, so undefine the return value.  
         $retVal = undef;  
     } else {  
         # We have a coupling! Get the score and check for inversion.  
         $score = $pegs[0]->[1];  
         my $firstFound = $pegs[0]->[0];  
         $inverted = ($firstFound ne $peg1);  
         Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);  
2090      }      }
2091      # Return the result.      # Return the result.
2092      return ($retVal, $inverted, $score);      return @retVal;
2093  }  }
2094    
2095  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2096    
2097  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2098    
2099  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2100    
# Line 1865  Line 2133 
2133    
2134  =head3 GetBoundaries  =head3 GetBoundaries
2135    
2136  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2137    
2138  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2139  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1927  Line 2195 
2195      return ($contig, $beg, $end);      return ($contig, $beg, $end);
2196  }  }
2197    
 =head3 CouplingID  
   
 C<< my $couplingID = $sprout->CouplingID($peg1, $peg2); >>  
   
 Return the coupling ID for a pair of feature IDs.  
   
 The coupling ID is currently computed by joining the feature IDs in  
 sorted order with a space. Client modules (that is, modules which  
 use Sprout) should not, however, count on this always being the  
 case. This method provides a way for abstracting the concept of a  
 coupling ID. All that we know for sure about it is that it can be  
 generated easily from the feature IDs and the order of the IDs  
 in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>  
 will have the same value as C<CouplingID("b1", "a1")>.  
   
 =over 4  
   
 =item peg1  
   
 First feature of interest.  
   
 =item peg2  
   
 Second feature of interest.  
   
 =item RETURN  
   
 Returns the ID that would be used to represent a functional coupling of  
 the two specified PEGs.  
   
 =back  
   
 =cut  
 #: Return Type $;  
 sub CouplingID {  
     my ($self, @pegs) = @_;  
     return $self->DigestKey(join " ", sort @pegs);  
 }  
   
2198  =head3 ReadFasta  =head3 ReadFasta
2199    
2200  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2201    
2202  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
2203  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 2034  Line 2263 
2263    
2264  =head3 FormatLocations  =head3 FormatLocations
2265    
2266  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2267    
2268  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
2269  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 2099  Line 2328 
2328    
2329  =head3 DumpData  =head3 DumpData
2330    
2331  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2332    
2333  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.
2334    
# Line 2116  Line 2345 
2345    
2346  =head3 XMLFileName  =head3 XMLFileName
2347    
2348  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2349    
2350  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2351    
# Line 2127  Line 2356 
2356      return $self->{_xmlName};      return $self->{_xmlName};
2357  }  }
2358    
2359  =head3 Insert  =head3 GetGenomeNameData
2360    
2361  C<< $sprout->Insert($objectType, \%fieldHash); >>      my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2362    
2363  Insert an entity or relationship instance into the database. The entity or relationship of interest  Return the genus, species, and unique characterization for a genome. This
2364  is defined by a type name and then a hash of field names to values. Field values in the primary  is similar to L</GenusSpecies>, with the exception that it returns the
2365  relation are represented by scalars. (Note that for relationships, the primary relation is  values in three seperate fields.
 the B<only> relation.) Field values for the other relations comprising the entity are always  
 list references. For example, the following line inserts an inactive PEG feature named  
 C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  
2366    
2367  C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>  =over 4
2368    
2369  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  =item genomeID
 property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  
2370    
2371  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  ID of the genome whose name data is desired.
2372    
2373  =over 4  =item RETURN
2374    
2375  =item newObjectType  Returns a three-element list, consisting of the genus, species, and strain
2376    of the specified genome. If the genome is not found, an error occurs.
2377    
2378  Type name of the entity or relationship to insert.  =back
2379    
2380    =cut
2381    
2382    sub GetGenomeNameData {
2383        # Get the parameters.
2384        my ($self, $genomeID) = @_;
2385        # Get the desired values.
2386        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2387                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2388        # Throw an error if they were not found.
2389        if (! defined $genus) {
2390            Confess("Genome $genomeID not found in database.");
2391        }
2392        # Return the results.
2393        return ($genus, $species, $strain);
2394    }
2395    
2396    =head3 GetGenomeByNameData
2397    
2398        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2399    
2400    Return a list of the IDs of the genomes with the specified genus,
2401    species, and strain. In almost every case, there will be either zero or
2402    one IDs returned; however, two or more IDs could be returned if there are
2403    multiple versions of the genome in the database.
2404    
2405    =over 4
2406    
2407    =item genus
2408    
2409    Genus of the desired genome.
2410    
2411    =item species
2412    
2413    Species of the desired genome.
2414    
2415    =item strain
2416    
2417    Strain (unique characterization) of the desired genome. This may be an empty
2418    string, in which case it is presumed that the desired genome has no strain
2419    specified.
2420    
2421    =item RETURN
2422    
2423    Returns a list of the IDs of the genomes having the specified genus, species, and
2424    strain.
2425    
2426    =back
2427    
2428    =cut
2429    
2430    sub GetGenomeByNameData {
2431        # Get the parameters.
2432        my ($self, $genus, $species, $strain) = @_;
2433        # Try to find the genomes.
2434        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2435                                    [$genus, $species, $strain], 'Genome(id)');
2436        # Return the result.
2437        return @retVal;
2438    }
2439    
2440    =head3 Insert
2441    
2442        $sprout->Insert($objectType, \%fieldHash);
2443    
2444    Insert an entity or relationship instance into the database. The entity or relationship of interest
2445    is defined by a type name and then a hash of field names to values. Field values in the primary
2446    relation are represented by scalars. (Note that for relationships, the primary relation is
2447    the B<only> relation.) Field values for the other relations comprising the entity are always
2448    list references. For example, the following line inserts an inactive PEG feature named
2449    C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2450    
2451        $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2452    
2453    The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2454    property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2455    
2456        $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2457    
2458    =over 4
2459    
2460    =item newObjectType
2461    
2462    Type name of the entity or relationship to insert.
2463    
2464  =item fieldHash  =item fieldHash
2465    
# Line 2168  Line 2478 
2478    
2479  =head3 Annotate  =head3 Annotate
2480    
2481  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2482    
2483  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
2484  specified feature and user.  specified feature and user.
# Line 2222  Line 2532 
2532    
2533  =head3 AssignFunction  =head3 AssignFunction
2534    
2535  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2536    
2537  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
2538  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2282  Line 2592 
2592    
2593  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2594    
2595  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2596    
2597  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
2598  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 2316  Line 2626 
2626          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2627      } else {      } else {
2628          # Here we have a non-FIG alias. Get the features with the normalized alias.          # Here we have a non-FIG alias. Get the features with the normalized alias.
2629          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2630      }      }
2631      # Return the result.      # Return the result.
2632      return @retVal;      return @retVal;
# Line 2324  Line 2634 
2634    
2635  =head3 FeatureTranslation  =head3 FeatureTranslation
2636    
2637  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2638    
2639  Return the translation of a feature.  Return the translation of a feature.
2640    
# Line 2352  Line 2662 
2662    
2663  =head3 Taxonomy  =head3 Taxonomy
2664    
2665  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2666    
2667  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
2668  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>,
2669  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2670    
2671  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2672    
2673  =over 4  =over 4
2674    
# Line 2393  Line 2703 
2703    
2704  =head3 CrudeDistance  =head3 CrudeDistance
2705    
2706  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2707    
2708  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
2709  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 2445  Line 2755 
2755    
2756  =head3 RoleName  =head3 RoleName
2757    
2758  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2759    
2760  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
2761  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 2479  Line 2789 
2789    
2790  =head3 RoleDiagrams  =head3 RoleDiagrams
2791    
2792  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2793    
2794  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2795    
# Line 2507  Line 2817 
2817      return @retVal;      return @retVal;
2818  }  }
2819    
 =head3 GetProperties  
   
 C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>  
   
 Return a list of the properties with the specified characteristics.  
   
 Properties are arbitrary key-value pairs associated with a feature. (At some point they  
 will also be associated with genomes.) A property value is represented by a 4-tuple of  
 the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  
   
 =over 4  
   
 =item fid  
   
 ID of the feature possessing the property.  
   
 =item key  
   
 Name or key of the property.  
   
 =item value  
   
 Value of the property.  
   
 =item url  
   
 URL of the document that indicated the property should have this particular value, or an  
 empty string if no such document exists.  
   
 =back  
   
 The parameters act as a filter for the desired data. Any non-null parameter will  
 automatically match all the tuples returned. So, specifying just the I<$fid> will  
 return all the properties of the specified feature; similarly, specifying the I<$key>  
 and I<$value> parameters will return all the features having the specified property  
 value.  
   
 A single property key can have many values, representing different ideas about the  
 feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
 virulent, and another may declare that it is not virulent. A query about the virulence of  
 C<fig|83333.1.peg.10> would be coded as  
   
     my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  
   
 Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  
 not to be filtered. The tuples returned would be  
   
     ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  
     ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  
   
 =cut  
 #: Return Type @@;  
 sub GetProperties {  
     # Get the parameters.  
     my ($self, @parms) = @_;  
     # Declare the return variable.  
     my @retVal = ();  
     # Now we need to create a WHERE clause that will get us the data we want. First,  
     # we create a list of the columns containing the data for each parameter.  
     my @colNames = ('HasProperty(from-link)', 'Property(property-name)',  
                     'Property(property-value)', 'HasProperty(evidence)');  
     # Now we build the WHERE clause and the list of parameter values.  
     my @where = ();  
     my @values = ();  
     for (my $i = 0; $i <= $#colNames; $i++) {  
         my $parm = $parms[$i];  
         if (defined $parm && ($parm ne '')) {  
             push @where, "$colNames[$i] = ?";  
             push @values, $parm;  
         }  
     }  
     # Format the WHERE clause.  
     my $filter = (@values > 0 ? (join " AND ", @where) : undef);  
     # Ask for all the propertie values with the desired characteristics.  
     my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);  
     while (my $valueObject = $query->Fetch()) {  
         my @tuple = $valueObject->Values(\@colNames);  
         push @retVal, \@tuple;  
     }  
     # Return the result.  
     return @retVal;  
 }  
   
2820  =head3 FeatureProperties  =head3 FeatureProperties
2821    
2822  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2823    
2824  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
2825  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
2826  that a feature is essential to the survival of the organism or that it has benign influence  that a feature is essential to the survival of the organism or that it has benign influence
2827  on the activities of a pathogen. Each property is returned as a triple of the form  on the activities of a pathogen. Each property is returned as a triple of the form
2828  C<($key,$value,$url)>, where C<$key> is the property name, C<$value> is its value (commonly  C<($key,@values)>, where C<$key> is the property name and  C<@values> are its values.
 a 1 or a 0, but possibly a string or a floating-point value), and C<$url> is a string describing  
 the web address or citation in which the property's value for the feature was identified.  
2829    
2830  =over 4  =over 4
2831    
# Line 2610  Line 2835 
2835    
2836  =item RETURN  =item RETURN
2837    
2838  Returns a list of triples, each triple containing the property name, its value, and a URL or  Returns a list of tuples, each tuple containing the property name and its values.
 citation.  
2839    
2840  =back  =back
2841    
# Line 2621  Line 2845 
2845      # Get the parameters.      # Get the parameters.
2846      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2847      # Get the properties.      # Get the properties.
2848      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2849                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2850                               'HasProperty(evidence)']);      my @retVal = ();
2851        for my $attributeRow (@attributes) {
2852            shift @{$attributeRow};
2853            push @retVal, $attributeRow;
2854        }
2855      # Return the resulting list.      # Return the resulting list.
2856      return @retVal;      return @retVal;
2857  }  }
2858    
2859  =head3 DiagramName  =head3 DiagramName
2860    
2861  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2862    
2863  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2864    
# Line 2656  Line 2884 
2884      return $retVal;      return $retVal;
2885  }  }
2886    
2887    =head3 PropertyID
2888    
2889        my $id = $sprout->PropertyID($propName, $propValue);
2890    
2891    Return the ID of the specified property name and value pair, if the
2892    pair exists. Only a small subset of the FIG attributes are stored as
2893    Sprout properties, mostly for use in search optimization.
2894    
2895    =over 4
2896    
2897    =item propName
2898    
2899    Name of the desired property.
2900    
2901    =item propValue
2902    
2903    Value expected for the desired property.
2904    
2905    =item RETURN
2906    
2907    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2908    
2909    =back
2910    
2911    =cut
2912    
2913    sub PropertyID {
2914        # Get the parameters.
2915        my ($self, $propName, $propValue) = @_;
2916        # Try to find the ID.
2917        my ($retVal) = $self->GetFlat(['Property'],
2918                                      "Property(property-name) = ? AND Property(property-value) = ?",
2919                                      [$propName, $propValue], 'Property(id)');
2920        # Return the result.
2921        return $retVal;
2922    }
2923    
2924  =head3 MergedAnnotations  =head3 MergedAnnotations
2925    
2926  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2927    
2928  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2929  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2707  Line 2972 
2972    
2973  =head3 RoleNeighbors  =head3 RoleNeighbors
2974    
2975  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2976    
2977  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
2978  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 2750  Line 3015 
3015    
3016  =head3 FeatureLinks  =head3 FeatureLinks
3017    
3018  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3019    
3020  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
3021  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 2781  Line 3046 
3046    
3047  =head3 SubsystemsOf  =head3 SubsystemsOf
3048    
3049  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3050    
3051  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
3052  to the roles the feature performs.  to the roles the feature performs.
# Line 2829  Line 3094 
3094    
3095  =head3 SubsystemList  =head3 SubsystemList
3096    
3097  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3098    
3099  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
3100  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2853  Line 3118 
3118      # Get the parameters.      # Get the parameters.
3119      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3120      # Get the list of names.      # Get the list of names.
3121      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      ##HACK: we do a join to the Subsystem table because we have missing subsystems in
3122                                  [$featureID], 'HasSSCell(from-link)');      ## the Sprout database!
3123      # Return the result.      my @retVal = $self->GetFlat(['HasRoleInSubsystem', 'Subsystem'], "HasRoleInSubsystem(from-link) = ?",
3124      return @retVal;                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3125        # Return the result, sorted.
3126        return sort @retVal;
3127  }  }
3128    
3129  =head3 GenomeSubsystemData  =head3 GenomeSubsystemData
3130    
3131  C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3132    
3133  Return a hash mapping genome features to their subsystem roles.  Return a hash mapping genome features to their subsystem roles.
3134    
# Line 2921  Line 3188 
3188    
3189  =head3 RelatedFeatures  =head3 RelatedFeatures
3190    
3191  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3192    
3193  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
3194  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 2972  Line 3239 
3239    
3240  =head3 TaxonomySort  =head3 TaxonomySort
3241    
3242  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3243    
3244  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3245  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 3007  Line 3274 
3274          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3275                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3276          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3277          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3278      }      }
3279      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3280      my @retVal = ();      my @retVal = ();
# Line 3020  Line 3287 
3287    
3288  =head3 Protein  =head3 Protein
3289    
3290  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3291    
3292  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3293    
# Line 3090  Line 3357 
3357      # Loop through the input triples.      # Loop through the input triples.
3358      my $n = length $sequence;      my $n = length $sequence;
3359      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3360          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3361          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3362            my $triple = uc substr($sequence, $i, 3);
3363          # Translate it using the table.          # Translate it using the table.
3364          my $protein = "X";          my $protein = "X";
3365          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3105  Line 3373 
3373    
3374  =head3 LoadInfo  =head3 LoadInfo
3375    
3376  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3377    
3378  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
3379  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 3124  Line 3392 
3392      return @retVal;      return @retVal;
3393  }  }
3394    
3395    =head3 BBHMatrix
3396    
3397        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3398    
3399    Find all the bidirectional best hits for the features of a genome in a
3400    specified list of target genomes. The return value will be a hash mapping
3401    features in the original genome to their bidirectional best hits in the
3402    target genomes.
3403    
3404    =over 4
3405    
3406    =item genomeID
3407    
3408    ID of the genome whose features are to be examined for bidirectional best hits.
3409    
3410    =item cutoff
3411    
3412    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3413    
3414    =item targets
3415    
3416    List of target genomes. Only pairs originating in the original
3417    genome and landing in one of the target genomes will be returned.
3418    
3419    =item RETURN
3420    
3421    Returns a hash mapping each feature in the original genome to a hash mapping its
3422    BBH pegs in the target genomes to their scores.
3423    
3424    =back
3425    
3426    =cut
3427    
3428    sub BBHMatrix {
3429        # Get the parameters.
3430        my ($self, $genomeID, $cutoff, @targets) = @_;
3431        # Declare the return variable.
3432        my %retVal = ();
3433        # Ask for the BBHs.
3434        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3435        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3436        for my $bbhData (@bbhList) {
3437            my ($peg1, $peg2, $score) = @{$bbhData};
3438            if (! exists $retVal{$peg1}) {
3439                $retVal{$peg1} = { $peg2 => $score };
3440            } else {
3441                $retVal{$peg1}->{$peg2} = $score;
3442            }
3443        }
3444        # Return the result.
3445        return %retVal;
3446    }
3447    
3448    
3449    =head3 SimMatrix
3450    
3451        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3452    
3453    Find all the similarities for the features of a genome in a
3454    specified list of target genomes. The return value will be a hash mapping
3455    features in the original genome to their similarites in the
3456    target genomes.
3457    
3458    =over 4
3459    
3460    =item genomeID
3461    
3462    ID of the genome whose features are to be examined for similarities.
3463    
3464    =item cutoff
3465    
3466    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3467    
3468    =item targets
3469    
3470    List of target genomes. Only pairs originating in the original
3471    genome and landing in one of the target genomes will be returned.
3472    
3473    =item RETURN
3474    
3475    Returns a hash mapping each feature in the original genome to a hash mapping its
3476    similar pegs in the target genomes to their scores.
3477    
3478    =back
3479    
3480    =cut
3481    
3482    sub SimMatrix {
3483        # Get the parameters.
3484        my ($self, $genomeID, $cutoff, @targets) = @_;
3485        # Declare the return variable.
3486        my %retVal = ();
3487        # Get the list of features in the source organism.
3488        my @fids = $self->FeaturesOf($genomeID);
3489        # Ask for the sims. We only want similarities to fig features.
3490        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3491        if (! defined $simList) {
3492            Confess("Unable to retrieve similarities from server.");
3493        } else {
3494            Trace("Processing sims.") if T(3);
3495            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3496            # Create a hash for the target genomes.
3497            my %targetHash = map { $_ => 1 } @targets;
3498            for my $simData (@{$simList}) {
3499                # Get the PEGs and the score.
3500                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3501                # Insure the second ID is in the target list.
3502                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3503                if (exists $targetHash{$genome2}) {
3504                    # Here it is. Now we need to add it to the return hash. How we do that depends
3505                    # on whether or not $peg1 is new to us.
3506                    if (! exists $retVal{$peg1}) {
3507                        $retVal{$peg1} = { $peg2 => $score };
3508                    } else {
3509                        $retVal{$peg1}->{$peg2} = $score;
3510                    }
3511                }
3512            }
3513        }
3514        # Return the result.
3515        return %retVal;
3516    }
3517    
3518    
3519  =head3 LowBBHs  =head3 LowBBHs
3520    
3521  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3522    
3523  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3524  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3159  Line 3551 
3551      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
3552      # Form the results into the return hash.      # Form the results into the return hash.
3553      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3554          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3555            if ($self->Exists('Feature', $fid)) {
3556                $retVal{$fid} = $pair->[1];
3557            }
3558      }      }
3559      # Return the result.      # Return the result.
3560      return %retVal;      return %retVal;
# Line 3167  Line 3562 
3562    
3563  =head3 Sims  =head3 Sims
3564    
3565  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3566    
3567  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
3568  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 3177  Line 3572 
3572  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3573  hits between features with similar DNA. Expanding a raw similarity drags in any  hits between features with similar DNA. Expanding a raw similarity drags in any
3574  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3575  B<A2>, and B<A3> are all substatially identical to B<A>, then a raw similarity  B<A2>, and B<A3> are all substantially identical to B<A>, then a raw similarity
3576  B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.  B<[C,A]> would be expanded to B<[C,A] [C,A1] [C,A2] [C,A3]>.
3577    
3578  =over 4  =over 4
3579    
3580  =item fid  =item fid
3581    
3582  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3583    of features whose similarities are desired.
3584    
3585  =item maxN  =item maxN
3586    
# Line 3230  Line 3626 
3626      return $retVal;      return $retVal;
3627  }  }
3628    
3629    =head3 IsAllGenomes
3630    
3631        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3632    
3633    Return TRUE if all genomes in the second list are represented in the first list at
3634    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3635    compared to a list of all the genomes.
3636    
3637    =over 4
3638    
3639    =item list
3640    
3641    Reference to the list to be compared to the second list.
3642    
3643    =item checkList (optional)
3644    
3645    Reference to the comparison target list. Every genome ID in this list must occur at
3646    least once in the first list. If this parameter is omitted, a list of all the genomes
3647    is used.
3648    
3649    =item RETURN
3650    
3651    Returns TRUE if every item in the second list appears at least once in the
3652    first list, else FALSE.
3653    
3654    =back
3655    
3656    =cut
3657    
3658    sub IsAllGenomes {
3659        # Get the parameters.
3660        my ($self, $list, $checkList) = @_;
3661        # Supply the checklist if it was omitted.
3662        $checkList = [$self->Genomes()] if ! defined($checkList);
3663        # Create a hash of the original list.
3664        my %testList = map { $_ => 1 } @{$list};
3665        # Declare the return variable. We assume that the representation
3666        # is complete and stop at the first failure.
3667        my $retVal = 1;
3668        my $n = scalar @{$checkList};
3669        for (my $i = 0; $retVal && $i < $n; $i++) {
3670            if (! $testList{$checkList->[$i]}) {
3671                $retVal = 0;
3672            }
3673        }
3674        # Return the result.
3675        return $retVal;
3676    }
3677    
3678  =head3 GetGroups  =head3 GetGroups
3679    
3680  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3681    
3682  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.
3683  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 3251  Line 3696 
3696          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3697          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3698          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3699              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3700                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3701              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3702          }          }
# Line 3259  Line 3704 
3704          # Here we need all of the groups. In this case, we run through all          # Here we need all of the groups. In this case, we run through all
3705          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3706          # group. Note that we use a filter clause to insure that only genomes          # group. Note that we use a filter clause to insure that only genomes
3707          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3708          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3709                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3710          # Loop through the genomes found.          # Loop through the genomes found.
3711          for my $genome (@genomes) {          for my $genome (@genomes) {
3712              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3713              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3714              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, $genomeID);  
             }  
3715          }          }
3716      }      }
3717      # Return the hash we just built.      # Return the hash we just built.
# Line 3280  Line 3720 
3720    
3721  =head3 MyGenomes  =head3 MyGenomes
3722    
3723  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3724    
3725  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3726    
# Line 3312  Line 3752 
3752    
3753  =head3 LoadFileName  =head3 LoadFileName
3754    
3755  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3756    
3757  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
3758  directory.  directory.
# Line 3353  Line 3793 
3793    
3794  =head3 DeleteGenome  =head3 DeleteGenome
3795    
3796  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3797    
3798  Delete a genome from the database.  Delete a genome from the database.
3799    
# Line 3379  Line 3819 
3819      # Get the parameters.      # Get the parameters.
3820      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3821      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3822      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3823      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3824      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3825      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3826      # Return the result.      # Return the result.
3827      return $retVal;      return $retVal;
# Line 3389  Line 3829 
3829    
3830  =head3 Fix  =head3 Fix
3831    
3832  C<< my %fixedHash = Sprout::Fix(%groupHash); >>      my %fixedHash = $sprout->Fix(%groupHash);
3833    
3834  Prepare a genome group hash (like that returned by L</GetGroups> for processing.  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3835  Groups with the same primary name will be combined. The primary name is the  The groups will be combined into the appropriate super-groups.
 first capitalized word in the group name.  
3836    
3837  =over 4  =over 4
3838    
# Line 3411  Line 3850 
3850    
3851  sub Fix {  sub Fix {
3852      # Get the parameters.      # Get the parameters.
3853      my (%groupHash) = @_;      my ($self, %groupHash) = @_;
3854      # Create the result hash.      # Create the result hash.
3855      my %retVal = ();      my %retVal = ();
3856      # Copy over the genomes.      # Copy over the genomes.
3857      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3858          # Make a safety copy of the group ID.          # Get the super-group name.
3859          my $realGroupID = $groupID;          my $realGroupID = $self->SuperGroup($groupID);
3860          # Yank the primary name.          # Append this group's genomes into the result hash
3861          if ($groupID =~ /([A-Z]\w+)/) {          # using the super-group name.
3862              $realGroupID = $1;          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
         }  
         # Append this group's genomes into the result hash.  
         Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});  
3863      }      }
3864      # Return the result hash.      # Return the result hash.
3865      return %retVal;      return %retVal;
3866  }  }
3867    
3868  =head3 ReadGroupFile  =head3 GroupPageName
3869    
3870  C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>      my $name = $sprout->GroupPageName($group);
3871    
3872  Read in the data from the specified group file. The group file contains information  Return the name of the page for the specified NMPDR group.
 about each of the NMPDR groups.  
3873    
3874  =over 4  =over 4
3875    
3876  =item name  =item group
3877    
3878  Name of the group.  Name of the relevant group.
3879    
3880  =item page  =item RETURN
3881    
3882  Name of the group's page on the web site (e.g. C<campy.php> for  Returns the relative page name (e.g. C<../content/campy.php>). If the group file is not in
3883  Campylobacter)  memory it will be read in.
3884    
3885  =item genus  =back
3886    
3887  Genus of the group  =cut
3888    
3889  =item species  sub GroupPageName {
3890        # Get the parameters.
3891        my ($self, $group) = @_;
3892        # Check for the group file data.
3893        my %superTable = $self->CheckGroupFile();
3894        # Compute the real group name.
3895        my $realGroup = $self->SuperGroup($group);
3896        # Get the associated page name.
3897        my $retVal = "../content/$superTable{$realGroup}->{page}";
3898        # Return the result.
3899        return $retVal;
3900    }
3901    
3902    
3903    =head3 AddProperty
3904    
3905        $sprout->AddProperty($featureID, $key, @values);
3906    
3907    Add a new attribute value (Property) to a feature.
3908    
3909    =over 4
3910    
3911    =item peg
3912    
3913    ID of the feature to which the attribute is to be added.
3914    
3915    =item key
3916    
3917    Name of the attribute (key).
3918    
3919  Species of the group, or an empty string if the group is for an entire  =item values
3920  genus. If the group contains more than one species, the species names  
3921  should be separated by commas.  Values of the attribute.
3922    
3923  =back  =back
3924    
3925  The parameters to this method are as follows  =cut
3926    #: Return Type ;
3927    sub AddProperty {
3928        # Get the parameters.
3929        my ($self, $featureID, $key, @values) = @_;
3930        # Add the property using the attached attributes object.
3931        $self->{_ca}->AddAttribute($featureID, $key, @values);
3932    }
3933    
3934    =head3 CheckGroupFile
3935    
3936        my %groupData = $sprout->CheckGroupFile();
3937    
3938    Get the group file hash. The group file hash describes the relationship
3939    between a group and the super-group to which it belongs for purposes of
3940    display. The super-group name is computed from the first capitalized word
3941    in the actual group name. For each super-group, the group file contains
3942    the page name and a list of the species expected to be in the group.
3943    Each species is specified by a genus and a species name. A species name
3944    of C<0> implies an entire genus.
3945    
3946    This method returns a hash from super-group names to a hash reference. Each
3947    resulting hash reference contains the following fields.
3948    
3949  =over 4  =over 4
3950    
3951  =item groupFile  =item page
3952    
3953  Name of the file containing the group data.  The super-group's web page in the NMPDR.
3954    
3955  =item RETURN  =item contents
3956    
3957  Returns a hash keyed on group name. The value of each hash  A list of 2-tuples, each containing a genus name followed by a species name
3958    (or 0, indicating all species). This list indicates which organisms belong
3959    in the super-group.
3960    
3961  =back  =back
3962    
3963  =cut  =cut
3964    
3965  sub ReadGroupFile {  sub CheckGroupFile {
3966      # Get the parameters.      # Get the parameters.
3967      my ($groupFileName) = @_;      my ($self) = @_;
3968      # Declare the return variable.      # Check to see if we already have this hash.
3969      my %retVal;      if (! defined $self->{groupHash}) {
3970            # We don't, so we need to read it in.
3971            my %groupHash;
3972      # Read the group file.      # Read the group file.
3973      my @groupLines = Tracer::GetFile($groupFileName);          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3974            # Loop through the list of sort-of groups.
3975      for my $groupLine (@groupLines) {      for my $groupLine (@groupLines) {
3976          my ($name, $page, $genus, $species) = split(/\t/, $groupLine);              my ($name, $page, @contents) = split /\t/, $groupLine;
3977          $retVal{$name} = [$page, $genus, $species];              $groupHash{$name} = { page => $page,
3978                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3979                                    };
3980            }
3981            # Save the hash.
3982            $self->{groupHash} = \%groupHash;
3983      }      }
3984      # Return the result.      # Return the result.
3985      return %retVal;      return %{$self->{groupHash}};
3986    }
3987    
3988    =head2 Virtual Methods
3989    
3990    =head3 CleanKeywords
3991    
3992        my $cleanedString = $sprout->CleanKeywords($searchExpression);
3993    
3994    Clean up a search expression or keyword list. This involves converting the periods
3995    in EC numbers to underscores, converting non-leading minus signs to underscores,
3996    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
3997    characters. In addition, any extra spaces are removed.
3998    
3999    =over 4
4000    
4001    =item searchExpression
4002    
4003    Search expression or keyword list to clean. Note that a search expression may
4004    contain boolean operators which need to be preserved. This includes leading
4005    minus signs.
4006    
4007    =item RETURN
4008    
4009    Cleaned expression or keyword list.
4010    
4011    =back
4012    
4013    =cut
4014    
4015    sub CleanKeywords {
4016        # Get the parameters.
4017        my ($self, $searchExpression) = @_;
4018        # Perform the standard cleanup.
4019        my $words = $self->ERDB::CleanKeywords($searchExpression);
4020        # Fix the periods in EC and TC numbers.
4021        $words =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4022        # Fix non-trailing periods.
4023        $words =~ s/\.(\w)/_$1/g;
4024        # Fix non-leading minus signs.
4025        $words =~ s/(\w)[\-]/$1_/g;
4026        # Fix the vertical bars and colons
4027        $words =~ s/(\w)[|:](\w)/$1'$2/g;
4028        # Now split up the list so that each keyword is in its own string. We keep the delimiters
4029        # because they may contain boolean expression data.
4030        my @words = split /([^A-Za-z'0-9_]+)/, $words;
4031        # We'll convert the stemmable words into stems and re-assemble the result.
4032        my $retVal = "";
4033        for my $word (@words) {
4034            my $stem = $self->Stem($word);
4035            if (defined $stem) {
4036                $retVal .= $stem;
4037            } else {
4038                $retVal .= $word;
4039            }
4040        }
4041        Trace("Cleaned keyword list for \"$searchExpression\" is \"$retVal\".") if T(3);
4042        # Return the result.
4043        return $retVal;
4044  }  }
4045    
4046  =head2 Internal Utility Methods  =head2 Internal Utility Methods
# Line 3500  Line 4053 
4053    
4054  A functional assignment is always of the form  A functional assignment is always of the form
4055    
4056      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4057        ZZZZ
4058    
4059  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,
4060  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 3553  Line 4107 
4107      return @retVal;      return @retVal;
4108  }  }
4109    
4110    =head3 _CheckFeature
4111    
4112        my $flag = $sprout->_CheckFeature($fid);
4113    
4114    Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4115    
4116    =over 4
4117    
4118    =item fid
4119    
4120    Feature ID to check.
4121    
4122    =item RETURN
4123    
4124    Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4125    
4126    =back
4127    
4128    =cut
4129    
4130    sub _CheckFeature {
4131        # Get the parameters.
4132        my ($self, $fid) = @_;
4133        # Insure we have a genome hash.
4134        if (! defined $self->{genomeHash}) {
4135            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4136            $self->{genomeHash} = \%genomeHash;
4137        }
4138        # Get the feature's genome ID.
4139        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4140        # Return an indicator of whether or not the genome ID is in the hash.
4141        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4142    }
4143    
4144  =head3 FriendlyTimestamp  =head3 FriendlyTimestamp
4145    
4146  Convert a time number to a user-friendly time stamp for display.  Convert a time number to a user-friendly time stamp for display.
# Line 3579  Line 4167 
4167      return $retVal;      return $retVal;
4168  }  }
4169    
 =head3 AddProperty  
   
 C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  
4170    
4171  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  =head3 Hint
 be added to almost any object. In Sprout, they can only be added to features. In  
 Sprout, attributes are implemented using I<properties>. A property represents a key/value  
 pair. If the particular key/value pair coming in is not already in the database, a new  
 B<Property> record is created to hold it.  
4172    
4173  =over 4      my $htmlText = SearchHelper::Hint($wikiPage, $hintText);
4174    
4175  =item peg  Return the HTML for a small question mark that displays the specified hint text when it is clicked.
4176    This HTML can be put in forms to provide a useful hinting mechanism.
4177    
4178  ID of the feature to which the attribute is to be replied.  =over 4
4179    
4180  =item key  =item wikiPage
4181    
4182  Name of the attribute (key).  Name of the wiki page to be popped up when the hint mark is clicked.
4183    
4184  =item value  =item hintText
4185    
4186  Value of the attribute.  Text to display for the hint. It is raw html, but may not contain any double quotes.
4187    
4188  =item url  =item RETURN
4189    
4190  URL or text citation from which the property was obtained.  Returns the html for the hint facility. The resulting html shows a small button-like thing that
4191    uses the standard FIG popup technology.
4192    
4193  =back  =back
4194    
4195  =cut  =cut
4196  #: Return Type ;  
4197  sub AddProperty {  sub Hint {
4198      # Get the parameters.      # Get the parameters.
4199      my ($self, $featureID, $key, $value, $url) = @_;      my ($wikiPage, $hintText) = @_;
4200      # Declare the variable to hold the desired property ID.      # Escape the single quotes in the hint text.
4201      my $propID;      my $quotedText = $hintText;
4202      # Attempt to find a property record for this key/value pair.      $quotedText =~ s/'/\\'/g;
4203      my @properties = $self->GetFlat(['Property'],      # Convert the wiki page name to a URL.
4204                                     "Property(property-name) = ? AND Property(property-value) = ?",      my $wikiURL = join("", map { ucfirst $_ } split /\s+/, $wikiPage);
4205                                     [$key, $value], 'Property(id)');      $wikiURL = "$FIG_Config::cgi_url/wiki/view.cgi/FIG/$wikiURL";
4206      if (@properties) {      # Compute the mouseover script.
4207          # Here the property is already in the database. We save its ID.      my $mouseOver = "doTooltip(this, '$quotedText')";
4208          $propID = $properties[0];      # Create the html.
4209          # Here the property value does not exist. We need to generate an ID. It will be set      my $retVal = "&nbsp;<a href=\"$wikiURL\"><img src=\"$FIG_Config::cgi_url/Html/button-h.png\" class=\"helpicon\" onmouseover=\"$mouseOver\"/></a>";
4210          # to a number one greater than the maximum value in the database. This call to      # Return it.
4211          # GetAll will stop after one record.      return $retVal;
         my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],  
                                         1);  
         $propID = $maxProperty[0]->[0] + 1;  
         # Insert the new property value.  
         $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });  
     }  
     # Now we connect the incoming feature to the property.  
     $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });  
4212  }  }
4213    
   
4214  1;  1;

Legend:
Removed from v.1.84  
changed lines
  Added in v.1.115

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3