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

Diff of /Sprout/Sprout.pm

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

revision 1.85, Tue Sep 19 00:14:04 2006 UTC revision 1.109, Sun Mar 23 16:32:05 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 base qw(ERDB);
19    
20  =head1 Sprout Database Manipulation Object  =head1 Sprout Database Manipulation Object
21    
# Line 28  Line 28 
28  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>
29  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>.
30    
31  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' });
32    
33  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
34  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
35  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
36  L</dna_seq> returns the DNA sequence for a specified genome location.  L</DNASeq> returns the DNA sequence for a specified genome location.
37    
38  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.
39    
# Line 45  Line 45 
45    
46  =head3 new  =head3 new
47    
48  C<< my $sprout = Sprout->new($dbName, \%options); >>      my $sprout = Sprout->new($dbName, \%options);
49    
50  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
51  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 79 
79    
80  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE  * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
81    
82    * B<host> name of the database host
83    
84  =back  =back
85    
86  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
87  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
88  F</usr/fig/SproutData>.  F</usr/fig/SproutData>.
89    
90  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' });
91    
92  =cut  =cut
93    
# Line 109  Line 111 
111                         port         => $FIG_Config::dbport,                         port         => $FIG_Config::dbport,
112                                                          # database connection port                                                          # database connection port
113                         sock         => $FIG_Config::dbsock,                         sock         => $FIG_Config::dbsock,
114                         host         => $FIG_Config::dbhost,                         host         => $FIG_Config::sprout_host,
115                         maxSegmentLength => 4500,        # maximum feature segment length                         maxSegmentLength => 4500,        # maximum feature segment length
116                         maxSequenceLength => 8000,       # maximum contig sequence length                         maxSequenceLength => 8000,       # maximum contig sequence length
117                         noDBOpen     => 0,               # 1 to suppress the database open                         noDBOpen     => 0,               # 1 to suppress the database open
# Line 122  Line 124 
124      # Connect to the database.      # Connect to the database.
125      my $dbh;      my $dbh;
126      if (! $optionTable->{noDBOpen}) {      if (! $optionTable->{noDBOpen}) {
127            Trace("Connect data: host = $optionTable->{host}, port = $optionTable->{port}.") if T(3);
128          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,          $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
129                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});                                  $password, $optionTable->{port}, $optionTable->{host}, $optionTable->{sock});
130      }      }
# Line 133  Line 136 
136      $retVal->{_xmlName} = $xmlFileName;      $retVal->{_xmlName} = $xmlFileName;
137      # Set up space for the group file data.      # Set up space for the group file data.
138      $retVal->{groupHash} = undef;      $retVal->{groupHash} = undef;
139        # Set up space for the genome hash. We use this to identify NMPDR genomes.
140        $retVal->{genomeHash} = undef;
141        # Connect to the attributes.
142        if ($FIG_Config::attrURL) {
143            Trace("Remote attribute server $FIG_Config::attrURL chosen.") if T(3);
144            $retVal->{_ca} = RemoteCustomAttributes->new($FIG_Config::attrURL);
145        } elsif ($FIG_Config::attrDbName) {
146            Trace("Local attribute database $FIG_Config::attrDbName chosen.") if T(3);
147            my $user = ($FIG_Config::arch eq 'win' ? 'self' : scalar(getpwent()));
148            $retVal->{_ca} = CustomAttributes->new(user => $user);
149        }
150      # Return it.      # Return it.
151      return $retVal;      return $retVal;
152  }  }
153    
154    =head3 CoreGenomes
155    
156        my @genomes = $sprout->CoreGenomes($scope);
157    
158    Return the IDs of NMPDR genomes in the specified scope.
159    
160    =over 4
161    
162    =item scope
163    
164    Scope of the desired genomes. C<core> covers the original core genomes,
165    C<nmpdr> covers all genomes in NMPDR groups, and C<all> covers all
166    genomes in the system.
167    
168    =item RETURN
169    
170    Returns a list of the IDs for the genomes in the specified scope.
171    
172    =back
173    
174    =cut
175    
176    sub CoreGenomes {
177        # Get the parameters.
178        my ($self, $scope) = @_;
179        # Declare the return variable.
180        my @retVal = ();
181        # If we want all genomes, then this is easy.
182        if ($scope eq 'all') {
183            @retVal = $self->Genomes();
184        } else {
185            # Here we're dealing with groups. Get the hash of all the
186            # genome groups.
187            my %groups = $self->GetGroups();
188            # Loop through the groups, keeping the ones that we want.
189            for my $group (keys %groups) {
190                # Decide if we want to keep this group.
191                my $keepGroup = 0;
192                if ($scope eq 'nmpdr') {
193                    # NMPDR mode: keep all groups.
194                    $keepGroup = 1;
195                } elsif ($scope eq 'core') {
196                    # CORE mode. Only keep real core groups.
197                    if (grep { $group =~ /$_/ } @{$FIG_Config::realCoreGroups}) {
198                        $keepGroup = 1;
199                    }
200                }
201                # Add this group if we're keeping it.
202                if ($keepGroup) {
203                    push @retVal, @{$groups{$group}};
204                }
205            }
206        }
207        # Return the result.
208        return @retVal;
209    }
210    
211    =head3 SuperGroup
212    
213        my $superGroup = $sprout->SuperGroup($groupName);
214    
215    Return the name of the super-group containing the specified NMPDR genome
216    group. If no appropriate super-group can be found, an error will be
217    thrown.
218    
219    =over 4
220    
221    =item groupName
222    
223    Name of the group whose super-group is desired.
224    
225    =item RETURN
226    
227    Returns the name of the super-group containing the incoming group.
228    
229    =back
230    
231    =cut
232    
233    sub SuperGroup {
234        # Get the parameters.
235        my ($self, $groupName) = @_;
236        # Declare the return variable.
237        my $retVal;
238        # Get the group hash.
239        my %groupHash = $self->CheckGroupFile();
240        # Find the super-group genus.
241        $groupName =~ /([A-Z]\w+)/;
242        my $nameThing = $1;
243        # See if it's directly in the group hash.
244        if (exists $groupHash{$nameThing}) {
245            # Yes, then it's our result.
246            $retVal = $nameThing;
247        } else {
248            # No, so we have to search.
249            for my $superGroup (keys %groupHash) {
250                # Get this super-group's item list.
251                my $list = $groupHash{$superGroup}->{contents};
252                # Search it.
253                if (grep { $_->[0] eq $nameThing } @{$list}) {
254                    $retVal = $superGroup;
255                }
256            }
257            # Make sure we found something.
258            if (! $retVal) {
259                Confess("No super-group found for \"$groupName\".");
260            }
261        }
262        # Return the result.
263        return $retVal;
264    }
265    
266  =head3 MaxSegment  =head3 MaxSegment
267    
268  C<< my $length = $sprout->MaxSegment(); >>      my $length = $sprout->MaxSegment();
269    
270  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
271  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 156  Line 282 
282    
283  =head3 MaxSequence  =head3 MaxSequence
284    
285  C<< my $length = $sprout->MaxSequence(); >>      my $length = $sprout->MaxSequence();
286    
287  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
288  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 171  Line 297 
297    
298  =head3 Load  =head3 Load
299    
300  C<< $sprout->Load($rebuild); >>;      $sprout->Load($rebuild);;
301    
302  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.
303    
# Line 211  Line 337 
337    
338  =head3 LoadUpdate  =head3 LoadUpdate
339    
340  C<< my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList); >>      my $stats = $sprout->LoadUpdate($truncateFlag, \@tableList);
341    
342  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
343  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 257  Line 383 
383              Trace("No load file found for $tableName in $dataDir.") if T(0);              Trace("No load file found for $tableName in $dataDir.") if T(0);
384          } else {          } else {
385              # Attempt to load this table.              # Attempt to load this table.
386              my $result = $self->LoadTable($fileName, $tableName, $truncateFlag);              my $result = $self->LoadTable($fileName, $tableName, truncate => $truncateFlag);
387              # Accumulate the resulting statistics.              # Accumulate the resulting statistics.
388              $retVal->Accumulate($result);              $retVal->Accumulate($result);
389          }          }
# Line 268  Line 394 
394    
395  =head3 GenomeCounts  =head3 GenomeCounts
396    
397  C<< my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete); >>      my ($arch, $bact, $euk, $vir, $env, $unk) = $sprout->GenomeCounts($complete);
398    
399  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
400  genomes will be included in the counts.  genomes will be included in the counts.
# Line 313  Line 439 
439    
440  =head3 ContigCount  =head3 ContigCount
441    
442  C<< my $count = $sprout->ContigCount($genomeID); >>      my $count = $sprout->ContigCount($genomeID);
443    
444  Return the number of contigs for the specified genome ID.  Return the number of contigs for the specified genome ID.
445    
# Line 340  Line 466 
466      return $retVal;      return $retVal;
467  }  }
468    
469  =head3 GeneMenu  =head3 GenomeMenu
470    
471  C<< my $selectHtml = $sprout->GeneMenu(\%attributes, $filterString, \@params, $selected); >>      my $html = $sprout->GenomeMenu(%options);
472    
473  Return an HTML select menu of genomes. Each genome will be an option in the menu,  Generate a genome selection control with the specified name and options.
474  and will be displayed by name with the ID and a contig count attached. The selection  This control is almost but not quite the same as the genome control in the
475  value will be the genome ID. The genomes will be sorted by genus/species name.  B<SearchHelper> class. Eventually, the two will be combined.
476    
477  =over 4  =over 4
478    
479  =item attributes  =item options
   
 Reference to a hash mapping attributes to values for the SELECT tag generated.  
480    
481  =item filterString  Optional parameters for the control (see below).
482    
483  A filter string for use in selecting the genomes. The filter string must conform  =item RETURN
 to the rules for the C<< ERDB->Get >> method.  
484    
485  =item params  Returns the HTML for a genome selection control on a form (sometimes called a popup menu).
486    
487  Reference to a list of values to be substituted in for the parameter marks in  =back
 the filter string.  
488    
489  =item selected (optional)  The valid options are as follows.
490    
491  ID of the genome to be initially selected.  =over 4
492    
493  =item fast (optional)  =item name
494    
495  If specified and TRUE, the contig counts will be omitted to improve performance.  Name to give this control for use in passing it to the form. The default is C<myGenomeControl>.
496    Terrible things will happen if you have two controls with the same name on the same page.
497    
498  =item RETURN  =item filter
499    
500  Returns an HTML select menu with the specified genomes as selectable options.  If specified, a filter for the list of genomes to display. The filter should be in the form of a
501    list reference. The first element of the list should be the filter string, and the remaining elements
502    the filter parameters.
503    
504    =item multiSelect
505    
506    If TRUE, then the user can select multiple genomes. If FALSE, the user can only select one genome.
507    
508    =item size
509    
510    Number of rows to display in the control. The default is C<10>
511    
512    =item id
513    
514    ID to give this control. The default is the value of the C<name> option. Nothing will work correctly
515    unless this ID is unique.
516    
517    =item selected
518    
519    A comma-delimited list of selected genomes, or a reference to a list of selected genomes. The
520    default is none.
521    
522    =item inTable
523    
524    If TRUE, then backslashes will be included at the end of each line in the resulting HTML. This enables the control
525    to be used in TWiki tables.
526    
527  =back  =back
528    
529  =cut  =cut
530    
531  sub GeneMenu {  sub GenomeMenu {
532      # Get the parameters.      # Get the parameters.
533      my ($self, $attributes, $filterString, $params, $selected, $fast) = @_;      my ($self, %options) = @_;
534      my $slowMode = ! $fast;      # Get the control's name and ID.
535      # Default to nothing selected. This prevents an execution warning if "$selected"      my $menuName = $options{name} || 'myGenomeControl';
536      # is undefined.      my $menuID = $options{id} || $menuName;
537      $selected = "" unless defined $selected;      # Compute the IDs for the status display.
538      Trace("Gene Menu called with slow mode \"$slowMode\" and selection \"$selected\".") if T(3);      my $divID = "${menuID}_status";
539      # Start the menu.      my $urlID = "${menuID}_url";
540      my $retVal = "<select " .      # Compute the code to show selected genomes in the status area.
541          join(" ", map { "$_=\"$attributes->{$_}\"" } keys %{$attributes}) .      my $showSelect = "showSelected('$menuID', '$divID', '$urlID', 1000)";
542          ">\n";      # Check for single-select or multi-select.
543      # Get the genomes.      my $multiSelect = $options{multiSelect} || 0;
544      my @genomes = $self->GetAll(['Genome'], $filterString, $params, ['Genome(id)',      # Get the list of pre-selected items.
545                                                                       'Genome(genus)',      my $selections = $options{selected} || [];
546                                                                       'Genome(species)',      if (ref $selections ne 'ARRAY') {
547                                                                       'Genome(unique-characterization)']);          $selections = [ split /\s*,\s*/, $selections ];
548      # Sort them by name.      }
549      my @sorted = sort { lc("$a->[1] $a->[2]") cmp lc("$b->[1] $b->[2]") } @genomes;      my %selected = map { $_ => } @{$selections};
550      # Loop through the genomes, creating the option tags.      # Extract the filter information. The default is no filtering. It can be passed as a tab-delimited
551      for my $genomeData (@sorted) {      # string or a list reference.
552          # Get the data for this genome.      my $filterParms = $options{filter} || "";
553          my ($genomeID, $genus, $species, $strain) = @{$genomeData};      if (! ref $filterParms) {
554          # Get the contig count.          $filterParms = [split /\t|\\t/, $filterParms];
555          my $contigInfo = "";      }
556          if ($slowMode) {      my $filterString = shift @{$filterParms};
557              my $count = $self->ContigCount($genomeID);      # Get a list of all the genomes in group order. In fact, we only need them ordered
558              my $counting = ($count == 1 ? "contig" : "contigs");      # by name (genus,species,strain), but putting primary-group in front enables us to
559              $contigInfo = "[$count $counting]";      # take advantage of an existing index.
560          }      my @genomeList = $self->GetAll(['Genome'], "$filterString ORDER BY Genome(primary-group), Genome(genus), Genome(species), Genome(unique-characterization)",
561          # Find out if we're selected.                                     $filterParms,
562          my $selectOption = ($selected eq $genomeID ? " selected" : "");                                     [qw(Genome(primary-group) Genome(id) Genome(genus) Genome(species) Genome(unique-characterization) Genome(taxonomy) Genome(contigs))]);
563          # Build the option tag.      # Create a hash to organize the genomes by group. Each group will contain a list of
564          $retVal .= "<option value=\"$genomeID\"$selectOption>$genus $species $strain ($genomeID)$contigInfo</option>\n";      # 2-tuples, the first element being the genome ID and the second being the genome
565        # name.
566        my %gHash = ();
567        for my $genome (@genomeList) {
568            # Get the genome data.
569            my ($group, $genomeID, $genus, $species, $strain, $taxonomy, $contigs) = @{$genome};
570            # Compute its name. This is the genus, species, strain (if any), and the contig count.
571            my $name = "$genus $species ";
572            $name .= "$strain " if $strain;
573            my $contigCount = ($contigs == 1 ? "" : ", $contigs contigs");
574            # Now we get the domain. The domain tells us the display style of the organism.
575            my ($domain) = split /\s*;\s*/, $taxonomy, 2;
576            # Now compute the display group. This is normally the primary group, but if the
577            # organism is supporting, we blank it out.
578            my $displayGroup = ($group eq $FIG_Config::otherGroup ? "" : $group);
579            # Push the genome into the group's list. Note that we use the real group
580            # name for the hash key here, not the display group name.
581            push @{$gHash{$group}}, [$genomeID, $name, $contigCount, $domain];
582        }
583        # We are almost ready to unroll the menu out of the group hash. The final step is to separate
584        # the supporting genomes by domain. First, we extract the NMPDR groups and sort them. They
585        # are sorted by the first capitalized word. Groups with "other" are sorted after groups
586        # that aren't "other". At some point, we will want to make this less complicated.
587        my %sortGroups = map { $_ =~ /(other)?(.*)([A-Z].+)/; "$3$1$2" => $_ }
588                             grep { $_ ne $FIG_Config::otherGroup } keys %gHash;
589        my @groups = map { $sortGroups{$_} } sort keys %sortGroups;
590        # Remember the number of NMPDR groups.
591        my $nmpdrGroupCount = scalar @groups;
592        # Loop through the supporting genomes, classifying them by domain. We'll also keep a list
593        # of the domains found.
594        my @otherGenomes = @{$gHash{$FIG_Config::otherGroup}};
595        my @domains = ();
596        for my $genomeData (@otherGenomes) {
597            my ($genomeID, $name, $contigCount, $domain) = @{$genomeData};
598            if (exists $gHash{$domain}) {
599                push @{$gHash{$domain}}, $genomeData;
600            } else {
601                $gHash{$domain} = [$genomeData];
602                push @domains, $domain;
603            }
604        }
605        # Add the domain groups at the end of the main group list. The main group list will now
606        # contain all the categories we need to display the genomes.
607        push @groups, sort @domains;
608        # Delete the supporting group.
609        delete $gHash{$FIG_Config::otherGroup};
610        # Now it gets complicated. We need a way to mark all the NMPDR genomes. We take advantage
611        # of the fact they come first in the list. We'll accumulate a count of the NMPDR genomes
612        # and use that to make the selections.
613        my $nmpdrCount = 0;
614        # Create the type counters.
615        my $groupCount = 1;
616        # Get the number of rows to display.
617        my $rows = $options{size} || 10;
618        # If we're multi-row, create an onChange event.
619        my $onChangeTag = ( $rows > 1 ? " onChange=\"$showSelect;\" onFocus=\"$showSelect;\"" : "" );
620        # Set up the multiple-select flag.
621        my $multipleTag = ($multiSelect ? " multiple" : "" );
622        # Create the SELECT tag and stuff it into the output array.
623        my @lines = ("<SELECT name=\"$menuID\" id=\"$menuID\" $onChangeTag$multipleTag size=\"$rows\" style=\"width: 100%\">");
624        # Loop through the groups.
625        for my $group (@groups) {
626            # Get the genomes in the group.
627            for my $genome (@{$gHash{$group}}) {
628                # If this is an NMPDR organism, we add an extra style and count it.
629                my $nmpdrStyle = "";
630                if ($nmpdrGroupCount > 0) {
631                    $nmpdrCount++;
632                    $nmpdrStyle = " Core";
633                }
634                # Get the organism ID, name, contig count, and domain.
635                my ($genomeID, $name, $contigCount, $domain) = @{$genome};
636                # See if we're pre-selected.
637                my $selectTag = ($selected{$genomeID} ? " SELECTED" : "");
638                # Compute the display name.
639                my $nameString = "$name ($genomeID$contigCount)";
640                # Generate the option tag.
641                my $optionTag = "<OPTION class=\"$domain$nmpdrStyle\" title=\"$group\" value=\"$genomeID\"$selectTag>$nameString</OPTION>";
642                push @lines, "    $optionTag";
643            }
644            # Record this group in the nmpdrGroup count. When that gets to 0, we've finished the NMPDR
645            # groups.
646            $nmpdrGroupCount--;
647      }      }
648      # Close the SELECT tag.      # Close the SELECT tag.
649      $retVal .= "</select>\n";      push @lines, "</SELECT>";
650        if ($rows > 1) {
651            # We're in a non-compact mode, so we need to add some selection helpers. First is
652            # the search box. This allows the user to type text and change which genomes are
653            # displayed. For multiple-select mode, we include a button that selects the displayed
654            # genes. For single-select mode, we use a plain label instead.
655            my $searchThingName = "${menuID}_SearchThing";
656            my $searchThingLabel = ($multiSelect ? "<INPUT type=\"button\" name=\"MacroSearch\" class=\"button\" value=\"Select genomes containing\" onClick=\"selectShowing('$menuID', '$searchThingName'); $showSelect;\" />"
657                                                 : "Show genomes containing");
658            push @lines, "<br />$searchThingLabel&nbsp;" .
659                         "<INPUT type=\"text\" id=\"$searchThingName\" name=\"$searchThingName\" size=\"30\" onKeyup=\"showTyped('$menuID', '$searchThingName');\" />";
660            # For multi-select mode, we also have buttons to set and clear selections.
661            if ($multiSelect) {
662                push @lines, "<INPUT type=\"button\" name=\"ClearAll\" class=\"bigButton\"  value=\"Clear All\" onClick=\"clearAll('$menuID'); $showSelect\" />";
663                push @lines, "<INPUT type=\"button\" name=\"SelectAll\" class=\"bigButton\" value=\"Select All\" onClick=\"selectAll('$menuID'); $showSelect\" />";
664                push @lines, "<INPUT type=\"button\" name=\"NMPDROnly\" class=\"bigButton\"  value=\"Select NMPDR\" onClick=\"selectSome('$menuID', $nmpdrCount, true); $showSelect;\" />";
665            }
666            # Add a hidden field we can use to generate organism page hyperlinks.
667            push @lines, "<INPUT type=\"hidden\" id=\"$urlID\" value=\"$FIG_Config::cgi_url/seedviewer.cgi?page=Organism;organism=\" />";
668            # Add the status display. This tells the user what's selected no matter where the list is scrolled.
669            push @lines, "<DIV id=\"$divID\" class=\"Panel\"></DIV>";
670        }
671        # Assemble all the lines into a string. This is where we do the "inTable" thing to insure we don't mess up TWiki tables.
672        my $delim = ($options{inTable} ? "\\" : "" ) . "\n";
673        my $retVal = join($delim, @lines, "");
674      # Return the result.      # Return the result.
675      return $retVal;      return $retVal;
676  }  }
677    
678    
679  =head3 Build  =head3 Build
680    
681  C<< $sprout->Build(); >>      $sprout->Build();
682    
683  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.
684  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 440  Line 695 
695    
696  =head3 Genomes  =head3 Genomes
697    
698  C<< my @genomes = $sprout->Genomes(); >>      my @genomes = $sprout->Genomes();
699    
700  Return a list of all the genome IDs.  Return a list of all the genome IDs.
701    
# Line 457  Line 712 
712    
713  =head3 GenusSpecies  =head3 GenusSpecies
714    
715  C<< my $infoString = $sprout->GenusSpecies($genomeID); >>      my $infoString = $sprout->GenusSpecies($genomeID);
716    
717  Return the genus, species, and unique characterization for a genome.  Return the genus, species, and unique characterization for a genome.
718    
# Line 489  Line 744 
744    
745  =head3 FeaturesOf  =head3 FeaturesOf
746    
747  C<< my @features = $sprout->FeaturesOf($genomeID, $ftype); >>      my @features = $sprout->FeaturesOf($genomeID, $ftype);
748    
749  Return a list of the features relevant to a specified genome.  Return a list of the features relevant to a specified genome.
750    
# Line 534  Line 789 
789    
790  =head3 FeatureLocation  =head3 FeatureLocation
791    
792  C<< my @locations = $sprout->FeatureLocation($featureID); >>      my @locations = $sprout->FeatureLocation($featureID);
793    
794  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
795  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 563  Line 818 
818  =back  =back
819    
820  =cut  =cut
821  #: Return Type @;  
 #: Return Type $;  
822  sub FeatureLocation {  sub FeatureLocation {
823      # Get the parameters.      # Get the parameters.
824      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
825      # Create a query for the feature locations.      # Get the feature record.
826      my $query = $self->Get(['IsLocatedIn'], "IsLocatedIn(from-link) = ? ORDER BY IsLocatedIn(locN)",      my $object = $self->GetEntity('Feature', $featureID);
827                             [$featureID]);      Confess("Feature $featureID not found.") if ! defined($object);
828        # Get the location string.
829        my $locString = $object->PrimaryValue('Feature(location-string)');
830      # Create the return list.      # Create the return list.
831      my @retVal = ();      my @retVal = split /\s*,\s*/, $locString;
     # Set up the variables used to determine if we have adjacent segments. This initial setup will  
     # not match anything.  
     my ($prevContig, $prevBeg, $prevDir, $prevLen) = ("", 0, "0", 0);  
     # Loop through the query results, creating location specifiers.  
     while (my $location = $query->Fetch()) {  
         # Get the location parameters.  
         my ($contigID, $beg, $dir, $len) = $location->Values(['IsLocatedIn(to-link)',  
             'IsLocatedIn(beg)', 'IsLocatedIn(dir)', 'IsLocatedIn(len)']);  
         # Check to see if we are adjacent to the previous segment.  
         if ($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$len";  
     }  
832      # Return the list in the format indicated by the context.      # Return the list in the format indicated by the context.
833      return (wantarray ? @retVal : join(',', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
834  }  }
835    
836  =head3 ParseLocation  =head3 ParseLocation
837    
838  C<< my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location); >>      my ($contigID, $start, $dir, $len) = Sprout::ParseLocation($location);
839    
840  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
841  length.  length.
# Line 632  Line 854 
854  =back  =back
855    
856  =cut  =cut
857  #: Return Type @;  
858  sub ParseLocation {  sub ParseLocation {
859      # 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
860      # the first parameter.      # the first parameter.
# Line 659  Line 881 
881    
882  =head3 PointLocation  =head3 PointLocation
883    
884  C<< my $found = Sprout::PointLocation($location, $point); >>      my $found = Sprout::PointLocation($location, $point);
885    
886  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
887  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 688  Line 910 
910  =back  =back
911    
912  =cut  =cut
913  #: Return Type $;  
914  sub PointLocation {  sub PointLocation {
915      # 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
916      # the first parameter.      # the first parameter.
# Line 711  Line 933 
933    
934  =head3 DNASeq  =head3 DNASeq
935    
936  C<< my $sequence = $sprout->DNASeq(\@locationList); >>      my $sequence = $sprout->DNASeq(\@locationList);
937    
938  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
939  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 795  Line 1017 
1017    
1018  =head3 AllContigs  =head3 AllContigs
1019    
1020  C<< my @idList = $sprout->AllContigs($genomeID); >>      my @idList = $sprout->AllContigs($genomeID);
1021    
1022  Return a list of all the contigs for a genome.  Return a list of all the contigs for a genome.
1023    
# Line 825  Line 1047 
1047    
1048  =head3 GenomeLength  =head3 GenomeLength
1049    
1050  C<< my $length = $sprout->GenomeLength($genomeID); >>      my $length = $sprout->GenomeLength($genomeID);
1051    
1052  Return the length of the specified genome in base pairs.  Return the length of the specified genome in base pairs.
1053    
# Line 860  Line 1082 
1082    
1083  =head3 FeatureCount  =head3 FeatureCount
1084    
1085  C<< my $count = $sprout->FeatureCount($genomeID, $type); >>      my $count = $sprout->FeatureCount($genomeID, $type);
1086    
1087  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.
1088    
# Line 895  Line 1117 
1117    
1118  =head3 GenomeAssignments  =head3 GenomeAssignments
1119    
1120  C<< my $fidHash = $sprout->GenomeAssignments($genomeID); >>      my $fidHash = $sprout->GenomeAssignments($genomeID);
1121    
1122  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
1123  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 921  Line 1143 
1143      my ($self, $genomeID) = @_;      my ($self, $genomeID) = @_;
1144      # Declare the return variable.      # Declare the return variable.
1145      my $retVal = {};      my $retVal = {};
1146      # Query the genome's features and annotations. We'll put the oldest annotations      # Query the genome's features.
1147      # 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 = $self->Get(['HasFeature', 'IsTargetOfAnnotation', 'Annotation'],  
                            "HasFeature(from-link) = ? ORDER BY Annotation(time)",  
1148                             [$genomeID]);                             [$genomeID]);
1149      # Loop through the annotations.      # Loop through the features.
1150      while (my $data = $query->Fetch) {      while (my $data = $query->Fetch) {
1151          # Get the feature ID and annotation text.          # Get the feature ID and assignment.
1152          my ($fid, $annotation) = $data->Values(['HasFeature(to-link)',          my ($fid, $assignment) = $data->Values(['Feature(id)', 'Feature(assignment)']);
1153                                                  'Annotation(annotation)']);          if ($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.  
1154              $retVal->{$fid} = $assignment;              $retVal->{$fid} = $assignment;
1155          }          }
1156      }      }
# Line 947  Line 1160 
1160    
1161  =head3 ContigLength  =head3 ContigLength
1162    
1163  C<< my $length = $sprout->ContigLength($contigID); >>      my $length = $sprout->ContigLength($contigID);
1164    
1165  Compute the length of a contig.  Compute the length of a contig.
1166    
# Line 986  Line 1199 
1199    
1200  =head3 ClusterPEGs  =head3 ClusterPEGs
1201    
1202  C<< my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs); >>      my $clusteredList = $sprout->ClusterPEGs($sub, \@pegs);
1203    
1204  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
1205  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
1206  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
1207  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
1208  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
1209  sequence.  appear in the output sequence.
1210    
1211  =over 4  =over 4
1212    
# Line 1034  Line 1247 
1247    
1248  =head3 GenesInRegion  =head3 GenesInRegion
1249    
1250  C<< my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop); >>      my (\@featureIDList, $beg, $end) = $sprout->GenesInRegion($contigID, $start, $stop);
1251    
1252  List the features which overlap a specified region in a contig.  List the features which overlap a specified region in a contig.
1253    
# Line 1063  Line 1276 
1276  =back  =back
1277    
1278  =cut  =cut
1279  #: Return Type @@;  
1280  sub GenesInRegion {  sub GenesInRegion {
1281      # Get the parameters.      # Get the parameters.
1282      my ($self, $contigID, $start, $stop) = @_;      my ($self, $contigID, $start, $stop) = @_;
1283      # Get the maximum segment length.      # Get the maximum segment length.
1284      my $maximumSegmentLength = $self->MaxSegment;      my $maximumSegmentLength = $self->MaxSegment;
     # Create a hash to receive the feature list. We use a hash so that we can eliminate  
     # duplicates easily. The hash key will be the feature ID. The value will be a two-element  
     # containing the minimum and maximum offsets. We will use the offsets to sort the results  
     # when we're building the result set.  
     my %featuresFound = ();  
1285      # Prime the values we'll use for the returned beginning and end.      # Prime the values we'll use for the returned beginning and end.
1286      my @initialMinMax = ($self->ContigLength($contigID), 0);      my @initialMinMax = ($self->ContigLength($contigID), 0);
1287      my ($min, $max) = @initialMinMax;      my ($min, $max) = @initialMinMax;
1288      # Create a table of parameters for each query. Each query looks for features travelling in      # Get the overlapping features.
1289        my @featureObjects = $self->GeneDataInRegion($contigID, $start, $stop);
1290        # We'l use this hash to help us track the feature IDs and sort them. The key is the
1291        # feature ID and the value is a [$left,$right] pair indicating the maximum extent
1292        # of the feature's locations.
1293        my %featureMap = ();
1294        # Loop through them to do the begin/end analysis.
1295        for my $featureObject (@featureObjects) {
1296            # Get the feature's location string. This may contain multiple actual locations.
1297            my ($locations, $fid) = $featureObject->Values([qw(Feature(location-string) Feature(id))]);
1298            my @locationSegments = split /\s*,\s*/, $locations;
1299            # Loop through the locations.
1300            for my $locationSegment (@locationSegments) {
1301                # Construct an object for the location.
1302                my $locationObject = BasicLocation->new($locationSegment);
1303                # Merge the current segment's begin and end into the min and max.
1304                my ($left, $right) = ($locationObject->Left, $locationObject->Right);
1305                my ($beg, $end);
1306                if (exists $featureMap{$fid}) {
1307                    ($beg, $end) = @{$featureMap{$fid}};
1308                    $beg = $left if $left < $beg;
1309                    $end = $right if $right > $end;
1310                } else {
1311                    ($beg, $end) = ($left, $right);
1312                }
1313                $min = $beg if $beg < $min;
1314                $max = $end if $end > $max;
1315                # Store the feature's new extent back into the hash table.
1316                $featureMap{$fid} = [$beg, $end];
1317            }
1318        }
1319        # Now we must compute the list of the IDs for the features found. We start with a list
1320        # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,
1321        # but the result of the sort will be the same.)
1322        my @list = map { [$featureMap{$_}->[0] + $featureMap{$_}->[1], $_] } keys %featureMap;
1323        # Now we sort by midpoint and yank out the feature IDs.
1324        my @retVal = map { $_->[1] } sort { $a->[0] <=> $b->[0] } @list;
1325        # Return it along with the min and max.
1326        return (\@retVal, $min, $max);
1327    }
1328    
1329    =head3 GeneDataInRegion
1330    
1331        my @featureList = $sprout->GenesInRegion($contigID, $start, $stop);
1332    
1333    List the features which overlap a specified region in a contig.
1334    
1335    =over 4
1336    
1337    =item contigID
1338    
1339    ID of the contig containing the region of interest.
1340    
1341    =item start
1342    
1343    Offset of the first residue in the region of interest.
1344    
1345    =item stop
1346    
1347    Offset of the last residue in the region of interest.
1348    
1349    =item RETURN
1350    
1351    Returns a list of B<ERDBObjects> for the desired features. Each object will
1352    contain a B<Feature> record.
1353    
1354    =back
1355    
1356    =cut
1357    
1358    sub GeneDataInRegion {
1359        # Get the parameters.
1360        my ($self, $contigID, $start, $stop) = @_;
1361        # Get the maximum segment length.
1362        my $maximumSegmentLength = $self->MaxSegment;
1363        # Create a hash to receive the feature list. We use a hash so that we can eliminate
1364        # duplicates easily. The hash key will be the feature ID. The value will be the feature's
1365        # ERDBObject from the query.
1366        my %featuresFound = ();
1367        # Create a table of parameters for the queries. Each query looks for features travelling in
1368      # 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,
1369      # 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
1370      # 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 1086  Line 1373 
1373      # Loop through the query parameters.      # Loop through the query parameters.
1374      for my $parms (values %queryParms) {      for my $parms (values %queryParms) {
1375          # Create the query.          # Create the query.
1376          my $query = $self->Get(['IsLocatedIn'],          my $query = $self->Get([qw(Feature IsLocatedIn)],
1377              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",              "IsLocatedIn(to-link)= ? AND IsLocatedIn(dir) = ? AND IsLocatedIn(beg) >= ? AND IsLocatedIn(beg) <= ?",
1378              $parms);              $parms);
1379          # Loop through the feature segments found.          # Loop through the feature segments found.
1380          while (my $segment = $query->Fetch) {          while (my $segment = $query->Fetch) {
1381              # Get the data about this segment.              # Get the data about this segment.
1382              my ($featureID, $dir, $beg, $len) = $segment->Values(['IsLocatedIn(from-link)',              my ($featureID, $contig, $dir, $beg, $len) = $segment->Values([qw(IsLocatedIn(from-link)
1383                  'IsLocatedIn(dir)', 'IsLocatedIn(beg)', 'IsLocatedIn(len)']);                  IsLocatedIn(to-link) IsLocatedIn(dir) IsLocatedIn(beg) IsLocatedIn(len))]);
1384              # Determine if this feature actually overlaps the region. The query insures that              # Determine if this feature segment actually overlaps the region. The query insures that
1385              # this will be the case if the segment is the maximum length, so to fine-tune              # this will be the case if the segment is the maximum length, so to fine-tune
1386              # the results we insure that the inequality from the query holds using the actual              # the results we insure that the inequality from the query holds using the actual
1387              # length.              # length.
1388              my ($found, $end) = (0, 0);              my $loc = BasicLocation->new($contig, $beg, $dir, $len);
1389              if ($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.  
                     $found = 1;  
                 }  
             }  
1390              if ($found) {              if ($found) {
1391                  # Here we need to record the feature and update the minima and maxima. First,                  # Save this feature in the result list.
1392                  # 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;  
1393                  }                  }
                 # Store the entry back into the hash table.  
                 $featuresFound{$featureID} = [$loc1, $loc2];  
1394              }              }
1395          }          }
1396      }      # Return the ERDB objects for the features found.
1397      # Now we must compute the list of the IDs for the features found. We start with a list      return values %featuresFound;
     # of midpoints / feature ID pairs. (It's not really a midpoint, it's twice the midpoint,  
     # but the result of the sort will be the same.)  
     my @list = map { [$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);  
1398  }  }
1399    
1400  =head3 FType  =head3 FType
1401    
1402  C<< my $ftype = $sprout->FType($featureID); >>      my $ftype = $sprout->FType($featureID);
1403    
1404  Return the type of a feature.  Return the type of a feature.
1405    
# Line 1176  Line 1429 
1429    
1430  =head3 FeatureAnnotations  =head3 FeatureAnnotations
1431    
1432  C<< my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag); >>      my @descriptors = $sprout->FeatureAnnotations($featureID, $rawFlag);
1433    
1434  Return the annotations of a feature.  Return the annotations of a feature.
1435    
# Line 1239  Line 1492 
1492    
1493  =head3 AllFunctionsOf  =head3 AllFunctionsOf
1494    
1495  C<< my %functions = $sprout->AllFunctionsOf($featureID); >>      my %functions = $sprout->AllFunctionsOf($featureID);
1496    
1497  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
1498  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 1294  Line 1547 
1547    
1548  =head3 FunctionOf  =head3 FunctionOf
1549    
1550  C<< my $functionText = $sprout->FunctionOf($featureID, $userID); >>      my $functionText = $sprout->FunctionOf($featureID, $userID);
1551    
1552  Return the most recently-determined functional assignment of a particular feature.  Return the most recently-determined functional assignment of a particular feature.
1553    
1554  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
1555  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
1556  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.  
1557    
1558  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
1559  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 1322  Line 1572 
1572    
1573  =item userID (optional)  =item userID (optional)
1574    
1575  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
1576  C<FIG> assignment will be returned.  functional assignment in the B<Feature> table will be returned.
1577    
1578  =item RETURN  =item RETURN
1579    
# Line 1340  Line 1590 
1590      my $retVal;      my $retVal;
1591      # Determine the ID type.      # Determine the ID type.
1592      if ($featureID =~ m/^fig\|/) {      if ($featureID =~ m/^fig\|/) {
1593          # Here we have a FIG feature ID. We must build the list of trusted          # Here we have a FIG feature ID.
1594          # users.          if (!$userID) {
1595                # Use the primary assignment.
1596                ($retVal) = $self->GetEntityValues('Feature', $featureID, ['Feature(assignment)']);
1597            } else {
1598                # We must build the list of trusted users.
1599          my %trusteeTable = ();          my %trusteeTable = ();
1600          # Check the user ID.          # Check the user ID.
1601          if (!$userID) {          if (!$userID) {
# Line 1384  Line 1638 
1638                  }                  }
1639              }              }
1640          }          }
1641            }
1642      } else {      } else {
1643          # 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
1644          # matter. We simply get the information from the External Alias Function          # matter. We simply get the information from the External Alias Function
# Line 1396  Line 1651 
1651    
1652  =head3 FunctionsOf  =head3 FunctionsOf
1653    
1654  C<< my @functionList = $sprout->FunctionOf($featureID, $userID); >>      my @functionList = $sprout->FunctionOf($featureID, $userID);
1655    
1656  Return the functional assignments of a particular feature.  Return the functional assignments of a particular feature.
1657    
# Line 1468  Line 1723 
1723    
1724  =head3 BBHList  =head3 BBHList
1725    
1726  C<< my $bbhHash = $sprout->BBHList($genomeID, \@featureList); >>      my $bbhHash = $sprout->BBHList($genomeID, \@featureList);
1727    
1728  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
1729  on a specified target genome.  on a specified target genome.
# Line 1504  Line 1759 
1759          # Peel off the BBHs found.          # Peel off the BBHs found.
1760          my @found = ();          my @found = ();
1761          for my $bbh (@bbhData) {          for my $bbh (@bbhData) {
1762              push @found, $bbh->[0];              my $fid = $bbh->[0];
1763                my $bbGenome = $self->GenomeOf($fid);
1764                if ($bbGenome eq $genomeID) {
1765                    push @found, $fid;
1766                }
1767          }          }
1768          $retVal{$featureID} = \@found;          $retVal{$featureID} = \@found;
1769      }      }
# Line 1514  Line 1773 
1773    
1774  =head3 SimList  =head3 SimList
1775    
1776  C<< my %similarities = $sprout->SimList($featureID, $count); >>      my %similarities = $sprout->SimList($featureID, $count);
1777    
1778  Return a list of the similarities to the specified feature.  Return a list of the similarities to the specified feature.
1779    
# Line 1550  Line 1809 
1809    
1810  =head3 IsComplete  =head3 IsComplete
1811    
1812  C<< my $flag = $sprout->IsComplete($genomeID); >>      my $flag = $sprout->IsComplete($genomeID);
1813    
1814  Return TRUE if the specified genome is complete, else FALSE.  Return TRUE if the specified genome is complete, else FALSE.
1815    
# Line 1578  Line 1837 
1837      my $genomeData = $self->GetEntity('Genome', $genomeID);      my $genomeData = $self->GetEntity('Genome', $genomeID);
1838      if ($genomeData) {      if ($genomeData) {
1839          # The genome exists, so get the completeness flag.          # The genome exists, so get the completeness flag.
1840          ($retVal) = $genomeData->Value('Genome(complete)');          $retVal = $genomeData->PrimaryValue('Genome(complete)');
1841      }      }
1842      # Return the result.      # Return the result.
1843      return $retVal;      return $retVal;
# Line 1586  Line 1845 
1845    
1846  =head3 FeatureAliases  =head3 FeatureAliases
1847    
1848  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>      my @aliasList = $sprout->FeatureAliases($featureID);
1849    
1850  Return a list of the aliases for a specified feature.  Return a list of the aliases for a specified feature.
1851    
# Line 1609  Line 1868 
1868      # Get the parameters.      # Get the parameters.
1869      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1870      # Get the desired feature's aliases      # Get the desired feature's aliases
1871      my @retVal = $self->GetEntityValues('Feature', $featureID, ['Feature(alias)']);      my @retVal = $self->GetFlat(['IsAliasOf'], "IsAliasOf(to-link) = ?", [$featureID], 'IsAliasOf(from-link)');
1872      # Return the result.      # Return the result.
1873      return @retVal;      return @retVal;
1874  }  }
1875    
1876  =head3 GenomeOf  =head3 GenomeOf
1877    
1878  C<< my $genomeID = $sprout->GenomeOf($featureID); >>      my $genomeID = $sprout->GenomeOf($featureID);
1879    
1880  Return the genome that contains a specified feature or contig.  Return the genome that contains a specified feature or contig.
1881    
# Line 1638  Line 1897 
1897  sub GenomeOf {  sub GenomeOf {
1898      # Get the parameters.      # Get the parameters.
1899      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]);  
1900      # Declare the return value.      # Declare the return value.
1901      my $retVal;      my $retVal;
1902      # Get the genome ID.      # Parse the genome ID from the feature ID.
1903      if (my $relationship = $query->Fetch()) {      if ($featureID =~ /^fig\|(\d+\.\d+)/) {
1904          ($retVal) = $relationship->Value('HasContig(from-link)');          $retVal = $1;
1905        } else {
1906            Confess("Invalid feature ID $featureID.");
1907      }      }
1908      # Return the value found.      # Return the value found.
1909      return $retVal;      return $retVal;
# Line 1653  Line 1911 
1911    
1912  =head3 CoupledFeatures  =head3 CoupledFeatures
1913    
1914  C<< my %coupleHash = $sprout->CoupledFeatures($featureID); >>      my %coupleHash = $sprout->CoupledFeatures($featureID);
1915    
1916  Return the features functionally coupled with a specified feature. Features are considered  Return the features functionally coupled with a specified feature. Features are considered
1917  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 1675  Line 1933 
1933  sub CoupledFeatures {  sub CoupledFeatures {
1934      # Get the parameters.      # Get the parameters.
1935      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
1936        # Ask the coupling server for the data.
1937      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);      Trace("Looking for features coupled to $featureID.") if T(coupling => 3);
1938      # Create a query to retrieve the functionally-coupled features.      my @rawPairs = FIGRules::NetCouplingData('coupled_to', id1 => $featureID);
1939      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],      Trace(scalar(@rawPairs) . " couplings returned.") if T(coupling => 3);
1940                             "ParticipatesInCoupling(from-link) = ?", [$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.  
1941      my %retVal = ();      my %retVal = ();
1942      # Retrieve the relationship records and store them in the hash.      for my $pair (@rawPairs) {
1943      while (my $clustering = $query->Fetch()) {          # Get the feature ID and score.
1944          # Get the ID and score of the coupling.          my ($featureID2, $score) = @{$pair};
1945          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',          # Only proceed if the feature is in NMPDR.
1946                                                          'Coupling(score)']);          if ($self->_CheckFeature($featureID2)) {
1947          Trace("$featureID coupled with score $score to ID $couplingID.") if T(coupling => 4);              $retVal{$featureID2} = $score;
1948          # Get the other feature that participates in the coupling.          }
         my ($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;  
         $found = 1;  
1949      }      }
1950      # Functional coupling is reflexive. If we found at least one coupled feature, we must add      # Functional coupling is reflexive. If we found at least one coupled feature, we must add
1951      # the incoming feature as well.      # the incoming feature as well.
1952      if ($found) {      if (keys %retVal) {
1953          $retVal{$featureID} = 9999;          $retVal{$featureID} = 9999;
1954      }      }
1955      # Return the hash.      # Return the hash.
# Line 1709  Line 1958 
1958    
1959  =head3 CouplingEvidence  =head3 CouplingEvidence
1960    
1961  C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>      my @evidence = $sprout->CouplingEvidence($peg1, $peg2);
1962    
1963  Return the evidence for a functional coupling.  Return the evidence for a functional coupling.
1964    
# Line 1757  Line 2006 
2006      my ($self, $peg1, $peg2) = @_;      my ($self, $peg1, $peg2) = @_;
2007      # Declare the return variable.      # Declare the return variable.
2008      my @retVal = ();      my @retVal = ();
2009      # Our first task is to find out the nature of the coupling: whether or not      # Get the coupling and evidence data.
2010      # it exists, its score, and whether the features are stored in the same      my @rawData = FIGRules::NetCouplingData('coupling_evidence', id1 => $peg1, id2 => $peg2);
2011      # order as the ones coming in.      # Loop through the raw data, saving the ones that are in NMPDR genomes.
2012      my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);      for my $rawTuple (@rawData) {
2013      # Only proceed if a coupling exists.          if ($self->_CheckFeature($rawTuple->[0]) && $self->_CheckFeature($rawTuple->[1])) {
2014      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;  
2015  }  }
   
 =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 $peg1.") if T(Coupling => 4);  
2016      }      }
2017      # Return the result.      # Return the result.
2018      return ($retVal, $inverted, $score);      return @retVal;
2019  }  }
2020    
2021  =head3 GetSynonymGroup  =head3 GetSynonymGroup
2022    
2023  C<< my $id = $sprout->GetSynonymGroup($fid); >>      my $id = $sprout->GetSynonymGroup($fid);
2024    
2025  Return the synonym group name for the specified feature.  Return the synonym group name for the specified feature.
2026    
# Line 1888  Line 2059 
2059    
2060  =head3 GetBoundaries  =head3 GetBoundaries
2061    
2062  C<< my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList); >>      my ($contig, $beg, $end) = $sprout->GetBoundaries(@locList);
2063    
2064  Determine the begin and end boundaries for the locations in a list. All of the  Determine the begin and end boundaries for the locations in a list. All of the
2065  locations must belong to the same contig and have mostly the same direction in  locations must belong to the same contig and have mostly the same direction in
# Line 1950  Line 2121 
2121      return ($contig, $beg, $end);      return ($contig, $beg, $end);
2122  }  }
2123    
 =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);  
 }  
   
2124  =head3 ReadFasta  =head3 ReadFasta
2125    
2126  C<< my %sequenceData = Sprout::ReadFasta($fileName, $prefix); >>      my %sequenceData = Sprout::ReadFasta($fileName, $prefix);
2127    
2128  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
2129  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 2057  Line 2189 
2189    
2190  =head3 FormatLocations  =head3 FormatLocations
2191    
2192  C<< my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat); >>      my @locations = $sprout->FormatLocations($prefix, \@locations, $oldFormat);
2193    
2194  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
2195  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 2122  Line 2254 
2254    
2255  =head3 DumpData  =head3 DumpData
2256    
2257  C<< $sprout->DumpData(); >>      $sprout->DumpData();
2258    
2259  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.
2260    
# Line 2139  Line 2271 
2271    
2272  =head3 XMLFileName  =head3 XMLFileName
2273    
2274  C<< my $fileName = $sprout->XMLFileName(); >>      my $fileName = $sprout->XMLFileName();
2275    
2276  Return the name of this database's XML definition file.  Return the name of this database's XML definition file.
2277    
# Line 2150  Line 2282 
2282      return $self->{_xmlName};      return $self->{_xmlName};
2283  }  }
2284    
2285    =head3 GetGenomeNameData
2286    
2287        my ($genus, $species, $strain) = $sprout->GenomeNameData($genomeID);
2288    
2289    Return the genus, species, and unique characterization for a genome. This
2290    is similar to L</GenusSpecies>, with the exception that it returns the
2291    values in three seperate fields.
2292    
2293    =over 4
2294    
2295    =item genomeID
2296    
2297    ID of the genome whose name data is desired.
2298    
2299    =item RETURN
2300    
2301    Returns a three-element list, consisting of the genus, species, and strain
2302    of the specified genome. If the genome is not found, an error occurs.
2303    
2304    =back
2305    
2306    =cut
2307    
2308    sub GetGenomeNameData {
2309        # Get the parameters.
2310        my ($self, $genomeID) = @_;
2311        # Get the desired values.
2312        my ($genus, $species, $strain) = $self->GetEntityValues('Genome', $genomeID =>
2313                                                                [qw(Genome(genus) Genome(species) Genome(unique-characterization))]);
2314        # Throw an error if they were not found.
2315        if (! defined $genus) {
2316            Confess("Genome $genomeID not found in database.");
2317        }
2318        # Return the results.
2319        return ($genus, $species, $strain);
2320    }
2321    
2322    =head3 GetGenomeByNameData
2323    
2324        my @genomes = $sprout->GetGenomeByNameData($genus, $species, $strain);
2325    
2326    Return a list of the IDs of the genomes with the specified genus,
2327    species, and strain. In almost every case, there will be either zero or
2328    one IDs returned; however, two or more IDs could be returned if there are
2329    multiple versions of the genome in the database.
2330    
2331    =over 4
2332    
2333    =item genus
2334    
2335    Genus of the desired genome.
2336    
2337    =item species
2338    
2339    Species of the desired genome.
2340    
2341    =item strain
2342    
2343    Strain (unique characterization) of the desired genome. This may be an empty
2344    string, in which case it is presumed that the desired genome has no strain
2345    specified.
2346    
2347    =item RETURN
2348    
2349    Returns a list of the IDs of the genomes having the specified genus, species, and
2350    strain.
2351    
2352    =back
2353    
2354    =cut
2355    
2356    sub GetGenomeByNameData {
2357        # Get the parameters.
2358        my ($self, $genus, $species, $strain) = @_;
2359        # Try to find the genomes.
2360        my @retVal = $self->GetFlat(['Genome'], "Genome(genus) = ? AND Genome(species) = ? AND Genome(unique-characterization) = ?",
2361                                    [$genus, $species, $strain], 'Genome(id)');
2362        # Return the result.
2363        return @retVal;
2364    }
2365    
2366  =head3 Insert  =head3 Insert
2367    
2368  C<< $sprout->Insert($objectType, \%fieldHash); >>      $sprout->Insert($objectType, \%fieldHash);
2369    
2370  Insert an entity or relationship instance into the database. The entity or relationship of interest  Insert an entity or relationship instance into the database. The entity or relationship of interest
2371  is defined by a type name and then a hash of field names to values. Field values in the primary  is defined by a type name and then a hash of field names to values. Field values in the primary
# Line 2161  Line 2374 
2374  list references. For example, the following line inserts an inactive PEG feature named  list references. For example, the following line inserts an inactive PEG feature named
2375  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.  C<fig|188.1.peg.1> with aliases C<ZP_00210270.1> and C<gi|46206278>.
2376    
2377  C<< $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']}); >>      $sprout->Insert('Feature', { id => 'fig|188.1.peg.1', active => 0, feature-type => 'peg', alias => ['ZP_00210270.1', 'gi|46206278']});
2378    
2379  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
2380  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
2381    
2382  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>      $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'});
2383    
2384  =over 4  =over 4
2385    
# Line 2191  Line 2404 
2404    
2405  =head3 Annotate  =head3 Annotate
2406    
2407  C<< my $ok = $sprout->Annotate($fid, $timestamp, $user, $text); >>      my $ok = $sprout->Annotate($fid, $timestamp, $user, $text);
2408    
2409  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
2410  specified feature and user.  specified feature and user.
# Line 2245  Line 2458 
2458    
2459  =head3 AssignFunction  =head3 AssignFunction
2460    
2461  C<< my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser); >>      my $ok = $sprout->AssignFunction($featureID, $user, $function, $assigningUser);
2462    
2463  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
2464  format is described in L</ParseAssignment>.  format is described in L</ParseAssignment>.
# Line 2305  Line 2518 
2518    
2519  =head3 FeaturesByAlias  =head3 FeaturesByAlias
2520    
2521  C<< my @features = $sprout->FeaturesByAlias($alias); >>      my @features = $sprout->FeaturesByAlias($alias);
2522    
2523  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
2524  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 2339  Line 2552 
2552          push @retVal, $mappedAlias;          push @retVal, $mappedAlias;
2553      } else {      } else {
2554          # 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.
2555          @retVal = $self->GetFlat(['Feature'], 'Feature(alias) = ?', [$mappedAlias], 'Feature(id)');          @retVal = $self->GetFlat(['IsAliasOf'], 'IsAliasOf(from-link) = ?', [$mappedAlias], 'IsAliasOf(to-link)');
2556      }      }
2557      # Return the result.      # Return the result.
2558      return @retVal;      return @retVal;
# Line 2347  Line 2560 
2560    
2561  =head3 FeatureTranslation  =head3 FeatureTranslation
2562    
2563  C<< my $translation = $sprout->FeatureTranslation($featureID); >>      my $translation = $sprout->FeatureTranslation($featureID);
2564    
2565  Return the translation of a feature.  Return the translation of a feature.
2566    
# Line 2375  Line 2588 
2588    
2589  =head3 Taxonomy  =head3 Taxonomy
2590    
2591  C<< my @taxonomyList = $sprout->Taxonomy($genome); >>      my @taxonomyList = $sprout->Taxonomy($genome);
2592    
2593  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
2594  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>,
2595  or C<Eukaryote>) to sub-species. For example,  or C<Eukaryote>) to sub-species. For example,
2596    
2597  C<< (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12) >>      (Bacteria, Proteobacteria, Gammaproteobacteria, Enterobacteriales, Enterobacteriaceae, Escherichia, Escherichia coli, Escherichia coli K12)
2598    
2599  =over 4  =over 4
2600    
# Line 2416  Line 2629 
2629    
2630  =head3 CrudeDistance  =head3 CrudeDistance
2631    
2632  C<< my $distance = $sprout->CrudeDistance($genome1, $genome2); >>      my $distance = $sprout->CrudeDistance($genome1, $genome2);
2633    
2634  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
2635  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 2468  Line 2681 
2681    
2682  =head3 RoleName  =head3 RoleName
2683    
2684  C<< my $roleName = $sprout->RoleName($roleID); >>      my $roleName = $sprout->RoleName($roleID);
2685    
2686  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
2687  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 2502  Line 2715 
2715    
2716  =head3 RoleDiagrams  =head3 RoleDiagrams
2717    
2718  C<< my @diagrams = $sprout->RoleDiagrams($roleID); >>      my @diagrams = $sprout->RoleDiagrams($roleID);
2719    
2720  Return a list of the diagrams containing a specified functional role.  Return a list of the diagrams containing a specified functional role.
2721    
# Line 2532  Line 2745 
2745    
2746  =head3 GetProperties  =head3 GetProperties
2747    
2748  C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>      my @list = $sprout->GetProperties($fid, $key, $value, $url);
2749    
2750  Return a list of the properties with the specified characteristics.  Return a list of the properties with the specified characteristics.
2751    
2752  Properties are arbitrary key-value pairs associated with a feature. (At some point they  Properties are the Sprout analog of the FIG attributes. The call is
2753  will also be associated with genomes.) A property value is represented by a 4-tuple of  passed directly to the CustomAttributes or RemoteCustomAttributes object
2754  the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter  contained in this object.
2755    
2756  =over 4  This method returns a series of tuples that match the specified criteria. Each tuple
2757    will contain an object ID, a key, and one or more values. The parameters to this
2758    method therefore correspond structurally to the values expected in each tuple. In
2759    addition, you can ask for a generic search by suffixing a percent sign (C<%>) to any
2760    of the parameters. So, for example,
2761    
2762  =item fid      my @attributeList = $sprout->GetProperties('fig|100226.1.peg.1004', 'structure%', 1, 2);
2763    
2764  ID of the feature possessing the property.  would return something like
2765    
2766  =item key      ['fig}100226.1.peg.1004', 'structure', 1, 2]
2767        ['fig}100226.1.peg.1004', 'structure1', 1, 2]
2768        ['fig}100226.1.peg.1004', 'structure2', 1, 2]
2769        ['fig}100226.1.peg.1004', 'structureA', 1, 2]
2770    
2771  Name or key of the property.  Use of C<undef> in any position acts as a wild card (all values). You can also specify
2772    a list reference in the ID column. Thus,
2773    
2774  =item value      my @attributeList = $sprout->GetProperties(['100226.1', 'fig|100226.1.%'], 'PUBMED');
2775    
2776  Value of the property.  would get the PUBMED attribute data for Streptomyces coelicolor A3(2) and all its
2777    features.
2778    
2779  =item url  In addition to values in multiple sections, a single attribute key can have multiple
2780    values, so even
2781    
2782  URL of the document that indicated the property should have this particular value, or an      my @attributeList = $sprout->GetProperties($peg, 'virulent');
 empty string if no such document exists.  
2783    
2784  =back  which has no wildcard in the key or the object ID, may return multiple tuples.
2785    
2786    =over 4
2787    
2788    =item objectID
2789    
2790  The parameters act as a filter for the desired data. Any non-null parameter will  ID of object whose attributes are desired. If the attributes are desired for multiple
2791  automatically match all the tuples returned. So, specifying just the I<$fid> will  objects, this parameter can be specified as a list reference. If the attributes are
2792  return all the properties of the specified feature; similarly, specifying the I<$key>  desired for all objects, specify C<undef> or an empty string. Finally, you can specify
2793  and I<$value> parameters will return all the features having the specified property  attributes for a range of object IDs by putting a percent sign (C<%>) at the end.
 value.  
2794    
2795  A single property key can have many values, representing different ideas about the  =item key
2796  feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is  
2797  virulent, and another may declare that it is not virulent. A query about the virulence of  Attribute key name. A value of C<undef> or an empty string will match all
2798  C<fig|83333.1.peg.10> would be coded as  attribute keys. If the values are desired for multiple keys, this parameter can be
2799    specified as a list reference. Finally, you can specify attributes for a range of
2800    keys by putting a percent sign (C<%>) at the end.
2801    
2802    =item values
2803    
2804    List of the desired attribute values, section by section. If C<undef>
2805    or an empty string is specified, all values in that section will match. A
2806    generic match can be requested by placing a percent sign (C<%>) at the end.
2807    In that case, all values that match up to and not including the percent sign
2808    will match. You may also specify a regular expression enclosed
2809    in slashes. All values that match the regular expression will be returned. For
2810    performance reasons, only values have this extra capability.
2811    
2812      my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');  =item RETURN
2813    
2814  Here the I<$value> and I<$url> fields are left blank, indicating that those fields are  Returns a list of tuples. The first element in the tuple is an object ID, the
2815  not to be filtered. The tuples returned would be  second is an attribute key, and the remaining elements are the sections of
2816    the attribute value. All of the tuples will match the criteria set forth in
2817    the parameter list.
2818    
2819      ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')  =back
     ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')  
2820    
2821  =cut  =cut
2822  #: Return Type @@;  
2823  sub GetProperties {  sub GetProperties {
2824      # Get the parameters.      # Get the parameters.
2825      my ($self, @parms) = @_;      my ($self, @parms) = @_;
2826      # Declare the return variable.      # Declare the return variable.
2827      my @retVal = ();      my @retVal = $self->{_ca}->GetAttributes(@parms);
     # 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;  
     }  
2828      # Return the result.      # Return the result.
2829      return @retVal;      return @retVal;
2830  }  }
2831    
2832  =head3 FeatureProperties  =head3 FeatureProperties
2833    
2834  C<< my @properties = $sprout->FeatureProperties($featureID); >>      my @properties = $sprout->FeatureProperties($featureID);
2835    
2836  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
2837  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
2838  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
2839  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
2840  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.  
2841    
2842  =over 4  =over 4
2843    
# Line 2633  Line 2847 
2847    
2848  =item RETURN  =item RETURN
2849    
2850  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.  
2851    
2852  =back  =back
2853    
# Line 2644  Line 2857 
2857      # Get the parameters.      # Get the parameters.
2858      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
2859      # Get the properties.      # Get the properties.
2860      my @retVal = $self->GetAll(['HasProperty', 'Property'], "HasProperty(from-link) = ?", [$featureID],      my @attributes = $self->{_ca}->GetAttributes($featureID);
2861                              ['Property(property-name)', 'Property(property-value)',      # Strip the feature ID off each tuple.
2862                               'HasProperty(evidence)']);      my @retVal = ();
2863        for my $attributeRow (@attributes) {
2864            shift @{$attributeRow};
2865            push @retVal, $attributeRow;
2866        }
2867      # Return the resulting list.      # Return the resulting list.
2868      return @retVal;      return @retVal;
2869  }  }
2870    
2871  =head3 DiagramName  =head3 DiagramName
2872    
2873  C<< my $diagramName = $sprout->DiagramName($diagramID); >>      my $diagramName = $sprout->DiagramName($diagramID);
2874    
2875  Return the descriptive name of a diagram.  Return the descriptive name of a diagram.
2876    
# Line 2679  Line 2896 
2896      return $retVal;      return $retVal;
2897  }  }
2898    
2899    =head3 PropertyID
2900    
2901        my $id = $sprout->PropertyID($propName, $propValue);
2902    
2903    Return the ID of the specified property name and value pair, if the
2904    pair exists. Only a small subset of the FIG attributes are stored as
2905    Sprout properties, mostly for use in search optimization.
2906    
2907    =over 4
2908    
2909    =item propName
2910    
2911    Name of the desired property.
2912    
2913    =item propValue
2914    
2915    Value expected for the desired property.
2916    
2917    =item RETURN
2918    
2919    Returns the ID of the name/value pair, or C<undef> if the pair does not exist.
2920    
2921    =back
2922    
2923    =cut
2924    
2925    sub PropertyID {
2926        # Get the parameters.
2927        my ($self, $propName, $propValue) = @_;
2928        # Try to find the ID.
2929        my ($retVal) = $self->GetFlat(['Property'],
2930                                      "Property(property-name) = ? AND Property(property-value) = ?",
2931                                      [$propName, $propValue], 'Property(id)');
2932        # Return the result.
2933        return $retVal;
2934    }
2935    
2936  =head3 MergedAnnotations  =head3 MergedAnnotations
2937    
2938  C<< my @annotationList = $sprout->MergedAnnotations(\@list); >>      my @annotationList = $sprout->MergedAnnotations(\@list);
2939    
2940  Returns a merged list of the annotations for the features in a list. Each annotation is  Returns a merged list of the annotations for the features in a list. Each annotation is
2941  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where  represented by a 4-tuple of the form C<($fid, $timestamp, $userID, $annotation)>, where
# Line 2730  Line 2984 
2984    
2985  =head3 RoleNeighbors  =head3 RoleNeighbors
2986    
2987  C<< my @roleList = $sprout->RoleNeighbors($roleID); >>      my @roleList = $sprout->RoleNeighbors($roleID);
2988    
2989  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
2990  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 2773  Line 3027 
3027    
3028  =head3 FeatureLinks  =head3 FeatureLinks
3029    
3030  C<< my @links = $sprout->FeatureLinks($featureID); >>      my @links = $sprout->FeatureLinks($featureID);
3031    
3032  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
3033  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 2804  Line 3058 
3058    
3059  =head3 SubsystemsOf  =head3 SubsystemsOf
3060    
3061  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>      my %subsystems = $sprout->SubsystemsOf($featureID);
3062    
3063  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
3064  to the roles the feature performs.  to the roles the feature performs.
# Line 2852  Line 3106 
3106    
3107  =head3 SubsystemList  =head3 SubsystemList
3108    
3109  C<< my @subsystems = $sprout->SubsystemList($featureID); >>      my @subsystems = $sprout->SubsystemList($featureID);
3110    
3111  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
3112  feature participates. Unlike L</SubsystemsOf>, this method only returns the  feature participates. Unlike L</SubsystemsOf>, this method only returns the
# Line 2876  Line 3130 
3130      # Get the parameters.      # Get the parameters.
3131      my ($self, $featureID) = @_;      my ($self, $featureID) = @_;
3132      # Get the list of names.      # Get the list of names.
3133      my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",      my @retVal = $self->GetFlat(['HasRoleInSubsystem'], "HasRoleInSubsystem(from-link) = ?",
3134                                  [$featureID], 'HasSSCell(from-link)');                                  [$featureID], 'HasRoleInSubsystem(to-link)');
3135      # Return the result.      # Return the result, sorted.
3136      return @retVal;      return sort @retVal;
3137  }  }
3138    
3139  =head3 GenomeSubsystemData  =head3 GenomeSubsystemData
3140    
3141  C<< my %featureData = $sprout->GenomeSubsystemData($genomeID); >>      my %featureData = $sprout->GenomeSubsystemData($genomeID);
3142    
3143  Return a hash mapping genome features to their subsystem roles.  Return a hash mapping genome features to their subsystem roles.
3144    
# Line 2944  Line 3198 
3198    
3199  =head3 RelatedFeatures  =head3 RelatedFeatures
3200    
3201  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>      my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID);
3202    
3203  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
3204  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 2995  Line 3249 
3249    
3250  =head3 TaxonomySort  =head3 TaxonomySort
3251    
3252  C<< my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs); >>      my @sortedFeatureIDs = $sprout->TaxonomySort(\@featureIDs);
3253    
3254  Return a list formed by sorting the specified features by the taxonomy of the containing  Return a list formed by sorting the specified features by the taxonomy of the containing
3255  genome. This will cause genomes from similar organisms to float close to each other.  genome. This will cause genomes from similar organisms to float close to each other.
# Line 3030  Line 3284 
3284          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",          my ($taxonomy) = $self->GetFlat(['IsLocatedIn', 'HasContig', 'Genome'], "IsLocatedIn(from-link) = ?",
3285                                          [$fid], 'Genome(taxonomy)');                                          [$fid], 'Genome(taxonomy)');
3286          # Add this feature to the hash buffer.          # Add this feature to the hash buffer.
3287          Tracer::AddToListMap(\%hashBuffer, $taxonomy, $fid);          push @{$hashBuffer{$taxonomy}}, $fid;
3288      }      }
3289      # Sort the keys and get the elements.      # Sort the keys and get the elements.
3290      my @retVal = ();      my @retVal = ();
# Line 3043  Line 3297 
3297    
3298  =head3 Protein  =head3 Protein
3299    
3300  C<< my $protein = Sprout::Protein($sequence, $table); >>      my $protein = Sprout::Protein($sequence, $table);
3301    
3302  Translate a DNA sequence into a protein sequence.  Translate a DNA sequence into a protein sequence.
3303    
# Line 3113  Line 3367 
3367      # Loop through the input triples.      # Loop through the input triples.
3368      my $n = length $sequence;      my $n = length $sequence;
3369      for (my $i = 0; $i < $n; $i += 3) {      for (my $i = 0; $i < $n; $i += 3) {
3370          # Get the current triple from the sequence.          # Get the current triple from the sequence. Note we convert to
3371          my $triple = substr($sequence, $i, 3);          # upper case to insure a match.
3372            my $triple = uc substr($sequence, $i, 3);
3373          # Translate it using the table.          # Translate it using the table.
3374          my $protein = "X";          my $protein = "X";
3375          if (exists $table->{$triple}) { $protein = $table->{$triple}; }          if (exists $table->{$triple}) { $protein = $table->{$triple}; }
# Line 3128  Line 3383 
3383    
3384  =head3 LoadInfo  =head3 LoadInfo
3385    
3386  C<< my ($dirName, @relNames) = $sprout->LoadInfo(); >>      my ($dirName, @relNames) = $sprout->LoadInfo();
3387    
3388  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
3389  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 3147  Line 3402 
3402      return @retVal;      return @retVal;
3403  }  }
3404    
3405    =head3 BBHMatrix
3406    
3407        my %bbhMap = $sprout->BBHMatrix($genomeID, $cutoff, @targets);
3408    
3409    Find all the bidirectional best hits for the features of a genome in a
3410    specified list of target genomes. The return value will be a hash mapping
3411    features in the original genome to their bidirectional best hits in the
3412    target genomes.
3413    
3414    =over 4
3415    
3416    =item genomeID
3417    
3418    ID of the genome whose features are to be examined for bidirectional best hits.
3419    
3420    =item cutoff
3421    
3422    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3423    
3424    =item targets
3425    
3426    List of target genomes. Only pairs originating in the original
3427    genome and landing in one of the target genomes will be returned.
3428    
3429    =item RETURN
3430    
3431    Returns a hash mapping each feature in the original genome to a hash mapping its
3432    BBH pegs in the target genomes to their scores.
3433    
3434    =back
3435    
3436    =cut
3437    
3438    sub BBHMatrix {
3439        # Get the parameters.
3440        my ($self, $genomeID, $cutoff, @targets) = @_;
3441        # Declare the return variable.
3442        my %retVal = ();
3443        # Ask for the BBHs.
3444        my @bbhList = FIGRules::BatchBBHs("fig|$genomeID.%", $cutoff, @targets);
3445        # We now have a set of 4-tuples that we need to convert into a hash of hashes.
3446        for my $bbhData (@bbhList) {
3447            my ($peg1, $peg2, $score) = @{$bbhData};
3448            if (! exists $retVal{$peg1}) {
3449                $retVal{$peg1} = { $peg2 => $score };
3450            } else {
3451                $retVal{$peg1}->{$peg2} = $score;
3452            }
3453        }
3454        # Return the result.
3455        return %retVal;
3456    }
3457    
3458    
3459    =head3 SimMatrix
3460    
3461        my %simMap = $sprout->SimMatrix($genomeID, $cutoff, @targets);
3462    
3463    Find all the similarities for the features of a genome in a
3464    specified list of target genomes. The return value will be a hash mapping
3465    features in the original genome to their similarites in the
3466    target genomes.
3467    
3468    =over 4
3469    
3470    =item genomeID
3471    
3472    ID of the genome whose features are to be examined for similarities.
3473    
3474    =item cutoff
3475    
3476    A cutoff value. Only hits with a score lower than the cutoff will be returned.
3477    
3478    =item targets
3479    
3480    List of target genomes. Only pairs originating in the original
3481    genome and landing in one of the target genomes will be returned.
3482    
3483    =item RETURN
3484    
3485    Returns a hash mapping each feature in the original genome to a hash mapping its
3486    similar pegs in the target genomes to their scores.
3487    
3488    =back
3489    
3490    =cut
3491    
3492    sub SimMatrix {
3493        # Get the parameters.
3494        my ($self, $genomeID, $cutoff, @targets) = @_;
3495        # Declare the return variable.
3496        my %retVal = ();
3497        # Get the list of features in the source organism.
3498        my @fids = $self->FeaturesOf($genomeID);
3499        # Ask for the sims. We only want similarities to fig features.
3500        my $simList = FIGRules::GetNetworkSims($self, \@fids, {}, 1000, $cutoff, "fig");
3501        if (! defined $simList) {
3502            Confess("Unable to retrieve similarities from server.");
3503        } else {
3504            Trace("Processing sims.") if T(3);
3505            # We now have a set of sims that we need to convert into a hash of hashes. First, we
3506            # Create a hash for the target genomes.
3507            my %targetHash = map { $_ => 1 } @targets;
3508            for my $simData (@{$simList}) {
3509                # Get the PEGs and the score.
3510                my ($peg1, $peg2, $score) = ($simData->id1, $simData->id2, $simData->psc);
3511                # Insure the second ID is in the target list.
3512                my ($genome2) = FIGRules::ParseFeatureID($peg2);
3513                if (exists $targetHash{$genome2}) {
3514                    # Here it is. Now we need to add it to the return hash. How we do that depends
3515                    # on whether or not $peg1 is new to us.
3516                    if (! exists $retVal{$peg1}) {
3517                        $retVal{$peg1} = { $peg2 => $score };
3518                    } else {
3519                        $retVal{$peg1}->{$peg2} = $score;
3520                    }
3521                }
3522            }
3523        }
3524        # Return the result.
3525        return %retVal;
3526    }
3527    
3528    
3529  =head3 LowBBHs  =head3 LowBBHs
3530    
3531  C<< my %bbhMap = $sprout->LowBBHs($featureID, $cutoff); >>      my %bbhMap = $sprout->LowBBHs($featureID, $cutoff);
3532    
3533  Return the bidirectional best hits of a feature whose score is no greater than a  Return the bidirectional best hits of a feature whose score is no greater than a
3534  specified cutoff value. A higher cutoff value will allow inclusion of hits with  specified cutoff value. A higher cutoff value will allow inclusion of hits with
# Line 3182  Line 3561 
3561      my @bbhList = FIGRules::BBHData($featureID, $cutoff);      my @bbhList = FIGRules::BBHData($featureID, $cutoff);
3562      # Form the results into the return hash.      # Form the results into the return hash.
3563      for my $pair (@bbhList) {      for my $pair (@bbhList) {
3564          $retVal{$pair->[0]} = $pair->[1];          my $fid = $pair->[0];
3565            if ($self->Exists('Feature', $fid)) {
3566                $retVal{$fid} = $pair->[1];
3567            }
3568      }      }
3569      # Return the result.      # Return the result.
3570      return %retVal;      return %retVal;
# Line 3190  Line 3572 
3572    
3573  =head3 Sims  =head3 Sims
3574    
3575  C<< my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters); >>      my $simList = $sprout->Sims($fid, $maxN, $maxP, $select, $max_expand, $filters);
3576    
3577  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
3578  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 3200  Line 3582 
3582  Similarities can be either raw or expanded. The raw similarities are basic  Similarities can be either raw or expanded. The raw similarities are basic
3583  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
3584  features considered substantially identical. So, for example, if features B<A1>,  features considered substantially identical. So, for example, if features B<A1>,
3585  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
3586  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]>.
3587    
3588  =over 4  =over 4
3589    
3590  =item fid  =item fid
3591    
3592  ID of the feature whose similarities are desired.  ID of the feature whose similarities are desired, or reference to a list of IDs
3593    of features whose similarities are desired.
3594    
3595  =item maxN  =item maxN
3596    
# Line 3253  Line 3636 
3636      return $retVal;      return $retVal;
3637  }  }
3638    
3639    =head3 IsAllGenomes
3640    
3641        my $flag = $sprout->IsAllGenomes(\@list, \@checkList);
3642    
3643    Return TRUE if all genomes in the second list are represented in the first list at
3644    least one. Otherwise, return FALSE. If the second list is omitted, the first list is
3645    compared to a list of all the genomes.
3646    
3647    =over 4
3648    
3649    =item list
3650    
3651    Reference to the list to be compared to the second list.
3652    
3653    =item checkList (optional)
3654    
3655    Reference to the comparison target list. Every genome ID in this list must occur at
3656    least once in the first list. If this parameter is omitted, a list of all the genomes
3657    is used.
3658    
3659    =item RETURN
3660    
3661    Returns TRUE if every item in the second list appears at least once in the
3662    first list, else FALSE.
3663    
3664    =back
3665    
3666    =cut
3667    
3668    sub IsAllGenomes {
3669        # Get the parameters.
3670        my ($self, $list, $checkList) = @_;
3671        # Supply the checklist if it was omitted.
3672        $checkList = [$self->Genomes()] if ! defined($checkList);
3673        # Create a hash of the original list.
3674        my %testList = map { $_ => 1 } @{$list};
3675        # Declare the return variable. We assume that the representation
3676        # is complete and stop at the first failure.
3677        my $retVal = 1;
3678        my $n = scalar @{$checkList};
3679        for (my $i = 0; $retVal && $i < $n; $i++) {
3680            if (! $testList{$checkList->[$i]}) {
3681                $retVal = 0;
3682            }
3683        }
3684        # Return the result.
3685        return $retVal;
3686    }
3687    
3688  =head3 GetGroups  =head3 GetGroups
3689    
3690  C<< my %groups = $sprout->GetGroups(\@groupList); >>      my %groups = $sprout->GetGroups(\@groupList);
3691    
3692  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.
3693  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 3274  Line 3706 
3706          # Here we have a group list. Loop through them individually,          # Here we have a group list. Loop through them individually,
3707          # getting a list of the relevant genomes.          # getting a list of the relevant genomes.
3708          for my $group (@{$groupList}) {          for my $group (@{$groupList}) {
3709              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(group-name) = ?",              my @genomeIDs = $self->GetFlat(['Genome'], "Genome(primary-group) = ?",
3710                  [$group], "Genome(id)");                  [$group], "Genome(id)");
3711              $retVal{$group} = \@genomeIDs;              $retVal{$group} = \@genomeIDs;
3712          }          }
# Line 3282  Line 3714 
3714          # 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
3715          # of the genome records, putting each one found into the appropriate          # of the genome records, putting each one found into the appropriate
3716          # 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
3717          # in groups are included in the return set.          # in real NMPDR groups are included in the return set.
3718          my @genomes = $self->GetAll(['Genome'], "Genome(group-name) > ' '", [],          my @genomes = $self->GetAll(['Genome'], "Genome(primary-group) <> ?",
3719                                      ['Genome(id)', 'Genome(group-name)']);                                      [$FIG_Config::otherGroup], ['Genome(id)', 'Genome(primary-group)']);
3720          # Loop through the genomes found.          # Loop through the genomes found.
3721          for my $genome (@genomes) {          for my $genome (@genomes) {
3722              # Pop this genome's ID off the current list.              # Get the genome ID and group, and add this genome to the group's list.
3723              my @groups = @{$genome};              my ($genomeID, $group) = @{$genome};
3724              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, $genomeID);  
             }  
3725          }          }
3726      }      }
3727      # Return the hash we just built.      # Return the hash we just built.
# Line 3303  Line 3730 
3730    
3731  =head3 MyGenomes  =head3 MyGenomes
3732    
3733  C<< my @genomes = Sprout::MyGenomes($dataDir); >>      my @genomes = Sprout::MyGenomes($dataDir);
3734    
3735  Return a list of the genomes to be included in the Sprout.  Return a list of the genomes to be included in the Sprout.
3736    
# Line 3335  Line 3762 
3762    
3763  =head3 LoadFileName  =head3 LoadFileName
3764    
3765  C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>      my $fileName = Sprout::LoadFileName($dataDir, $tableName);
3766    
3767  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
3768  directory.  directory.
# Line 3376  Line 3803 
3803    
3804  =head3 DeleteGenome  =head3 DeleteGenome
3805    
3806  C<< my $stats = $sprout->DeleteGenome($genomeID, $testFlag); >>      my $stats = $sprout->DeleteGenome($genomeID, $testFlag);
3807    
3808  Delete a genome from the database.  Delete a genome from the database.
3809    
# Line 3402  Line 3829 
3829      # Get the parameters.      # Get the parameters.
3830      my ($self, $genomeID, $testFlag) = @_;      my ($self, $genomeID, $testFlag) = @_;
3831      # Perform the delete for the genome's features.      # Perform the delete for the genome's features.
3832      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", $testFlag);      my $retVal = $self->Delete('Feature', "fig|$genomeID.%", testMode => $testFlag);
3833      # Perform the delete for the primary genome data.      # Perform the delete for the primary genome data.
3834      my $stats = $self->Delete('Genome', $genomeID, $testFlag);      my $stats = $self->Delete('Genome', $genomeID, testMode => $testFlag);
3835      $retVal->Accumulate($stats);      $retVal->Accumulate($stats);
3836      # Return the result.      # Return the result.
3837      return $retVal;      return $retVal;
# Line 3412  Line 3839 
3839    
3840  =head3 Fix  =head3 Fix
3841    
3842  C<< my %fixedHash = Sprout::Fix(%groupHash); >>      my %fixedHash = $sprout->Fix(%groupHash);
3843    
3844  Prepare a genome group hash (like that returned by L</GetGroups> for processing.  Prepare a genome group hash (like that returned by L</GetGroups>) for processing.
3845  Groups with the same primary name will be combined. The primary name is the  The groups will be combined into the appropriate super-groups.
 first capitalized word in the group name.  
3846    
3847  =over 4  =over 4
3848    
# Line 3434  Line 3860 
3860    
3861  sub Fix {  sub Fix {
3862      # Get the parameters.      # Get the parameters.
3863      my (%groupHash) = @_;      my ($self, %groupHash) = @_;
3864      # Create the result hash.      # Create the result hash.
3865      my %retVal = ();      my %retVal = ();
3866      # Copy over the genomes.      # Copy over the genomes.
3867      for my $groupID (keys %groupHash) {      for my $groupID (keys %groupHash) {
3868          # Make a safety copy of the group ID.          # Get the super-group name.
3869          my $realGroupID = $groupID;          my $realGroupID = $self->SuperGroup($groupID);
3870          # Yank the primary name.          # Append this group's genomes into the result hash
3871          if ($groupID =~ /([A-Z]\w+)/) {          # using the super-group name.
3872              $realGroupID = $1;          push @{$retVal{$realGroupID}}, @{$groupHash{$groupID}};
         }  
         # Append this group's genomes into the result hash.  
         Tracer::AddToListMap(\%retVal, $realGroupID, @{$groupHash{$groupID}});  
3873      }      }
3874      # Return the result hash.      # Return the result hash.
3875      return %retVal;      return %retVal;
# Line 3454  Line 3877 
3877    
3878  =head3 GroupPageName  =head3 GroupPageName
3879    
3880  C<< my $name = $sprout->GroupPageName($group); >>      my $name = $sprout->GroupPageName($group);
3881    
3882  Return the name of the page for the specified NMPDR group.  Return the name of the page for the specified NMPDR group.
3883    
# Line 3476  Line 3899 
3899  sub GroupPageName {  sub GroupPageName {
3900      # Get the parameters.      # Get the parameters.
3901      my ($self, $group) = @_;      my ($self, $group) = @_;
     # Declare the return variable.  
     my $retVal;  
3902      # Check for the group file data.      # Check for the group file data.
3903      if (! defined $self->{groupHash}) {      my %superTable = $self->CheckGroupFile();
         # Read the group file.  
         my %groupData = Sprout::ReadGroupFile($self->{_options}->{dataDir} . "/groups.tbl");  
         # Store it in our object.  
         $self->{groupHash} = \%groupData;  
     }  
3904      # Compute the real group name.      # Compute the real group name.
3905      my $realGroup = $group;      my $realGroup = $self->SuperGroup($group);
3906      if ($group =~ /([A-Z]\w+)/) {      # Get the associated page name.
3907          $realGroup = $1;      my $retVal = "../content/$superTable{$realGroup}->{page}";
     }  
     # Return the page name.  
     $retVal = "../content/" . $self->{groupHash}->{$realGroup}->[1];  
3908      # Return the result.      # Return the result.
3909      return $retVal;      return $retVal;
3910  }  }
3911    
 =head3 ReadGroupFile  
3912    
3913  C<< my %groupData = Sprout::ReadGroupFile($groupFileName); >>  =head3 AddProperty
3914    
3915        $sprout->AddProperty($featureID, $key, @values);
3916    
3917  Read in the data from the specified group file. The group file contains information  Add a new attribute value (Property) to a feature.
 about each of the NMPDR groups.  
3918    
3919  =over 4  =over 4
3920    
3921  =item name  =item peg
3922    
3923  Name of the group.  ID of the feature to which the attribute is to be added.
3924    
3925  =item page  =item key
3926    
3927  Name of the group's page on the web site (e.g. C<campy.php> for  Name of the attribute (key).
 Campylobacter)  
3928    
3929  =item genus  =item values
3930    
3931  Genus of the group  Values of the attribute.
3932    
3933  =item species  =back
3934    
3935  Species of the group, or an empty string if the group is for an entire  =cut
3936  genus. If the group contains more than one species, the species names  #: Return Type ;
3937  should be separated by commas.  sub AddProperty {
3938        # Get the parameters.
3939        my ($self, $featureID, $key, @values) = @_;
3940        # Add the property using the attached attributes object.
3941        $self->{_ca}->AddAttribute($featureID, $key, @values);
3942    }
3943    
3944  =back  =head3 CheckGroupFile
3945    
3946        my %groupData = $sprout->CheckGroupFile();
3947    
3948    Get the group file hash. The group file hash describes the relationship
3949    between a group and the super-group to which it belongs for purposes of
3950    display. The super-group name is computed from the first capitalized word
3951    in the actual group name. For each super-group, the group file contains
3952    the page name and a list of the species expected to be in the group.
3953    Each species is specified by a genus and a species name. A species name
3954    of C<0> implies an entire genus.
3955    
3956  The parameters to this method are as follows  This method returns a hash from super-group names to a hash reference. Each
3957    resulting hash reference contains the following fields.
3958    
3959  =over 4  =over 4
3960    
3961  =item groupFile  =item page
3962    
3963  Name of the file containing the group data.  The super-group's web page in the NMPDR.
3964    
3965  =item RETURN  =item contents
3966    
3967  Returns a hash keyed on group name. The value of each hash  A list of 2-tuples, each containing a genus name followed by a species name
3968    (or 0, indicating all species). This list indicates which organisms belong
3969    in the super-group.
3970    
3971  =back  =back
3972    
3973  =cut  =cut
3974    
3975  sub ReadGroupFile {  sub CheckGroupFile {
3976      # Get the parameters.      # Get the parameters.
3977      my ($groupFileName) = @_;      my ($self) = @_;
3978      # Declare the return variable.      # Check to see if we already have this hash.
3979      my %retVal;      if (! defined $self->{groupHash}) {
3980            # We don't, so we need to read it in.
3981            my %groupHash;
3982      # Read the group file.      # Read the group file.
3983      my @groupLines = Tracer::GetFile($groupFileName);          my @groupLines = Tracer::GetFile("$FIG_Config::sproutData/groups.tbl");
3984            # Loop through the list of sort-of groups.
3985      for my $groupLine (@groupLines) {      for my $groupLine (@groupLines) {
3986          my ($name, $page, $genus, $species) = split(/\t/, $groupLine);              my ($name, $page, @contents) = split /\t/, $groupLine;
3987          $retVal{$name} = [$page, $genus, $species];              $groupHash{$name} = { page => $page,
3988                                      contents => [ map { [ split /\s*,\s*/, $_ ] } @contents ]
3989                                    };
3990            }
3991            # Save the hash.
3992            $self->{groupHash} = \%groupHash;
3993      }      }
3994      # Return the result.      # Return the result.
3995      return %retVal;      return %{$self->{groupHash}};
3996    }
3997    
3998    =head2 Virtual Methods
3999    
4000    =head3 CleanKeywords
4001    
4002        my $cleanedString = $sprout->CleanKeywords($searchExpression);
4003    
4004    Clean up a search expression or keyword list. This involves converting the periods
4005    in EC numbers to underscores, converting non-leading minus signs to underscores,
4006    a vertical bar or colon to an apostrophe, and forcing lower case for all alphabetic
4007    characters. In addition, any extra spaces are removed.
4008    
4009    =over 4
4010    
4011    =item searchExpression
4012    
4013    Search expression or keyword list to clean. Note that a search expression may
4014    contain boolean operators which need to be preserved. This includes leading
4015    minus signs.
4016    
4017    =item RETURN
4018    
4019    Cleaned expression or keyword list.
4020    
4021    =back
4022    
4023    =cut
4024    
4025    sub CleanKeywords {
4026        # Get the parameters.
4027        my ($self, $searchExpression) = @_;
4028        # Perform the standard cleanup.
4029        my $retVal = $self->ERDB::CleanKeywords($searchExpression);
4030        # Fix the periods in EC and TC numbers.
4031        $retVal =~ s/(\d+|\-)\.(\d+|-)\.(\d+|-)\.(\d+|-)/$1_$2_$3_$4/g;
4032        # Fix non-trailing periods.
4033        $retVal =~ s/\.(\w)/_$1/g;
4034        # Fix non-leading minus signs.
4035        $retVal =~ s/(\w)[\-]/$1_/g;
4036        # Fix the vertical bars and colons
4037        $retVal =~ s/(\w)[|:](\w)/$1'$2/g;
4038        # Return the result.
4039        return $retVal;
4040  }  }
4041    
4042  =head2 Internal Utility Methods  =head2 Internal Utility Methods
# Line 3567  Line 4049 
4049    
4050  A functional assignment is always of the form  A functional assignment is always of the form
4051    
4052      C<set >I<YYYY>C< function to\n>I<ZZZZZ>      set YYYY function to
4053        ZZZZ
4054    
4055  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,
4056  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 3620  Line 4103 
4103      return @retVal;      return @retVal;
4104  }  }
4105    
4106  =head3 FriendlyTimestamp  =head3 _CheckFeature
4107    
4108  Convert a time number to a user-friendly time stamp for display.      my $flag = $sprout->_CheckFeature($fid);
4109    
4110  This is a static method.  Return TRUE if the specified FID is probably an NMPDR feature ID, else FALSE.
4111    
4112  =over 4  =over 4
4113    
4114  =item timeValue  =item fid
4115    
4116  Numeric time value.  Feature ID to check.
4117    
4118  =item RETURN  =item RETURN
4119    
4120  Returns a string containing the same time in user-readable format.  Returns TRUE if the FID is for one of the NMPDR genomes, else FALSE.
4121    
4122  =back  =back
4123    
4124  =cut  =cut
4125    
4126  sub FriendlyTimestamp {  sub _CheckFeature {
4127      my ($timeValue) = @_;      # Get the parameters.
4128      my $retVal = localtime($timeValue);      my ($self, $fid) = @_;
4129      return $retVal;      # Insure we have a genome hash.
4130        if (! defined $self->{genomeHash}) {
4131            my %genomeHash = map { $_ => 1 } $self->GetFlat(['Genome'], "", [], 'Genome(id)');
4132            $self->{genomeHash} = \%genomeHash;
4133        }
4134        # Get the feature's genome ID.
4135        my ($genomeID) = FIGRules::ParseFeatureID($fid);
4136        # Return an indicator of whether or not the genome ID is in the hash.
4137        return ($self->{genomeHash}->{$genomeID} ? 1 : 0);
4138  }  }
4139    
4140  =head3 AddProperty  =head3 FriendlyTimestamp
4141    
4142  C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>  Convert a time number to a user-friendly time stamp for display.
4143    
4144  Add a new attribute value (Property) to a feature. In the SEED system, attributes can  This is a static method.
 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.  
4145    
4146  =over 4  =over 4
4147    
4148  =item peg  =item timeValue
   
 ID of the feature to which the attribute is to be replied.  
   
 =item key  
   
 Name of the attribute (key).  
   
 =item value  
4149    
4150  Value of the attribute.  Numeric time value.
4151    
4152  =item url  =item RETURN
4153    
4154  URL or text citation from which the property was obtained.  Returns a string containing the same time in user-readable format.
4155    
4156  =back  =back
4157    
4158  =cut  =cut
4159  #: Return Type ;  
4160  sub AddProperty {  sub FriendlyTimestamp {
4161      # Get the parameters.      my ($timeValue) = @_;
4162      my ($self, $featureID, $key, $value, $url) = @_;      my $retVal = localtime($timeValue);
4163      # Declare the variable to hold the desired property ID.      return $retVal;
     my $propID;  
     # Attempt to find a property record for this key/value pair.  
     my @properties = $self->GetFlat(['Property'],  
                                    "Property(property-name) = ? AND Property(property-value) = ?",  
                                    [$key, $value], 'Property(id)');  
     if (@properties) {  
         # Here the property is already in the database. We save its ID.  
         $propID = $properties[0];  
         # Here the property value does not exist. We need to generate an ID. It will be set  
         # to a number one greater than the maximum value in the database. This call to  
         # GetAll will stop after one record.  
         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 });  
4164  }  }
4165    
4166    

Legend:
Removed from v.1.85  
changed lines
  Added in v.1.109

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3