diff mothur/tools/mothur/mothur_wrapper.py @ 26:5c77423823cb

Updates for Mothur version 1.25.0 (includes changes to datatypes metagenomics.py and uses more efficient means for labels and groups options)

--- a/mothur/tools/mothur/mothur_wrapper.py	Wed May 16 12:28:44 2012 -0500
+++ b/mothur/tools/mothur/mothur_wrapper.py	Wed May 16 13:12:05 2012 -0500
@@ -202,14 +202,20 @@
     cmd_dict['collect.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','freq','groups','all']})
     cmd_dict['collect.single'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['calc','abund','size','label','freq']})
     cmd_dict['consensus.seqs'] = dict({'required' : ['fasta'], 'optional' : ['list','name','label','cutoff']})
+
+    cmd_dict['cooccurrence'] = dict({'required' : ['shared'], 'optional' : ['iters','metric','matrixmodel','groups','label']})
+
     cmd_dict['corr.axes'] = dict({'required' : [['shared','relabund','metadata'],'axes'], 'optional' : ['label','groups','method','numaxes']})
     cmd_dict['count.groups'] = dict({'required' : ['group','shared'], 'optional' : ['accnos','groups']})
     cmd_dict['count.seqs'] = dict({'required' : ['name'], 'optional' : ['group','groups']})
+
+    cmd_dict['create.database'] = dict({'required' : ['list, repfasta','repname','contaxonomy'], 'optional' : ['group','label']})
+
     cmd_dict['degap.seqs'] = dict({'required' : ['fasta']})
     cmd_dict['deunique.seqs'] = dict({'required' : ['fasta','name'],  'optional' : []})
     cmd_dict['deunique.tree'] = dict({'required' : ['tree','name'],  'optional' : []})
     cmd_dict['dist.seqs'] = dict({'required' : ['fasta'],  'optional' : ['calc','countends','output','cutoff','oldfasta','column','processors']})
-    cmd_dict['dist.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','groups','output','processors']})
+    cmd_dict['dist.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','groups','output','subsample','iters','processors']})
     cmd_dict['fastq.info'] = dict({'required' : ['fastq'], 'optional' : ['fasta','qfile']})
     cmd_dict['filter.seqs'] = dict({'required' : ['fasta'],  'optional' : ['vertical','trump','soft','hard','processors']})
     cmd_dict['get.group'] = dict({'required' : ['shared'], 'optional' : []})
@@ -230,9 +236,12 @@
     cmd_dict['indicator'] = dict({'required' : [['tree','design'],['shared','relabund']], 'optional' : ['groups','label','processors']})
     cmd_dict['libshuff'] = dict({'required' : ['phylip','group'],'optional' : ['groups','iters','form','sim','step','cutoff']})
     cmd_dict['list.seqs'] = dict({'required' : [['fasta','name','group','list','alignreport','taxonomy']]})
+
+    cmd_dict['make.biom'] = dict({'required' : ['shared'] ,  'optional' : ['contaxonomy','matrixtype','groups','label']})
+
     cmd_dict['make.fastq'] = dict({'required' : ['fasta','qfile'] ,  'optional' : []})
     cmd_dict['make.group'] = dict({'required' : ['fasta','groups'],  'optional' : []})
-    cmd_dict['make.shared'] = dict({'required' : ['list','group'],  'optional' : ['label','groups']})
+    cmd_dict['make.shared'] = dict({'required' : [['list','group','biom']],  'optional' : ['label','groups']})
     cmd_dict['mantel'] = dict({'required' : ['phylip','phylip2'] ,  'optional' : ['method','iters']})
     cmd_dict['merge.files'] = dict({'required' : ['input','output']})
     cmd_dict['merge.groups'] = dict({'required' : [['shared','group'],'design'],  'optional' : ['groups', 'label']})
@@ -246,6 +255,9 @@
     cmd_dict['parsimony'] = dict({'required' : ['tree'], 'optional' : ['group','groups','name','iters','random','processors']})
     cmd_dict['pca'] = dict({'required' : [['shared','relabund']], 'optional' : ['label','groups','metric']})
     cmd_dict['pcoa'] = dict({'required' : ['phylip'], 'optional' : ['metric']})
+
+    cmd_dict['pcr.seqs'] = dict({'required' : ['fasta'], 'optional' : ['oligos','name','group','taxonomy','ecoli','start','end','nomatch','keepprimer','keepdots','processors']})
+
     cmd_dict['phylo.diversity'] = dict({'required' : ['tree'],'optional' : ['group','name','groups','iters','freq','scale','rarefy','collect','summary','processors']})
     cmd_dict['phylotype'] = dict({'required' : ['taxonomy'],'optional' : ['name','cutoff','label']})
     cmd_dict['pre.cluster'] = dict({'required' : ['fasta'],  'optional' : ['name','diffs','group','processors']})
@@ -272,11 +284,11 @@
     cmd_dict['summary.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','groups','all','distance','processors']})
     cmd_dict['summary.single'] = dict({'required' : [['list','sabund','rabund','shared']], 'optional' : ['calc','abund','size','label','groupmode']})
     cmd_dict['summary.tax'] = dict({'required' : ['taxonomy'], 'optional' : ['name','group','reftaxonomy']})
-    cmd_dict['tree.shared'] = dict({'required' : [['shared','phylip','column']], 'optional' : ['name','groups','calc','cutoff','precision','label']})
+    cmd_dict['tree.shared'] = dict({'required' : [['shared','phylip','column']], 'optional' : ['name','groups','calc','cutoff','precision','label','subsample','iters','processors']})
     cmd_dict['trim.flows'] = dict({'required' : ['flow'],  'optional' : ['oligos','bdiffs','pdiffs','tdiffs','ldiffs','sdiffs','minflows','maxflows','fasta','signal','noise','maxhomop','order','processors']})
     cmd_dict['trim.seqs'] = dict({'required' : ['fasta'],  'optional' : ['name','group','oligos','qfile','qaverage','qthreshold','qwindowaverage','qwindowsize','rollaverage','qstepsize','qtrim','flip','maxambig','maxhomop','minlength','maxlength','bdiffs','pdiffs','tdiffs','ldiffs','sdiffs','keepforward','allfiles','keepfirst','removelast','processors']})
-    cmd_dict['unifrac.unweighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','processors']})
-    cmd_dict['unifrac.weighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','processors']})
+    cmd_dict['unifrac.unweighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','subsample','consensus','processors']})
+    cmd_dict['unifrac.weighted'] = dict({'required' : ['tree'], 'optional' : ['name','group','groups','iters','distance','random','root','subsample','consensus','processors']})
     cmd_dict['unique.seqs'] = dict({'required' : ['fasta'],  'optional' : ['name']})
     cmd_dict['venn'] = dict({'required' : [['list','shared']], 'optional' : ['calc','label','groups','abund','nseqs','permute','fontsize']})
 
@@ -320,6 +332,7 @@
     parser.add_option( '--fasta', dest='fasta', help='fasta file paths' )
     parser.add_option( '--fastq', dest='fastq', help='fastq file paths' )
     parser.add_option( '--qfile', dest='qfile', help='Sequence read quality file (454 platform)' )
+    parser.add_option( '--repfasta', dest='repfasta', help='fasta file paths' )
     parser.add_option( '--qaverage', dest='qaverage', type="int", help='Remove sequences that have an average quality below the value' )
     parser.add_option( '--qthreshold', dest='qthreshold', type="int", help='If at any point a base call in a sequence has a quality score below the value provided to the option, the sequence is terminated' )
     parser.add_option( '--qwindowaverage', dest='qwindowaverage', type="int", help='Remove sequences that have a window average quality below the value' )
@@ -343,6 +356,7 @@
     parser.add_option( '--allfiles', dest='allfiles', help='T - generate fasta and group for each barcode' )
     parser.add_option( '--keepforward', dest='keepforward', help='T - keep primer' )
     parser.add_option( '--name', dest='name', help='A file containing a 2 column table: name, and comma separated list of represetatives' )
+    parser.add_option( '--repname', dest='repname', help='A file containing a 2 column table: name, and comma separated list of represetatives' )
     parser.add_option( '--accnos', dest='accnos', help='A file containing a list of names' )
     parser.add_option( '--groups', dest='groups', help='pairwise group labels' )
     parser.add_option( '--group', dest='group', help='A file containing a list of names' )
@@ -351,6 +365,7 @@
     parser.add_option( '--report', dest='report', help='' )
     parser.add_option( '--taxonomy', dest='taxonomy', help='A Taxonomy file' )
     parser.add_option( '--reftaxonomy', dest='reftaxonomy', help='A Taxonomy file' )
+    parser.add_option( '--contaxonomy', dest='contaxonomy', help='The Taxonomy file output by classify.otu' )
     parser.add_option( '--taxon', dest='taxon',  help='A Taxon' )
     parser.add_option( '--taxlevel', dest='taxlevel', type="int", help='A Taxonomy level' )
     # parser.add_option( '--taxon', dest='taxon', action="callback", callback=remove_confidence_callback, help='A Taxon' )
@@ -401,6 +416,7 @@
     parser.add_option( '--iters', dest='iters', type='int', help='Iterations of randomizations' )
     parser.add_option( '--maxiter', dest='maxiter', type='int', help='Iterations' )
     parser.add_option( '--maxiters', dest='maxiters', type='int', help='Iterations of randomizations' )
+    parser.add_option( '--subsample', dest='subsample', help='Number of subsample, or T to default to smallest group size' )
     parser.add_option( '--jumble', dest='jumble',  help='If false, just a collector curve across the samples' )
     parser.add_option( '--conservation', dest='conservation',  help='Template frequency information' )
     parser.add_option( '--quantile', dest='quantile',  help='Template quantile information' )
@@ -461,6 +477,7 @@
     parser.add_option( '--design', dest='design', help='' )
     parser.add_option( '--sets', dest='sets', help='' )
     parser.add_option( '--metric', dest='metric', help='' )
+    parser.add_option( '--matrixmodel', dest='matrixmodel', help='' )
     parser.add_option( '--epsilon', dest='epsilon', help='' )
     parser.add_option( '--alpha', dest='alpha', help='' )
     parser.add_option( '--root', dest='root', help='' )
@@ -491,6 +508,13 @@
     parser.add_option( '--queryfract', dest='queryfract', type="float", help='')
     parser.add_option( '--minlen', dest='minlen', type="int", help='Minimun sequence length' )
     parser.add_option( '--maxlen', dest='maxlen', type="int", help='Maximun sequence length' )
+    parser.add_option( '--ecoli', dest='ecoli',  help='ecoli referance fasta' )
+    parser.add_option( '--nomatch', dest='nomatch',  help='What to with non matching items' )
+    parser.add_option( '--keepprimer', dest='keepprimer',  help='Whether to retain the primer' )
+    parser.add_option( '--keepdots', dest='keepdots',  help='Whether to retain dots in the sequence' )
+    parser.add_option( '--matrixtype', dest='matrixtype',  help='' )
+    parser.add_option( '--consensus', dest='consensus',  help='boolean' )
+    parser.add_option( '--biom', dest='biom',  help='biom file' )
     # include read.otu options
     parser.add_option( '--rabund', dest='rabund', help='' )
     parser.add_option( '--sabund', dest='sabund', help='' )