comparison mothur/tools/mothur/mothur_wrapper.py @ 24:09740be2bc9c

Mothur - updates for Mothur version 1.24

23:efd36aa39261

"""
http://www.mothur.org/

Supports mothur version 
mothur v.1.23.0

Class encapsulating Mothur galaxy tool.
Expect each invocation to include:
Here is an example call to this script with an explanation before each param :
 mothur_wrapper.py

    cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','reference'], 'optional' : ['name','group','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','split','blastlocation','save','processors']})
    cmd_dict['chimera.uchime'] = dict({'required' : ['fasta'], 'optional' : ['name','group','reference','abskew','chimealns','minh','mindiv','xn','dn','xa','chunks','minchunk','idsmoothwindow','minsmoothid','maxp','skipgaps','skipgaps2','minlen','maxlen','ucl','queryfract','processors']})
    cmd_dict['chop.seqs'] = dict({'required' : ['fasta','numbases'],  'optional' : ['countgaps','keep','short']})
    cmd_dict['classify.otu'] = dict({'required' : ['list','taxonomy'],'optional' : ['name','cutoff','label','group','probs','basis','reftaxonomy']})
    cmd_dict['classify.seqs'] = dict({'required' : ['fasta','reference','taxonomy'],'optional' : ['name','search','ksize','method','match','mismatch','gapopen','gapextend','numwanted','probs','save','processors']})
    #clear.memory ## not needed in galaxy framework
    cmd_dict['clearcut'] = dict({'required' : [['phylip','fasta']],'optional' : ['seed','norandom','shuffle','neighbor','expblen','expdist','ntrees','matrixout','kimura','jukes','protein','DNA']})
    cmd_dict['cluster'] = dict({'required' : [['phylip','column']] ,  'optional' : ['name','method','cutoff','hard','precision','sim','showabund','timing']})
    cmd_dict['cluster.classic'] = dict({'required' : ['phylip'] ,  'optional' : ['name','method','cutoff','hard','sim','precision']})
    cmd_dict['cluster.fragments'] = dict({'required' : ['fasta'] ,  'optional' : ['name','diffs','percent']})

    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['fastq.info'] = dict({'required' : ['fastq'], 'optional' : []})
    cmd_dict['filter.seqs'] = dict({'required' : ['fasta'],  'optional' : ['vertical','trump','soft','hard','processors']})
    cmd_dict['get.group'] = dict({'required' : ['shared'], 'optional' : []})
    cmd_dict['get.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','shared','taxonomy']})
    cmd_dict['get.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']})
    cmd_dict['get.otulist'] = dict({'required' : ['list'], 'optional' : ['label','sort']})
    cmd_dict['get.oturep'] = dict({'required' : ['list',['phylip','column']], 'optional' : ['fasta','name','label','group','groups','sorted','precision','cutoff','large','weighted']})
    cmd_dict['get.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']})
    cmd_dict['get.rabund'] = dict({'required' : [['list','sabund']],'optional' : ['sorted','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['mantel'] = dict({'required' : ['phylip','phylip2'] ,  'optional' : ['method','iters']})
    cmd_dict['merge.files'] = dict({'required' : ['input','output']})
    cmd_dict['merge.groups'] = dict({'required' : ['shared','design'],  'optional' : ['groups', 'label']})
    cmd_dict['metastats'] = dict({'required' : ['shared','design'],  'optional' : ['groups', 'label','iters','threshold','sets','processors']})
    cmd_dict['nmds'] = dict({'required' : ['phylip'], 'optional' : ['axes','mindim','maxdim','iters','maxiters','epsilon']})
    cmd_dict['normalize.shared'] = dict({'required' : [['shared','relabund']], 'optional' : ['label','method','norm','groups','makerelabund']})
    cmd_dict['otu.hierarchy'] = dict({'required' : ['list','label'], 'optional' : ['output']})
    cmd_dict['pairwise.seqs'] = dict({'required' : ['fasta'],  'optional' : ['align','calc','countends','output','cutoff','match','mismatch','gapopen','gapextend','processors']})
    cmd_dict['parse.list'] = dict({'required' : ['list','group'], 'optional' : ['label']})
    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['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']})
    cmd_dict['rarefaction.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','iters','groups','jumble']})
    cmd_dict['rarefaction.single'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['calc','abund','iters','label','freq','processors']})
    cmd_dict['remove.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','shared','taxonomy']})
    cmd_dict['remove.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']})
    cmd_dict['remove.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']})
    cmd_dict['remove.rare'] = dict({'required' : [['list','sabund','rabund','shared'],'nseqs'], 'optional' : ['group','groups','label','bygroup']})
    cmd_dict['remove.seqs'] = dict({'required' : ['accnos',['fasta','qfile','name','group','list','alignreport','taxonomy']], 'optional' : ['dups']})
    cmd_dict['reverse.seqs'] = dict({'required' : ['fasta']})
    cmd_dict['screen.seqs'] = dict({'required' : ['fasta'],  'optional' : ['start','end','maxambig','maxhomop','minlength','maxlength','criteria','optimize','name','group','alignreport'''taxonomy','processors']})
    cmd_dict['sens.spec'] = dict({'required' : ['list',['column','phylip']] , 'optional' : ['label','cutoff','hard','precision']})

    cmd_dict['seq.error'] = dict({'required' : ['fasta','reference'] , 'optional' : ['name','qfile','report','ignorechimeras','threshold','processors']})

    cmd_dict['sffinfo'] = dict({'required' : [['sff','sfftxt']], 'optional' : ['fasta','qfile','trim','sfftxt','flow','accnos']})

    cmd_dict['shhh.flows'] = dict({'required' : [['flow','files']], 'optional' : ['lookup','maxiter','mindelta','cutoff','sigma','order','processors']})
    cmd_dict['shhh.seqs'] = dict({'required' : [['fasta','files']], 'optional' : ['group','sigma','processors']})

    cmd_dict['split.abund'] = dict({'required' : ['fasta',['name','list']], 'optional' : ['cutoff','group','groups','label','accnos']})
    cmd_dict['split.groups'] = dict({'required' : ['fasta','group'], 'optional' : ['name','groups']})
    cmd_dict['sub.sample'] = dict({'required' : [['fasta','list','sabund','rabund','shared']], 'optional' : ['name','group','groups','label','size','persample']})
    cmd_dict['summary.qual'] = dict({'required' : ['qfile'], 'optional' : ['name']})
    cmd_dict['summary.seqs'] = dict({'required' : ['fasta'], 'optional' : ['name','processors']})
    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['trim.flows'] = dict({'required' : ['flow'],  'optional' : ['oligos','bdiffs','pdiffs','tdiffs','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','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['unique.seqs'] = dict({'required' : ['fasta'],  'optional' : ['name']})
    cmd_dict['venn'] = dict({'required' : [['list','shared']], 'optional' : ['calc','label','groups','abund','nseqs','permute','fontsize']})

    parser.add_option( '--minlength', dest='minlength', type="int", help='Minimun sequence length' )
    parser.add_option( '--maxlength', dest='maxlength', type="int", help='Maximun sequence length' )
    parser.add_option( '--oligos', dest='oligos', help='The oligos option takes a file that can contain the sequences of the forward and reverse primers and barcodes and their sample identifier.' )
    parser.add_option( '--bdiffs', dest='bdiffs', type="int", help='Number of barcode differences to allow' )
    parser.add_option( '--pdiffs', dest='pdiffs', type="int", help='Number of primer differences to allow' )
    parser.add_option( '--tdiffs', dest='tdiffs', type="int", help='Total number of barcode and primer differences to allow' )
    parser.add_option( '--diffs', dest='diffs', type="int", help='Number of mismatched bases to allow between sequences in a group' )
    parser.add_option( '--allfiles', dest='allfiles', help='T - generate fasta and group for each barcode' )
    parser.add_option( '--name', dest='name', 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' )
    parser.add_option( '--list', dest='list', help='A file containing a list of names' )

24:09740be2bc9c

"""
http://www.mothur.org/

Supports mothur version 
mothur v.1.24.0

Class encapsulating Mothur galaxy tool.
Expect each invocation to include:
Here is an example call to this script with an explanation before each param :
 mothur_wrapper.py

    cmd_dict['chimera.slayer'] = dict({'required' : ['fasta','reference'], 'optional' : ['name','group','search','window','increment','match','mismatch','numwanted','parents','minsim','mincov','iters','minbs','minsnp','divergence','realign','split','blastlocation','save','processors']})
    cmd_dict['chimera.uchime'] = dict({'required' : ['fasta'], 'optional' : ['name','group','reference','abskew','chimealns','minh','mindiv','xn','dn','xa','chunks','minchunk','idsmoothwindow','minsmoothid','maxp','skipgaps','skipgaps2','minlen','maxlen','ucl','queryfract','processors']})
    cmd_dict['chop.seqs'] = dict({'required' : ['fasta','numbases'],  'optional' : ['countgaps','keep','short']})
    cmd_dict['classify.otu'] = dict({'required' : ['list','taxonomy'],'optional' : ['name','cutoff','label','group','probs','basis','reftaxonomy']})
    cmd_dict['classify.seqs'] = dict({'required' : ['fasta','reference','taxonomy'],'optional' : ['name','search','ksize','method','match','mismatch','gapopen','gapextend','numwanted','probs','save','processors']})
    cmd_dict['classify.tree'] = dict({'required' : ['taxonomy','tree'],'optional' : ['name','group','cutoff']})
    #clear.memory ## not needed in galaxy framework
    cmd_dict['clearcut'] = dict({'required' : [['phylip','fasta']],'optional' : ['seed','norandom','shuffle','neighbor','expblen','expdist','ntrees','matrixout','kimura','jukes','protein','DNA']})
    cmd_dict['cluster'] = dict({'required' : [['phylip','column']] ,  'optional' : ['name','method','cutoff','hard','precision','sim','showabund','timing']})
    cmd_dict['cluster.classic'] = dict({'required' : ['phylip'] ,  'optional' : ['name','method','cutoff','hard','sim','precision']})
    cmd_dict['cluster.fragments'] = dict({'required' : ['fasta'] ,  'optional' : ['name','diffs','percent']})

    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['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' : []})
    cmd_dict['get.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','shared','taxonomy','design']})
    cmd_dict['get.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']})
    cmd_dict['get.otulist'] = dict({'required' : ['list'], 'optional' : ['label','sort']})
    cmd_dict['get.oturep'] = dict({'required' : ['list',['phylip','column']], 'optional' : ['fasta','name','label','group','groups','sorted','precision','cutoff','large','weighted']})
    cmd_dict['get.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']})
    cmd_dict['get.rabund'] = dict({'required' : [['list','sabund']],'optional' : ['sorted','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['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']})
    cmd_dict['metastats'] = dict({'required' : ['shared','design'],  'optional' : ['groups', 'label','iters','threshold','sets','processors']})
    cmd_dict['nmds'] = dict({'required' : ['phylip'], 'optional' : ['axes','mindim','maxdim','iters','maxiters','epsilon']})
    cmd_dict['normalize.shared'] = dict({'required' : [['shared','relabund']], 'optional' : ['label','method','norm','groups','makerelabund']})
    cmd_dict['otu.association'] = dict({'required' : [['shared','relabund']], 'optional' : ['groups', 'label','method']})
    cmd_dict['otu.hierarchy'] = dict({'required' : ['list','label'], 'optional' : ['output']})
    cmd_dict['pairwise.seqs'] = dict({'required' : ['fasta'],  'optional' : ['align','calc','countends','output','cutoff','match','mismatch','gapopen','gapextend','processors']})
    cmd_dict['parse.list'] = dict({'required' : ['list','group'], 'optional' : ['label']})
    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['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']})
    cmd_dict['rarefaction.shared'] = dict({'required' : ['shared'], 'optional' : ['calc','label','iters','groups','jumble']})
    cmd_dict['rarefaction.single'] = dict({'required' : [['list', 'sabund', 'rabund', 'shared']], 'optional' : ['calc','abund','iters','label','freq','processors']})
    cmd_dict['remove.groups'] = dict({'required' : ['group'], 'optional' : ['groups','accnos','fasta','name','list','shared','taxonomy','design']})
    cmd_dict['remove.lineage'] = dict({'required' : ['taxonomy','taxon'],'optional' : ['fasta','name','group','list','alignreport','dups']})
    cmd_dict['remove.otus'] = dict({'required' : ['group','list','label'], 'optional' : ['groups','accnos']})
    cmd_dict['remove.rare'] = dict({'required' : [['list','sabund','rabund','shared'],'nseqs'], 'optional' : ['group','groups','label','bygroup']})
    cmd_dict['remove.seqs'] = dict({'required' : ['accnos',['fasta','qfile','name','group','list','alignreport','taxonomy']], 'optional' : ['dups']})
    cmd_dict['reverse.seqs'] = dict({'required' : ['fasta']})
    cmd_dict['screen.seqs'] = dict({'required' : ['fasta'],  'optional' : ['start','end','maxambig','maxhomop','minlength','maxlength','criteria','optimize','name','group','alignreport','taxonomy','processors']})
    cmd_dict['sens.spec'] = dict({'required' : ['list',['column','phylip']] , 'optional' : ['label','cutoff','hard','precision']})
    cmd_dict['seq.error'] = dict({'required' : ['fasta','reference'] , 'optional' : ['name','qfile','report','ignorechimeras','threshold','processors']})
    cmd_dict['sffinfo'] = dict({'required' : [['sff','sfftxt']], 'optional' : ['fasta','qfile','trim','sfftxt','flow','accnos']})
    cmd_dict['shhh.flows'] = dict({'required' : [['flow','files']], 'optional' : ['lookup','maxiter','mindelta','cutoff','sigma','order','processors']})
    cmd_dict['shhh.seqs'] = dict({'required' : [['fasta','files']], 'optional' : ['group','sigma','processors']})
    cmd_dict['split.abund'] = dict({'required' : ['fasta',['name','list']], 'optional' : ['cutoff','group','groups','label','accnos']})
    cmd_dict['split.groups'] = dict({'required' : ['fasta','group'], 'optional' : ['name','groups']})
    cmd_dict['sort.seqs'] = dict({'required' : [['fasta','qfile','name','group','flow','taxonomy']], 'optional' : ['accnos','large']})
    cmd_dict['sub.sample'] = dict({'required' : [['fasta','list','sabund','rabund','shared']], 'optional' : ['name','group','groups','label','size','persample']})
    cmd_dict['summary.qual'] = dict({'required' : ['qfile'], 'optional' : ['name']})
    cmd_dict['summary.seqs'] = dict({'required' : ['fasta'], 'optional' : ['name','processors']})
    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['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['unique.seqs'] = dict({'required' : ['fasta'],  'optional' : ['name']})
    cmd_dict['venn'] = dict({'required' : [['list','shared']], 'optional' : ['calc','label','groups','abund','nseqs','permute','fontsize']})

    parser.add_option( '--minlength', dest='minlength', type="int", help='Minimun sequence length' )
    parser.add_option( '--maxlength', dest='maxlength', type="int", help='Maximun sequence length' )
    parser.add_option( '--oligos', dest='oligos', help='The oligos option takes a file that can contain the sequences of the forward and reverse primers and barcodes and their sample identifier.' )
    parser.add_option( '--bdiffs', dest='bdiffs', type="int", help='Number of barcode differences to allow' )
    parser.add_option( '--pdiffs', dest='pdiffs', type="int", help='Number of primer differences to allow' )
    parser.add_option( '--ldiffs', dest='ldiffs', type="int", help='Number of linker sequence differences to allow' )
    parser.add_option( '--sdiffs', dest='sdiffs', type="int", help='Number of spacer sequence differences to allow' )
    parser.add_option( '--tdiffs', dest='tdiffs', type="int", help='Total number of barcode and primer differences to allow' )
    parser.add_option( '--diffs', dest='diffs', type="int", help='Number of mismatched bases to allow between sequences in a group' )
    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( '--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' )
    parser.add_option( '--list', dest='list', help='A file containing a list of names' )