comparison mothur/lib/galaxy/datatypes/metagenomics.py @ 17:57df76d861e4

Modifications for ToolShed proprietary data types

16:541e3c97c240

metagenomics datatypes
James E Johnson - University of Minnesota
for Mothur
"""

import data
import logging, os, sys, time, tempfile, shutil, string, glob, re
import galaxy.model
from galaxy.datatypes import metadata
from galaxy.datatypes import tabular
from galaxy.datatypes import sequence
from galaxy.datatypes.metadata import MetadataElement
from galaxy.datatypes.tabular import Tabular
from galaxy.datatypes.sequence import Fasta
from galaxy import util
from galaxy.datatypes.images import Html
from sniff import *

log = logging.getLogger(__name__)


## Mothur Classes 

    def __init__(self, **kwd):
        """Initialize SecondaryStructureMatch datatype"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','pound','dash','plus','equal','loop','tilde','total']

class DistanceMatrix(data.Text):
    file_ext = 'dist'
    """Add metadata elements"""
    MetadataElement( name="sequence_count", default=0, desc="Number of sequences", readonly=False, optional=True, no_value=0 )

    def __init__(self, **kwd):
        """Initialize secondary structure map datatype"""
        Tabular.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        data.Text.init_meta( self, dataset, copy_from=copy_from )
    def set_meta( self, dataset, overwrite = True, skip = None, **kwd ):
        dataset.metadata.sequences = 0 

    def sniff( self, filename ):
        """

        """A list of names"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name']
        self.columns = 1

class Oligos( data.Text ):
    file_ext = 'oligos'

    def sniff( self, filename ):
        """
        Determines whether the file is a otu (operational taxonomic unit) format

        """Quantiles for chimera analysis"""
        Quantile.__init__( self, **kwd )
        self.masked = True
        self.filtered = True

class LaneMask(data.Text):
    file_ext = 'filter'

    def sniff( self, filename ):
        """
        Determines whether the file is a lane mask filter:  1 line consisting of zeros and ones.

    def __init__(self, **kwd):
        """A Summary of taxon classification"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['taxlevel','rankID','taxon','daughterlevels','total']

class Phylip(data.Text):
    file_ext = 'phy'

    def sniff( self, filename ):
        """
        Determines whether the file is in Phylip format (Interleaved or Sequential)

            out = "".join( out )
        except Exception, exc:
            out = "Can't create peek %s" % str( exc )
        return out


## Qiime Classes

class QiimeMetadataMapping(Tabular):
    MetadataElement( name="column_names", default=[], desc="Column Names", readonly=False, visible=True, no_value=[] )

pick_rep_set:rep_set_picking_method     first
pick_rep_set:sort_by    otu
    """
    file_ext = 'qiimeparams'

class QiimePrefs(data.Text):
    """
    A text file, containing coloring preferences to be used by make_distance_histograms.py, make_2d_plots.py and make_3d_plots.py.
    Example:
{
'background_color':'black',

17:57df76d861e4

metagenomics datatypes
James E Johnson - University of Minnesota
for Mothur
"""

import logging, os, os.path, sys, time, tempfile, shutil, string, glob, re
import galaxy.model
from galaxy.datatypes import data
from galaxy.datatypes.sniff import *
from galaxy.datatypes import metadata
from galaxy.datatypes import tabular
from galaxy.datatypes import sequence
from galaxy.datatypes.metadata import MetadataElement
from galaxy.datatypes.data import Text
from galaxy.datatypes.tabular import Tabular
from galaxy.datatypes.sequence import Fasta
from galaxy import util
from galaxy.datatypes.images import Html

log = logging.getLogger(__name__)


## Mothur Classes 

    def __init__(self, **kwd):
        """Initialize SecondaryStructureMatch datatype"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','pound','dash','plus','equal','loop','tilde','total']

class DistanceMatrix( Text ):
    file_ext = 'dist'
    """Add metadata elements"""
    MetadataElement( name="sequence_count", default=0, desc="Number of sequences", readonly=False, optional=True, no_value=0 )

    def __init__(self, **kwd):
        """Initialize secondary structure map datatype"""
        Tabular.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Text.init_meta( self, dataset, copy_from=copy_from )
    def set_meta( self, dataset, overwrite = True, skip = None, **kwd ):
        dataset.metadata.sequences = 0 

    def sniff( self, filename ):
        """

        """A list of names"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name']
        self.columns = 1

class Oligos( Text ):
    file_ext = 'oligos'

    def sniff( self, filename ):
        """
        Determines whether the file is a otu (operational taxonomic unit) format

        """Quantiles for chimera analysis"""
        Quantile.__init__( self, **kwd )
        self.masked = True
        self.filtered = True

class LaneMask(Text):
    file_ext = 'filter'

    def sniff( self, filename ):
        """
        Determines whether the file is a lane mask filter:  1 line consisting of zeros and ones.

    def __init__(self, **kwd):
        """A Summary of taxon classification"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['taxlevel','rankID','taxon','daughterlevels','total']

class Phylip(Text):
    file_ext = 'phy'

    def sniff( self, filename ):
        """
        Determines whether the file is in Phylip format (Interleaved or Sequential)

            out = "".join( out )
        except Exception, exc:
            out = "Can't create peek %s" % str( exc )
        return out

class Newick( Text ):
    """
    The Newick Standard for representing trees in computer-readable form makes use of the correspondence between trees and nested parentheses.
    http://evolution.genetics.washington.edu/phylip/newicktree.html
    http://en.wikipedia.org/wiki/Newick_format
    Example:
    (B,(A,C,E),D);
    or example with branch lengths:
    (B:6.0,(A:5.0,C:3.0,E:4.0):5.0,D:11.0);
    or an example with embedded comments but no branch lengths:
    ((a [&&PRIME S=x], b [&&PRIME S=y]), c [&&PRIME S=z]); 
    Example with named interior noe:
    (B:6.0,(A:5.0,C:3.0,E:4.0)Ancestor1:5.0,D:11.0);
    """
    file_ext = 'tre'

    def __init__(self, **kwd):
        Text.__init__( self, **kwd )

    def sniff( self, filename ):   ## TODO
        """
        Determine whether the file is in Newick format
        Note: Last non-space char of a tree should be a semicolon: ';'
        Usually the first char will be a open parenthesis: '('
        (,,(,));                               no nodes are named
        (A,B,(C,D));                           leaf nodes are named
        (A,B,(C,D)E)F;                         all nodes are named
        (:0.1,:0.2,(:0.3,:0.4):0.5);           all but root node have a distance to parent
        (:0.1,:0.2,(:0.3,:0.4):0.5):0.0;       all have a distance to parent
        (A:0.1,B:0.2,(C:0.3,D:0.4):0.5);       distances and leaf names (popular)
        (A:0.1,B:0.2,(C:0.3,D:0.4)E:0.5)F;     distances and all names
        ((B:0.2,(C:0.3,D:0.4)E:0.5)F:0.1)A;    a tree rooted on a leaf node (rare)
        """
        if not os.path.exists(filename):
            return False
        try:
            ## For now, guess this is a Newick file if it starts with a '(' and ends with a ';'
            flen = os.path.getsize(filename)
            fh = open( filename )
            len = min(flen,2000)
            # check end of the file for a semicolon
            fh.seek(-len,os.SEEK_END)
            buf = fh.read(len).strip()
            buf = buf.strip()
            if not buf.endswith(';'):
                return False
            # See if this starts with a open parenthesis
            if len < flen:
                fh.seek(0)
                buf = fh.read(len).strip()
            if buf.startswith('('):
                return True
        except:
            pass
        finally:
            close(fh)
        return False

class Nhx( Newick ):
    """
    New Hampshire eXtended  Newick with embedded 
    The Newick Standard for representing trees in computer-readable form makes use of the correspondence between trees and nested parentheses.
    http://evolution.genetics.washington.edu/phylip/newicktree.html
    http://en.wikipedia.org/wiki/Newick_format
    Example:
    (gene1_Hu[&&NHX:S=Hu_Homo_sapiens], (gene2_Hu[&&NHX:S=Hu_Homo_sapiens], gene2_Mu[&&NHX:S=Mu_Mus_musculus]));
    """
    file_ext = 'nhx'

class Nexus( Text ):
    """
    http://en.wikipedia.org/wiki/Nexus_file
    Example:
    #NEXUS
    BEGIN TAXA;
          Dimensions NTax=4;
          TaxLabels fish frog snake mouse;
    END;
    
    BEGIN CHARACTERS;
          Dimensions NChar=20;
          Format DataType=DNA;
          Matrix
            fish   ACATA GAGGG TACCT CTAAG
            frog   ACATA GAGGG TACCT CTAAG
            snake  ACATA GAGGG TACCT CTAAG
            mouse  ACATA GAGGG TACCT CTAAG
    END;
    
    BEGIN TREES;
          Tree best=(fish, (frog, (snake, mouse)));
    END;
    """
    file_ext = 'nex'

    def __init__(self, **kwd):
        Text.__init__( self, **kwd )

    def sniff( self, filename ):
        """
        Determines whether the file is in nexus format
        First line should be:
        #NEXUS
        """
        try:
            fh = open( filename )
            count = 0
            line = fh.readline()
            line = line.strip()
            if line and line == '#NEXUS':
                fh.close()
                return True
        except:
            pass
        finally:
            fh.close()
        return False


## Qiime Classes

class QiimeMetadataMapping(Tabular):
    MetadataElement( name="column_names", default=[], desc="Column Names", readonly=False, visible=True, no_value=[] )

pick_rep_set:rep_set_picking_method     first
pick_rep_set:sort_by    otu
    """
    file_ext = 'qiimeparams'

class QiimePrefs(Text):
    """
    A text file, containing coloring preferences to be used by make_distance_histograms.py, make_2d_plots.py and make_3d_plots.py.
    Example:
{
'background_color':'black',