comparison mothur/lib/galaxy/datatypes/metagenomics.py @ 30:a90d1915a176

metagenomics.py - require ref.taxonomy sniff to find at least 1 multi-level tax assignment with semicolon separators

29:9c0cd3b92295

        return False

class OtuList( Otu ):
    file_ext = 'list'
    def __init__(self, **kwd):
        Otu.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Otu.init_meta( self, dataset, copy_from=copy_from )
    def set_meta( self, dataset, overwrite = True, **kwd ):
        Otu.set_meta(self,dataset, overwrite = True, **kwd )

        """

class Sabund( Otu ):
    file_ext = 'sabund'
    def __init__(self, **kwd):
        Otu.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Otu.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        return False

class Rabund( Sabund ):
    file_ext = 'rabund'
    def __init__(self, **kwd):
        Sabund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Sabund.init_meta( self, dataset, copy_from=copy_from )

class GroupAbund( Otu ):

        return False

class SharedRabund( GroupAbund ):
    file_ext = 'shared'
    def __init__(self, **kwd):
        GroupAbund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        GroupAbund.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        

class RelAbund( GroupAbund ):
    file_ext = 'relabund'
    def __init__(self, **kwd):
        GroupAbund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        GroupAbund.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        self.columns = 8

class Names(Tabular):
    file_ext = 'names'
    def __init__(self, **kwd):
        """Name file shows the relationship between a representative sequence(col 1)  and the sequences(comma-separated) it represents(col 2)"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','representatives']
        self.columns = 2

class Summary(Tabular):

class Group(Tabular):
    file_ext = 'groups'
    MetadataElement( name="groups", default=[], desc="Group Names", readonly=True, visible=True, no_value=[] )
    def __init__(self, **kwd):
        """Group file assigns sequence (col 1)  to a group (col 2)"""
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','group']
        self.columns = 2
    def set_meta( self, dataset, overwrite = True, skip = None, max_data_lines = None, **kwd ):
        Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines)

            fh.close()

class Design(Group):
    file_ext = 'design'
    def __init__(self, **kwd):
        """Design file shows the relationship between a group(col 1) and a grouping (col 2), providing a way to merge groups."""
        Group.__init__( self, **kwd )

class AccNos(Tabular):
    file_ext = 'accnos'
    def __init__(self, **kwd):

class Oligos( Text ):
    file_ext = 'oligos'

    def sniff( self, filename ):
        """
        Determines whether the file is a otu (operational taxonomic unit) format
        """
        try:
            fh = open( filename )
            count = 0

    MetadataElement( name="groups", default=[], desc="Group Names", readonly=True, visible=True, no_value=[] )
    file_ext = 'count_table'

    def __init__(self, **kwd):
        """
        A table with first column names and following columns integer counts
        # Example 1:
        Representative_Sequence total   
        U68630  1
        U68595  1

            close(fh)

class RefTaxonomy(Tabular):
    file_ext = 'ref.taxonomy'
    """
        A table with 2 or 3 columns:
        - SequenceName
        - Taxonomy (semicolon-separated taxonomy in descending order)
        - integer ?
        Example: 2-column ( http://www.mothur.org/wiki/Taxonomy_outline )

        Tabular.__init__( self, **kwd )
        self.column_names = ['name','taxonomy']

    def sniff( self, filename ):
        """
        Determines whether the file is a SequenceTaxonomy
        """
        try:
            pat = '^([^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?(;[^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?)*(;)?)$'
            fh = open( filename )
            count = 0
            while True:
                line = fh.readline()
                if not line:
                    break #EOF
                line = line.strip()

                    fields = line.split('\t')
                    if not (2 <= len(fields) <= 3):
                        return False
                    if not re.match(pat,fields[1]):
                        return False
                    if len(fields) == 3:
                        check = int(fields[2])
                    count += 1
                    if count > 10:
                        break
            if count > 0:
                return True
        except:
            pass
        finally:
            fh.close()
        return False

class SequenceTaxonomy(RefTaxonomy):
    file_ext = 'seq.taxonomy'
    """
        A table with 2 columns:
        - SequenceName
        - Taxonomy (semicolon-separated taxonomy in descending order)
        Example:
          X56533.1        Eukaryota;Alveolata;Ciliophora;Intramacronucleata;Oligohymenophorea;Hymenostomatida;Tetrahymenina;Glaucomidae;Glaucoma;

            fh = open( filename )
            count = 0
            line = fh.readline()
            line = line.strip()
            col_cnt = None
            while True:
                line = fh.readline()
                line = line.strip()
                if not line:
                    break #EOF

                        if len(fields) != col_cnt :
                            return False
                        try:
                            for i in range(1, col_cnt):
                                check = float(fields[i])
                        except ValueError:
                            return False
                        count += 1
                    if count > 10:
                        return True
            if count > 0:
                return True
        except:
            pass
        finally:
            fh.close()
        return False

class SffFlow(Tabular):
    MetadataElement( name="flow_values", default="", no_value="", optional=True , desc="Total number of flow values", readonly=True)
    MetadataElement( name="flow_order", default="TACG", no_value="TACG", desc="Total number of flow values", readonly=False)
    file_ext = 'sff.flow'
    """
        The first line is the total number of flow values - 800 for Titanium data. For GS FLX it would be 400. 
        Following lines contain:
        - SequenceName
        - the number of useable flows as defined by 454's software
        - the flow intensity for each base going in the order of TACG.

30:a90d1915a176

        return False

class OtuList( Otu ):
    file_ext = 'list'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/List_file
        The first column is a label that represents the distance that sequences were assigned to OTUs.
        The number in the second column is the number of OTUs that have been formed. 
        Subsequent columns contain the names of sequences within each OTU separated by a comma.
        distance_label	otu_count	OTU1	OTU2	OTUn
        """
        Otu.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Otu.init_meta( self, dataset, copy_from=copy_from )
    def set_meta( self, dataset, overwrite = True, **kwd ):
        Otu.set_meta(self,dataset, overwrite = True, **kwd )

        """

class Sabund( Otu ):
    file_ext = 'sabund'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Sabund_file
        """
        Otu.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Otu.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        return False

class Rabund( Sabund ):
    file_ext = 'rabund'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Rabund_file
        """
        Sabund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        Sabund.init_meta( self, dataset, copy_from=copy_from )

class GroupAbund( Otu ):

        return False

class SharedRabund( GroupAbund ):
    file_ext = 'shared'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Shared_file
        A shared file is analogous to an rabund file. 
        The data in a shared file represent the number of times that an OTU is observed in multiple samples. 
        The structure of a shared file is analogous to an rabund file. 
        The first column contains the label for the comparison - this will be the value for the first column of each line from the original list file. 
        The second column contains the group name that designates where the data is coming from for that row. 
        The third column is the number of OTUs that were found between each of the groups and is the number of columns that follow. 
        Finally, the remaining columns indicate the number of sequences that belonged to each OTU from that group. 
        """
        GroupAbund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        GroupAbund.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        

class RelAbund( GroupAbund ):
    file_ext = 'relabund'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Relabund_file
        The structure of a relabund file is analogous to an shared file. 
        The first column contains the label for the comparison - this will be the value for the first column of each line from the original list file (e.g. final.an.list). 
        The second column contains the group name that designates where the data is coming from for that row. Next is the number of OTUs that were found between each of the groups and is the number of columns that follow. 
        Finally, the remaining columns indicate the relative abundance of each OTU from that group.
        """
        GroupAbund.__init__( self, **kwd )
    def init_meta( self, dataset, copy_from=None ):
        GroupAbund.init_meta( self, dataset, copy_from=copy_from )
    def sniff( self, filename ):
        """

        self.columns = 8

class Names(Tabular):
    file_ext = 'names'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Name_file
        Name file shows the relationship between a representative sequence(col 1)  and the sequences(comma-separated) it represents(col 2)
        """
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','representatives']
        self.columns = 2

class Summary(Tabular):

class Group(Tabular):
    file_ext = 'groups'
    MetadataElement( name="groups", default=[], desc="Group Names", readonly=True, visible=True, no_value=[] )
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Groups_file
        Group file assigns sequence (col 1)  to a group (col 2)
        """
        Tabular.__init__( self, **kwd )
        self.column_names = ['name','group']
        self.columns = 2
    def set_meta( self, dataset, overwrite = True, skip = None, max_data_lines = None, **kwd ):
        Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines)

            fh.close()

class Design(Group):
    file_ext = 'design'
    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Design_File
        Design file shows the relationship between a group(col 1) and a grouping (col 2), providing a way to merge groups.
        """
        Group.__init__( self, **kwd )

class AccNos(Tabular):
    file_ext = 'accnos'
    def __init__(self, **kwd):

class Oligos( Text ):
    file_ext = 'oligos'

    def sniff( self, filename ):
        """
        # http://www.mothur.org/wiki/Oligos_File
        Determines whether the file is a otu (operational taxonomic unit) format
        """
        try:
            fh = open( filename )
            count = 0

    MetadataElement( name="groups", default=[], desc="Group Names", readonly=True, visible=True, no_value=[] )
    file_ext = 'count_table'

    def __init__(self, **kwd):
        """
        # http://www.mothur.org/wiki/Count_File
        A table with first column names and following columns integer counts
        # Example 1:
        Representative_Sequence total   
        U68630  1
        U68595  1

            close(fh)

class RefTaxonomy(Tabular):
    file_ext = 'ref.taxonomy'
    """
        # http://www.mothur.org/wiki/Taxonomy_outline
        A table with 2 or 3 columns:
        - SequenceName
        - Taxonomy (semicolon-separated taxonomy in descending order)
        - integer ?
        Example: 2-column ( http://www.mothur.org/wiki/Taxonomy_outline )

        Tabular.__init__( self, **kwd )
        self.column_names = ['name','taxonomy']

    def sniff( self, filename ):
        """
        Determines whether the file is a Reference Taxonomy
        """
        try:
            pat = '^([^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?(;[^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?)*(;)?)$'
            fh = open( filename )
            count = 0
            # VAMPS  taxonomy files do not require a semicolon after the last taxonomy category
            # but assume assume the file will have some multi-level taxonomy assignments
            found_semicolons = False
            while True:
                line = fh.readline()
                if not line:
                    break #EOF
                line = line.strip()

                    fields = line.split('\t')
                    if not (2 <= len(fields) <= 3):
                        return False
                    if not re.match(pat,fields[1]):
                        return False
                    if not found_semicolons and str(fields[1]).count(';') > 0:
                        found_semicolons = True
                    if len(fields) == 3:
                        check = int(fields[2])
                    count += 1
                    if count > 100:
                        break
            if count > 0:
                # This will be true if at least one entry
                # has semicolons in the 2nd column
                return found_semicolons
        except:
            pass
        finally:
            fh.close()
        return False

class SequenceTaxonomy(RefTaxonomy):
    file_ext = 'seq.taxonomy'
    """
        # http://www.mothur.org/wiki/Taxonomy_outline
        A table with 2 columns:
        - SequenceName
        - Taxonomy (semicolon-separated taxonomy in descending order)
        Example:
          X56533.1        Eukaryota;Alveolata;Ciliophora;Intramacronucleata;Oligohymenophorea;Hymenostomatida;Tetrahymenina;Glaucomidae;Glaucoma;

            fh = open( filename )
            count = 0
            line = fh.readline()
            line = line.strip()
            col_cnt = None
            all_integers = True
            while True:
                line = fh.readline()
                line = line.strip()
                if not line:
                    break #EOF

                        if len(fields) != col_cnt :
                            return False
                        try:
                            for i in range(1, col_cnt):
                                check = float(fields[i])
                                # Also test for whether value is an integer
                                try:
                                    check = int(fields[i])
                                except ValueError:
                                    all_integers = False
                        except ValueError:
                            return False
                        count += 1
                    if count > 10:
                        break
            if count > 0:
                if not all_integers:
                    # At least one value was a float
                    return True
                else:
                    return False
        except:
            pass
        finally:
            fh.close()
        return False

class SffFlow(Tabular):
    MetadataElement( name="flow_values", default="", no_value="", optional=True , desc="Total number of flow values", readonly=True)
    MetadataElement( name="flow_order", default="TACG", no_value="TACG", desc="Total number of flow values", readonly=False)
    file_ext = 'sff.flow'
    """
        # http://www.mothur.org/wiki/Flow_file
        The first line is the total number of flow values - 800 for Titanium data. For GS FLX it would be 400. 
        Following lines contain:
        - SequenceName
        - the number of useable flows as defined by 454's software
        - the flow intensity for each base going in the order of TACG.