def sniff(self, filename):
"""
Try to guess if the file is a PDB file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('5e5z.pdb')
>>> PDB().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> PDB().sniff(fname)
False
"""
headers = get_headers(filename, sep=' ', count=300)
h = t = c = s = k = e = False
for line in headers:
section_name = line[0].strip()
if section_name == 'HEADER':
h = True
elif section_name == 'TITLE':
t = True
elif section_name == 'COMPND':
c = True
elif section_name == 'SOURCE':
s = True
elif section_name == 'KEYWDS':
k = True
elif section_name == 'EXPDTA':
e = True
if h * t * c * s * k * e:
return True
else:
return False
def sniff ( self, filename ):
"""
Determines whether the file is in generic fastq format
For details, see http://maq.sourceforge.net/fastq.shtml
Note: There are three kinds of FASTQ files, known as "Sanger" (sometimes called "Standard"), Solexa, and Illumina
These differ in the representation of the quality scores
>>> fname = get_test_fname( '1.fastqsanger' )
>>> Fastq().sniff( fname )
True
>>> fname = get_test_fname( '2.fastqsanger' )
>>> Fastq().sniff( fname )
True
"""
headers = get_headers( filename, None )
bases_regexp = re.compile( "^[NGTAC]*" )
# check that first block looks like a fastq block
try:
if len( headers ) >= 4 and headers[0][0] and headers[0][0][0] == "@" and headers[2][0] and headers[2][0][0] == "+" and headers[1][0]:
# Check the sequence line, make sure it contains only G/C/A/T/N
if not bases_regexp.match( headers[1][0] ):
return False
return True
return False
except:
return False
def sniff(self, filename):
"""
Try to guess if the file is a PDBQT file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('NuBBE_1_obabel_3D.pdbqt')
>>> PDBQT().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> PDBQT().sniff(fname)
False
"""
headers = get_headers(filename, sep=' ', count=300)
h = t = c = s = k = False
for line in headers:
section_name = line[0].strip()
if section_name == 'REMARK':
h = True
elif section_name == 'ROOT':
t = True
elif section_name == 'ENDROOT':
c = True
elif section_name == 'BRANCH':
s = True
elif section_name == 'TORSDOF':
k = True
if h * t * c * s * k:
return True
else:
return False
def sniff( self, filename ):
"""
Determines wether the file is in maf format
The .maf format is line-oriented. Each multiple alignment ends with a blank line.
Each sequence in an alignment is on a single line, which can get quite long, but
there is no length limit. Words in a line are delimited by any white space.
Lines starting with # are considered to be comments. Lines starting with ## can
be ignored by most programs, but contain meta-data of one form or another.
The first line of a .maf file begins with ##maf. This word is followed by white-space-separated
variable=value pairs. There should be no white space surrounding the "=".
For complete details see http://genome.ucsc.edu/FAQ/FAQformat#format5
>>> fname = get_test_fname( 'sequence.maf' )
>>> Maf().sniff( fname )
True
>>> fname = get_test_fname( 'sequence.fasta' )
>>> Maf().sniff( fname )
False
"""
headers = get_headers( filename, None )
try:
if len(headers) > 1 and headers[0][0] and headers[0][0] == "##maf":
return True
else:
return False
except:
return False
def sniff(self, filename):
"""
Determines whether the file is a secondary structure map format
A single column with an integer value which indicates the row that this
row maps to. Check to make sure if structMap[10] = 380 then
structMap[380] = 10 and vice versa.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.map' )
>>> SecondaryStructureMap().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.map' )
>>> SecondaryStructureMap().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
line_num = 0
rowidxmap = {}
for line in headers:
line_num += 1
if len(line) > 1:
return False
try:
pointer = int(line[0])
if pointer > line_num:
rowidxmap[pointer] = line_num
elif pointer > 0 or line_num in rowidxmap:
if rowidxmap[line_num] != pointer:
return False
except (ValueError, KeyError):
return False
if line_num < 3:
return False
return True
def sniff( self, filename ):
"""
Checks for 'pileup-ness'
There are two main types of pileup: 6-column and 10-column. For both,
the first three and last two columns are the same. We only check the
first three to allow for some personalization of the format.
>>> fname = get_test_fname( 'interval.interval' )
>>> Pileup().sniff( fname )
False
>>> fname = get_test_fname( '6col.pileup' )
>>> Pileup().sniff( fname )
True
>>> fname = get_test_fname( '10col.pileup' )
>>> Pileup().sniff( fname )
True
"""
headers = get_headers( filename, '\t' )
try:
for hdr in headers:
if hdr and not hdr[0].startswith( '#' ):
if len( hdr ) < 3:
return False
try:
# chrom start in column 1 (with 0-based columns)
# and reference base is in column 2
check = int( hdr[1] )
assert hdr[2] in [ 'A', 'C', 'G', 'T', 'N', 'a', 'c', 'g', 't', 'n' ]
except:
return False
return True
except:
return False
def sniff(self, filename):
"""
Determines whether the file is a pairwise distance matrix (Column-formatted distance matrix) format
The first and second columns have the sequence names and the third column is the distance between those sequences.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.pair.dist' )
>>> PairwiseDistanceMatrix().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.pair.dist' )
>>> PairwiseDistanceMatrix().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@'):
if len(line) != 3:
return False
try:
float(line[2])
try:
# See if it's also an integer
int(line[2])
except ValueError:
# At least one value is not an integer
all_ints = False
except ValueError:
return False
count += 1
if count > 2:
return not all_ints
return False
def set_meta(self, dataset, overwrite=True, **kwd):
super(Otu, self).set_meta(dataset, overwrite=overwrite, **kwd)
if dataset.has_data():
label_names = set()
otulabel_names = set()
ncols = 0
data_lines = 0
comment_lines = 0
headers = get_headers(dataset.file_name, sep='\t', count=-1)
# set otulabels
if len(headers[0]) > 2:
otulabel_names = headers[0][2:]
# set label names and number of lines
for line in headers:
if len(line) >= 2 and not line[0].startswith('@'):
data_lines += 1
ncols = max(ncols, len(line))
label_names.add(line[0])
else:
comment_lines += 1
# Set the discovered metadata values for the dataset
dataset.metadata.data_lines = data_lines
dataset.metadata.columns = ncols
dataset.metadata.labels = list(label_names)
dataset.metadata.labels.sort()
dataset.metadata.otulabels = list(otulabel_names)
dataset.metadata.otulabels.sort()
def sniff(self, filename):
"""
http://www.mothur.org/wiki/Oligos_File
Determines whether the file is a otu (operational taxonomic unit) format
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.oligos' )
>>> Oligos().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.oligos' )
>>> Oligos().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@') and not line[0].startswith('#'):
if len(line) == 2 and line[0] in ['forward', 'reverse']:
count += 1
continue
elif len(line) == 3 and line[0] == 'barcode':
count += 1
continue
else:
return False
if count > 0:
return True
return False
def sniff(self, filename):
"""
Determines whether the file is otu (operational taxonomic unit) format
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.otu' )
>>> Otu().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.otu' )
>>> Otu().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@'):
if len(line) < 2:
return False
if count >= 1:
try:
check = int(line[1])
if check + 2 != len(line):
return False
except ValueError:
return False
count += 1
if count > 2:
return True
return False
def set_meta(self, dataset, overwrite=True, skip=1, **kwd):
super(GroupAbund, self).set_meta(dataset, overwrite=overwrite, **kwd)
# See if file starts with header line
if dataset.has_data():
label_names = set()
group_names = set()
data_lines = 0
comment_lines = 0
ncols = 0
headers = get_headers(dataset.file_name, sep='\t', count=-1)
for line in headers:
if line[0] == 'label' and line[1] == 'Group':
skip = 1
comment_lines += 1
else:
skip = 0
data_lines += 1
ncols = max(ncols, len(line))
label_names.add(line[0])
group_names.add(line[1])
# Set the discovered metadata values for the dataset
dataset.metadata.data_lines = data_lines
dataset.metadata.columns = ncols
dataset.metadata.labels = list(label_names)
dataset.metadata.labels.sort()
dataset.metadata.groups = list(group_names)
dataset.metadata.groups.sort()
dataset.metadata.skip = skip
def sniff(self, filename):
"""
Determines whether the file is otu (operational taxonomic unit) format
label<TAB>count[<TAB>value(1..n)]
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.sabund' )
>>> Sabund().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.sabund' )
>>> Sabund().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@'):
if len(line) < 2:
return False
try:
check = int(line[1])
if check + 2 != len(line):
return False
for i in range(2, len(line)):
int(line[i])
except ValueError:
return False
count += 1
if count > 0:
return True
return False
def sniff( self, filename ):
"""
Determines whether the file is in lav format
LAV is an alignment format developed by Webb Miller's group. It is the primary output format for BLASTZ.
The first line of a .lav file begins with #:lav.
For complete details see http://www.bioperl.org/wiki/LAV_alignment_format
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'alignment.lav' )
>>> Lav().sniff( fname )
True
>>> fname = get_test_fname( 'alignment.axt' )
>>> Lav().sniff( fname )
False
"""
headers = get_headers( filename, None )
try:
if len(headers) > 1 and headers[0][0] and headers[0][0].startswith('#:lav'):
return True
else:
return False
except:
return False
def set_meta(self, dataset, overwrite=True, skip=None, max_data_lines=None, **kwd):
super(Group, self).set_meta(dataset, overwrite, skip, max_data_lines)
group_names = set()
headers = get_headers(dataset.file_name, sep='\t', count=-1)
for line in headers:
if len(line) > 1:
group_names.add(line[1])
dataset.metadata.groups = list(group_names)
def sniff( self, filename ):
"""
InChI files starts with 'InChI='
"""
inchi_lines = get_headers( filename, sep=' ', count=10 )
for inchi in inchi_lines:
if not inchi[0].startswith('InChI='):
return False
return True
def set_meta(self, dataset, overwrite=True, skip=1, max_data_lines=None, **kwd):
super(SffFlow, self).set_meta(dataset, overwrite, 1, max_data_lines)
headers = get_headers(dataset.file_name, sep='\t', count=1)
try:
flow_values = int(headers[0][0])
dataset.metadata.flow_values = flow_values
except Exception as e:
log.warning("SffFlow set_meta %s" % e)
def sniff(self, filename):
"""
Determines whether the file is an axes format
The first line may have column headings.
The following lines have the name in the first column plus float columns for each axis.
==> 98_sq_phylip_amazon.fn.unique.pca.axes <==
group axis1 axis2
forest 0.000000 0.145743
pasture 0.145743 0.000000
==> 98_sq_phylip_amazon.nmds.axes <==
axis1 axis2
U68589 0.262608 -0.077498
U68590 0.027118 0.195197
U68591 0.329854 0.014395
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.axes' )
>>> Axes().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.axes' )
>>> Axes().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
col_cnt = None
all_integers = True
for line in headers:
if count != 0:
if col_cnt is None:
col_cnt = len(line)
if col_cnt < 2:
return False
else:
if len(line) != col_cnt:
return False
try:
for i in range(1, col_cnt):
check = float(line[i])
# Check abs value is <= 1.0
if abs(check) > 1.0:
return False
# Also test for whether value is an integer
try:
check = int(line[i])
except ValueError:
all_integers = False
except ValueError:
return False
count += 1
if count > 0:
return not all_integers
return False
def sniff(self, filename):
"""Determine if the file is in pdf format."""
headers = get_headers(filename, None, 1)
try:
if headers[0][0].startswith("%PDF"):
return True
else:
return False
except IndexError:
return False
def set_meta(self, dataset, overwrite=True, skip=0, **kwd):
super(DistanceMatrix, self).set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
headers = get_headers(dataset.file_name, sep='\t')
for line in headers:
if not line[0].startswith('@'):
try:
dataset.metadata.sequence_count = int(''.join(line)) # seq count sometimes preceded by tab
break
except Exception as e:
if not isinstance(self, PairwiseDistanceMatrix):
log.warning("DistanceMatrix set_meta %s" % e)
def sniff_prefix(self, file_prefix):
"""
Try to guess if the file is a Gal file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('test.gal')
>>> Gal().sniff(fname)
True
>>> fname = get_test_fname('test.gpr')
>>> Gal().sniff(fname)
False
"""
headers = get_headers(file_prefix, sep="\t", count=3)
return "ATF" in headers[0][0] and "GenePix ArrayList" in headers[2][0]
def set_meta(self, dataset, overwrite=True, skip=1, max_data_lines=None, **kwd):
super(CountTable, self).set_meta(dataset, overwrite=overwrite, **kwd)
headers = get_headers(dataset.file_name, sep='\t', count=1)
colnames = headers[0]
dataset.metadata.column_types = ['str'] + (['int'] * ( len(headers[0]) - 1))
if len(colnames) > 1:
dataset.metadata.columns = len(colnames)
if len(colnames) > 2:
dataset.metadata.groups = colnames[2:]
dataset.metadata.comment_lines = 1
dataset.metadata.data_lines -= 1
def sniff(self, filename):
"""
Determines whether the file is a lower-triangle distance matrix (phylip) format
The first line has the number of sequences in the matrix.
The remaining lines have the sequence name followed by a list of distances from all preceeding sequences
5 # possibly but not always preceded by a tab :/
U68589
U68590 0.3371
U68591 0.3609 0.3782
U68592 0.4155 0.3197 0.4148
U68593 0.2872 0.1690 0.3361 0.2842
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.lower.dist' )
>>> LowerTriangleDistanceMatrix().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.lower.dist' )
>>> LowerTriangleDistanceMatrix().sniff( fname )
False
"""
numlines = 300
headers = get_headers(filename, sep='\t', count=numlines)
line_num = 0
for line in headers:
if not line[0].startswith('@'):
# first line should contain the number of sequences in the file
if line_num == 0:
if len(line) > 2:
return False
else:
try:
sequence_count = int(''.join(line))
except ValueError:
return False
else:
# number of fields should equal the line number
if len(line) != (line_num):
return False
try:
# Distances should be floats
for column in line[2:]:
float(column)
except ValueError:
return False
line_num += 1
# check if the number of lines in the file was as expected
if line_num == sequence_count + 1 or line_num == numlines + 1:
return True
return False
def sniff(self, filename):
"""
Determines whether the file is a lower-triangle distance matrix (phylip) format
The first line has the number of sequences in the matrix.
The remaining lines have the sequence name followed by a list of distances from all preceeding sequences
5 # possibly but not always preceded by a tab :/
U68589
U68590 0.3371
U68591 0.3609 0.3782
U68592 0.4155 0.3197 0.4148
U68593 0.2872 0.1690 0.3361 0.2842
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.lower.dist' )
>>> LowerTriangleDistanceMatrix().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.lower.dist' )
>>> LowerTriangleDistanceMatrix().sniff( fname )
False
"""
numlines = 300
headers = get_headers(filename, sep='\t', count=numlines)
line_num = 0
for line in headers:
if not line[0].startswith('@'):
# first line should contain the number of sequences in the file
if line_num == 0:
if len(line) > 2:
return False
else:
try:
sequence_count = int(''.join(line))
except ValueError:
return False
else:
# number of fields should equal the line number
if len(line) != (line_num):
return False
try:
# Distances should be floats
for column in line[2:]:
float(column)
except ValueError:
return False
line_num += 1
# check if the number of lines in the file was as expected
if line_num == sequence_count + 1 or line_num == numlines + 1:
return True
return False
def set_meta(self, dataset, overwrite=True, **kwd):
"""
Set metadata for Otu files.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> from galaxy.util.bunch import Bunch
>>> dataset = Bunch()
>>> dataset.metadata = Bunch
>>> otu = Otu()
>>> dataset.file_name = get_test_fname( 'mothur_datatypetest_true.mothur.otu' )
>>> dataset.has_data = lambda: True
>>> otu.set_meta(dataset)
>>> dataset.metadata.columns
100
>>> len(dataset.metadata.labels) == 37
True
>>> len(dataset.metadata.otulabels) == 98
True
"""
super(Otu, self).set_meta(dataset, overwrite=overwrite, **kwd)
if dataset.has_data():
label_names = set()
otulabel_names = set()
ncols = 0
data_lines = 0
comment_lines = 0
headers = iter_headers(dataset.file_name, sep='\t', count=-1)
first_line = get_headers(dataset.file_name, sep='\t', count=1)
if first_line:
first_line = first_line[0]
# set otulabels
if len(first_line) > 2:
otulabel_names = first_line[2:]
# set label names and number of lines
for line in headers:
if len(line) >= 2 and not line[0].startswith('@'):
data_lines += 1
ncols = max(ncols, len(line))
label_names.add(line[0])
else:
comment_lines += 1
# Set the discovered metadata values for the dataset
dataset.metadata.data_lines = data_lines
dataset.metadata.columns = ncols
dataset.metadata.labels = list(label_names)
dataset.metadata.labels.sort()
dataset.metadata.otulabels = list(otulabel_names)
dataset.metadata.otulabels.sort()
def set_meta(self, dataset, overwrite=True, **kwd):
"""
Set metadata for Otu files.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> from galaxy.util.bunch import Bunch
>>> dataset = Bunch()
>>> dataset.metadata = Bunch
>>> otu = Otu()
>>> dataset.file_name = get_test_fname( 'mothur_datatypetest_true.mothur.otu' )
>>> dataset.has_data = lambda: True
>>> otu.set_meta(dataset)
>>> dataset.metadata.columns
100
>>> len(dataset.metadata.labels) == 37
True
>>> len(dataset.metadata.otulabels) == 98
True
"""
super(Otu, self).set_meta(dataset, overwrite=overwrite, **kwd)
if dataset.has_data():
label_names = set()
otulabel_names = set()
ncols = 0
data_lines = 0
comment_lines = 0
headers = iter_headers(dataset.file_name, sep='\t', count=-1)
first_line = get_headers(dataset.file_name, sep='\t', count=1)
if first_line:
first_line = first_line[0]
# set otulabels
if len(first_line) > 2:
otulabel_names = first_line[2:]
# set label names and number of lines
for line in headers:
if len(line) >= 2 and not line[0].startswith('@'):
data_lines += 1
ncols = max(ncols, len(line))
label_names.add(line[0])
else:
comment_lines += 1
# Set the discovered metadata values for the dataset
dataset.metadata.data_lines = data_lines
dataset.metadata.columns = ncols
dataset.metadata.labels = list(label_names)
dataset.metadata.labels.sort()
dataset.metadata.otulabels = list(otulabel_names)
dataset.metadata.otulabels.sort()
def set_meta(self, dataset, overwrite=True, skip=1, max_data_lines=None, **kwd):
super(CountTable, self).set_meta(dataset, overwrite=overwrite, **kwd)
headers = get_headers(dataset.file_name, sep='\t', count=1)
colnames = headers[0]
dataset.metadata.column_types = ['str'] + (['int'] * (len(headers[0]) - 1))
if len(colnames) > 1:
dataset.metadata.columns = len(colnames)
if len(colnames) > 2:
dataset.metadata.groups = colnames[2:]
dataset.metadata.comment_lines = 1
if isinstance(dataset.metadata.data_lines, int):
dataset.metadata.data_lines -= 1
def sniff(self, filename):
"""
Determines whether the file is a Reference 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)
X56533.1 Eukaryota;Alveolata;Ciliophora;Intramacronucleata;Oligohymenophorea;Hymenostomatida;Tetrahymenina;Glaucomidae;Glaucoma;
X97975.1 Eukaryota;Parabasalidea;Trichomonada;Trichomonadida;unclassified_Trichomonadida;
AF052717.1 Eukaryota;Parabasalidea;
Example: 3-column (http://vamps.mbl.edu/resources/databases.php)
v3_AA008 Bacteria;Firmicutes;Bacilli;Lactobacillales;Streptococcaceae;Streptococcus 5
v3_AA016 Bacteria 120
v3_AA019 Archaea;Crenarchaeota;Marine_Group_I 1
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.ref.taxonomy' )
>>> RefTaxonomy().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.ref.taxonomy' )
>>> RefTaxonomy().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t', count=300)
count = 0
pat_prog = re.compile('^([^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?(;[^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?)*(;)?)$')
found_semicolons = False
for line in headers:
if not line[0].startswith('@') and not line[0].startswith('#'):
if not (2 <= len(line) <= 3):
return False
if not pat_prog.match(line[1]):
return False
if not found_semicolons and line[1].find(';') > -1:
found_semicolons = True
if len(line) == 3:
try:
int(line[2])
except Exception:
return False
count += 1
if count > 0:
# Require that at least one entry has semicolons in the 2nd column
return found_semicolons
return False
def set_meta(self,
dataset,
overwrite=True,
skip=1,
max_data_lines=None,
**kwd):
super(SffFlow, self).set_meta(dataset, overwrite, 1, max_data_lines)
headers = get_headers(dataset.file_name, sep='\t', count=1)
try:
flow_values = int(headers[0][0])
dataset.metadata.flow_values = flow_values
except Exception as e:
log.warning("SffFlow set_meta %s" % e)
def sniff(self, filename):
"""
Determines whether the file is a Reference 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)
X56533.1 Eukaryota;Alveolata;Ciliophora;Intramacronucleata;Oligohymenophorea;Hymenostomatida;Tetrahymenina;Glaucomidae;Glaucoma;
X97975.1 Eukaryota;Parabasalidea;Trichomonada;Trichomonadida;unclassified_Trichomonadida;
AF052717.1 Eukaryota;Parabasalidea;
Example: 3-column (http://vamps.mbl.edu/resources/databases.php)
v3_AA008 Bacteria;Firmicutes;Bacilli;Lactobacillales;Streptococcaceae;Streptococcus 5
v3_AA016 Bacteria 120
v3_AA019 Archaea;Crenarchaeota;Marine_Group_I 1
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.ref.taxonomy' )
>>> RefTaxonomy().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.ref.taxonomy' )
>>> RefTaxonomy().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t', count=300)
count = 0
pat_prog = re.compile('^([^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?(;[^ \t\n\r\x0c\x0b;]+([(]\\d+[)])?)*(;)?)$')
found_semicolons = False
for line in headers:
if not line[0].startswith('@') and not line[0].startswith('#'):
if not (2 <= len(line) <= 3):
return False
if not pat_prog.match(line[1]):
return False
if not found_semicolons and line[1].find(';') > -1:
found_semicolons = True
if len(line) == 3:
try:
int(line[2])
except Exception:
return False
count += 1
if count > 0:
# Require that at least one entry has semicolons in the 2nd column
return found_semicolons
return False
def set_meta(self,
dataset,
overwrite=True,
skip=None,
max_data_lines=None,
**kwd):
super(Group, self).set_meta(dataset, overwrite, skip, max_data_lines)
group_names = set()
headers = get_headers(dataset.file_name, sep='\t', count=-1)
for line in headers:
if len(line) > 1:
group_names.add(line[1])
dataset.metadata.groups = list(group_names)
def sniff(self, filename):
"""
Determines whether the file is a square distance matrix (Column-formatted distance matrix) format
The first line has the number of sequences in the matrix.
The following lines have the sequence name in the first column plus a column for the distance to each sequence
in the row order in which they appear in the matrix.
3
U68589 0.0000 0.3371 0.3610
U68590 0.3371 0.0000 0.3783
U68590 0.3371 0.0000 0.3783
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.square.dist' )
>>> SquareDistanceMatrix().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.square.dist' )
>>> SquareDistanceMatrix().sniff( fname )
False
"""
numlines = 300
headers = get_headers(filename, sep='\t', count=numlines)
line_num = 0
for line in headers:
if not line[0].startswith('@'):
if line_num == 0:
if len(line) > 2:
return False
else:
try:
sequence_count = int(''.join(line))
except ValueError:
return False
else:
# number of fields should equal the number of sequences
if len(line) != sequence_count + 1:
return False
try:
# Distances should be floats
for column in line[2:]:
float(column)
except ValueError:
return False
line_num += 1
# check if the number of lines in the file was as expected
if line_num == sequence_count + 1 or line_num == numlines + 1:
return True
return False
def sniff(self, filename):
"""
Determines whether the file is a square distance matrix (Column-formatted distance matrix) format
The first line has the number of sequences in the matrix.
The following lines have the sequence name in the first column plus a column for the distance to each sequence
in the row order in which they appear in the matrix.
3
U68589 0.0000 0.3371 0.3610
U68590 0.3371 0.0000 0.3783
U68590 0.3371 0.0000 0.3783
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.square.dist' )
>>> SquareDistanceMatrix().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.square.dist' )
>>> SquareDistanceMatrix().sniff( fname )
False
"""
numlines = 300
headers = get_headers(filename, sep='\t', count=numlines)
line_num = 0
for line in headers:
if not line[0].startswith('@'):
if line_num == 0:
if len(line) > 2:
return False
else:
try:
sequence_count = int(''.join(line))
except ValueError:
return False
else:
# number of fields should equal the number of sequences
if len(line) != sequence_count + 1:
return False
try:
# Distances should be floats
for column in line[2:]:
float(column)
except ValueError:
return False
line_num += 1
# check if the number of lines in the file was as expected
if line_num == sequence_count + 1 or line_num == numlines + 1:
return True
return False
def sniff(self, filename):
"""
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('test_tab.bed')
>>> PlantTribesKsComponents().sniff(fname)
False
>>> fname = get_test_fname('1.ptkscmp')
>>> PlantTribesKsComponents().sniff(fname)
True
"""
try:
line_item_str = get_headers(filename, '\\t', 1)[0][0]
return line_item_str == 'species\tn\tnumber_comp\tlnL\tAIC\tBIC\tmean\tvariance\tporportion'
except Exception:
return False
def set_meta(self, dataset, **kwd):
"""
Set metadata for Gal file.
"""
super().set_meta(dataset, **kwd)
headers = get_headers(dataset.file_name, sep="\t", count=5)
dataset.metadata.file_format = headers[0][0]
dataset.metadata.version_number = headers[0][1]
dataset.metadata.number_of_optional_header_records = int(headers[1][0])
dataset.metadata.number_of_data_columns = int(headers[1][1])
dataset.metadata.file_type = headers[2][0].strip().strip('"').split("=")[1]
if "BlockCount" in headers[3][0]:
dataset.metadata.block_count = int(headers[3][0].strip().strip('"').split("=")[1])
if "BlockType" in headers[4][0]:
dataset.metadata.block_type = int(headers[4][0].strip().strip('"').split("=")[1])
def sniff(self, filename):
"""
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('test_tab.bed')
>>> PlantTribesKsComponents().sniff(fname)
False
>>> fname = get_test_fname('1.ptkscmp')
>>> PlantTribesKsComponents().sniff(fname)
True
"""
try:
line_item_str = get_headers(filename, '\\t', 1)[0][0]
return line_item_str == 'species\tn\tnumber_comp\tlnL\tAIC\tBIC\tmean\tvariance\tporportion'
except Exception:
return False
def set_meta(self, dataset, overwrite=True, skip=0, **kwd):
super(DistanceMatrix, self).set_meta(dataset,
overwrite=overwrite,
skip=skip,
**kwd)
headers = get_headers(dataset.file_name, sep='\t')
for line in headers:
if not line[0].startswith('@'):
try:
dataset.metadata.sequence_count = int(
''.join(line)) # seq count sometimes preceded by tab
break
except Exception as e:
if not isinstance(self, PairwiseDistanceMatrix):
log.warning("DistanceMatrix set_meta %s" % e)
def sniff_prefix(self, file_prefix):
"""
Try to guess if the file is a FPS file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('q.fps')
>>> FPS().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> FPS().sniff(fname)
False
"""
header = get_headers(file_prefix, sep='\t', count=1)
if header[0][0].strip() == '#FPS1':
return True
else:
return False
def sniff_prefix(self, file_prefix):
"""
Try to guess if the file is a FPS file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('q.fps')
>>> FPS().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> FPS().sniff(fname)
False
"""
header = get_headers(file_prefix, sep='\t', count=1)
if header[0][0].strip() == '#FPS1':
return True
else:
return False
def sniff(self, filename):
"""
Try to guess if the file is a InChI file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('drugbank_drugs.inchi')
>>> InChI().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> InChI().sniff(fname)
False
"""
inchi_lines = get_headers(filename, sep=' ', count=10)
for inchi in inchi_lines:
if not inchi[0].startswith('InChI='):
return False
return True
def sniff(self, filename):
"""
Try to guess if the file is a InChI file.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('drugbank_drugs.inchi')
>>> InChI().sniff(fname)
True
>>> fname = get_test_fname('drugbank_drugs.cml')
>>> InChI().sniff(fname)
False
"""
inchi_lines = get_headers(filename, sep=' ', count=10)
for inchi in inchi_lines:
if not inchi[0].startswith('InChI='):
return False
return True
def sniff(self, filename):
"""
Determines whether the file is in axt format
axt alignment files are produced from Blastz, an alignment tool available from Webb Miller's lab
at Penn State University.
Each alignment block in an axt file contains three lines: a summary line and 2 sequence lines.
Blocks are separated from one another by blank lines.
The summary line contains chromosomal position and size information about the alignment. It
consists of 9 required fields.
The sequence lines contain the sequence of the primary assembly (line 2) and aligning assembly
(line 3) with inserts. Repeats are indicated by lower-case letters.
For complete details see http://genome.ucsc.edu/goldenPath/help/axt.html
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'alignment.axt' )
>>> Axt().sniff( fname )
True
>>> fname = get_test_fname( 'alignment.lav' )
>>> Axt().sniff( fname )
False
"""
headers = get_headers(filename, None)
if len(headers) < 4:
return False
for hdr in headers:
if len(hdr) > 0 and hdr[0].startswith("##matrix=axt"):
return True
if len(hdr) > 0 and not hdr[0].startswith("#"):
if len(hdr) != 9:
return False
try:
map(int, [hdr[0], hdr[2], hdr[3], hdr[5], hdr[6], hdr[8]])
except:
return False
if hdr[7] not in data.valid_strand:
return False
else:
return True
def sniff( self, filename ):
"""
Determines whether the file is in axt format
axt alignment files are produced from Blastz, an alignment tool available from Webb Miller's lab
at Penn State University.
Each alignment block in an axt file contains three lines: a summary line and 2 sequence lines.
Blocks are separated from one another by blank lines.
The summary line contains chromosomal position and size information about the alignment. It
consists of 9 required fields.
The sequence lines contain the sequence of the primary assembly (line 2) and aligning assembly
(line 3) with inserts. Repeats are indicated by lower-case letters.
For complete details see http://genome.ucsc.edu/goldenPath/help/axt.html
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'alignment.axt' )
>>> Axt().sniff( fname )
True
>>> fname = get_test_fname( 'alignment.lav' )
>>> Axt().sniff( fname )
False
"""
headers = get_headers( filename, None )
if len(headers) < 4:
return False
for hdr in headers:
if len(hdr) > 0 and hdr[0].startswith("##matrix=axt"):
return True
if len(hdr) > 0 and not hdr[0].startswith("#"):
if len(hdr) != 9:
return False
try:
map( int, [hdr[0], hdr[2], hdr[3], hdr[5], hdr[6], hdr[8]] )
except:
return False
if hdr[7] not in data.valid_strand:
return False
else:
return True
def sniff( self, filename ):
"""
Determines whether the file is in html format
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'complete.bed' )
>>> Html().sniff( fname )
False
>>> fname = get_test_fname( 'file.html' )
>>> Html().sniff( fname )
True
"""
headers = get_headers( filename, None )
try:
for i, hdr in enumerate(headers):
if hdr and hdr[0].lower().find( '<html>' ) >= 0:
return True
return False
except:
return True
def sniff(self, filename):
"""
Determines whether the file is in html format
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'complete.bed' )
>>> Html().sniff( fname )
False
>>> fname = get_test_fname( 'file.html' )
>>> Html().sniff( fname )
True
"""
headers = get_headers(filename, None)
try:
for i, hdr in enumerate(headers):
if hdr and hdr[0].lower().find('<html>') >= 0:
return True
return False
except:
return True
def sniff(self, filename):
"""
Determines whether the file is a lane mask filter: 1 line consisting of zeros and ones.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.filter' )
>>> LaneMask().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.filter' )
>>> LaneMask().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
if len(headers) != 1 or len(headers[0]) != 1:
return False
if not re.match('^[01]+$', headers[0][0]):
return False
return True
def sniff(self, filename):
"""
Determines whether the file is a lane mask filter: 1 line consisting of zeros and ones.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.filter' )
>>> LaneMask().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.filter' )
>>> LaneMask().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t', count=2)
if len(headers) != 1 or len(headers[0]) != 1:
return False
if not re.match('^[01]+$', headers[0][0]):
return False
return True
def sniff(self, filename):
headers = get_headers(filename, sep=' ', count=300)
h = t = c = s = k = e = False
for line in headers:
section_name = line[0].strip()
if section_name == 'HEADER':
h = True
elif section_name == 'TITLE':
t = True
elif section_name == 'COMPND':
c = True
elif section_name == 'SOURCE':
s = True
elif section_name == 'KEYWDS':
k = True
elif section_name == 'EXPDTA':
e = True
if h * t * c * s * k * e == True:
return True
else:
return False
def sniff(self, filename):
"""
Determines whether the file is a frequency tabular format for chimera analysis
#1.14.0
0 0.000
1 0.000
...
155 0.975
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.freq' )
>>> Frequency().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.freq' )
>>> Frequency().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@'):
if count == 0:
# first line should be #<version string>
if not line[0].startswith('#') and len(line) == 1:
return False
else:
# all other lines should be <int> <float>
if len(line) != 2:
return False
try:
int(line[0])
float(line[1])
except Exception:
return False
count += 1
if count > 1:
return True
return False
def sniff(self, filename):
"""
Determines whether a file is in gdm format
GDM files have at least 6 required fields.
(Actually in the format definition only the first 5 are mandatory, but the ones returned by the system have
always at least 6).
Required fields must be tab separated.
Columns 0, 3, 4 must be strings.
Columns 1, 2, 5 numbers.
Column 5 (Score) can be not provided.
"""
headers = get_headers(filename, '\t', count=10)
try:
for hdr in headers:
if hdr and hdr[0] and not hdr[0].startswith('#'):
if len(hdr) != 6:
return False
try:
int(hdr[1])
int(hdr[2])
except:
return False
if hdr[5] != '.':
try:
float(hdr[5])
except:
return False
return True
except:
return False
def sniff(self, filename, vals_are_int=False):
"""
Determines whether the file is a otu (operational taxonomic unit)
Shared format
label<TAB>group<TAB>count[<TAB>value(1..n)]
The first line is column headings as of Mothur v 1.2
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.shared' )
>>> GroupAbund().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.shared' )
>>> GroupAbund().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@'):
if len(line) < 3:
return False
if count > 0 or line[0] != 'label':
try:
check = int(line[2])
if check + 3 != len(line):
return False
for i in range(3, len(line)):
if vals_are_int:
int(line[i])
else:
float(line[i])
except ValueError:
return False
count += 1
if count > 1:
return True
return False
def sniff(self, filename):
"""
Determines whether the file is a quantiles tabular format for chimera analysis
1 0 0 0 0 0 0
2 0.309198 0.309198 0.37161 0.37161 0.37161 0.37161
3 0.510982 0.563213 0.693529 0.858939 1.07442 1.20608
...
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname( 'mothur_datatypetest_true.mothur.quan' )
>>> Quantile().sniff( fname )
True
>>> fname = get_test_fname( 'mothur_datatypetest_false.mothur.quan' )
>>> Quantile().sniff( fname )
False
"""
headers = get_headers(filename, sep='\t')
count = 0
for line in headers:
if not line[0].startswith('@') and not line[0].startswith('#'):
if len(line) != 7:
return False
try:
int(line[0])
float(line[1])
float(line[2])
float(line[3])
float(line[4])
float(line[5])
float(line[6])
except Exception:
return False
count += 1
if count > 0:
return True
return False
def sniff( self, filename ):
"""
Determines whether the file is in lav format
LAV is an alignment format developed by Webb Miller's group. It is the primary output format for BLASTZ.
The first line of a .lav file begins with #:lav.
For complete details see http://www.bioperl.org/wiki/LAV_alignment_format
>>> fname = get_test_fname( 'alignment.lav' )
>>> Lav().sniff( fname )
True
>>> fname = get_test_fname( 'alignment.axt' )
>>> Lav().sniff( fname )
False
"""
headers = get_headers( filename, None )
try:
if len(headers) > 1 and headers[0][0] and headers[0][0].startswith('#:lav'):
return True
else:
return False
except:
return False
def sniff(self, filename):
"""
Checks for 'pileup-ness'
There are two main types of pileup: 6-column and 10-column. For both,
the first three and last two columns are the same. We only check the
first three to allow for some personalization of the format.
>>> fname = get_test_fname( 'interval.interval' )
>>> Pileup().sniff( fname )
False
>>> fname = get_test_fname( '6col.pileup' )
>>> Pileup().sniff( fname )
True
>>> fname = get_test_fname( '10col.pileup' )
>>> Pileup().sniff( fname )
True
"""
headers = get_headers(filename, '\t')
try:
for hdr in headers:
if hdr and not hdr[0].startswith('#'):
if len(hdr) < 3:
return False
try:
# chrom start in column 1 (with 0-based columns)
# and reference base is in column 2
check = int(hdr[1])
assert hdr[2] in [
'A', 'C', 'G', 'T', 'N', 'a', 'c', 'g', 't', 'n'
]
except:
return False
return True
except:
return False
def sniff(self, filename):
header = get_headers(filename, sep='\t', count=1)
if header[0][0].strip() == '#FPS1':
return True
else:
return False
def sniff(self, filename):
headers = get_headers(filename, '\n', count=1)
return (len(headers) > 0 and len(headers[0]) >= 7
and headers[0][0] == "gene_id"
and headers[0][1].startswith("transcript_id")
and headers[0][6] == "FPKM")
def sniff( self, filename ):
headers = get_headers( filename, '\n', count=1 )
return headers[0][0].startswith("##fileformat=VCF")
