def parse(handle, format):
"""Parses an output file of motif finding programs.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- MEME: MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> for m in motifs.parse(open("Motif/alignace.out"), "AlignAce"):
... print(m.consensus)
TCTACGATTGAG
CTGCAGCTAGCTACGAGTGAG
GTGCTCTAAGCATAGTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAGGTGCCGGAG
GCGCGTCGCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GGGATCAGAGGGCCG
TGGAGGCGGGG
GACCAGAGCTTCGCATGGGGG
GGCGTGCGTG
GCTGGTTGCTGTTCATTAGG
GCCGGCGGCAGCTAAAAGGG
GAGGCCGGGGAT
CGACTCGTGCTTAGAAGG
"""
format = format.lower()
if format=="alignace":
from Bio.motifs import alignace
record = alignace.read(handle)
return record
elif format=="meme":
from Bio.motifs import meme
record = meme.read(handle)
return record
elif format=="mast":
from Bio.motifs import mast
record = mast.read(handle)
return record
elif format=="transfac":
from Bio.motifs import transfac
record = transfac.read(handle)
return record
elif format in ('pfm', 'sites', 'jaspar'):
from Bio.motifs import jaspar
record = jaspar.read(handle, format)
return record
else:
raise ValueError("Unknown format %s" % format)
def parse(handle, format):
"""Parses an output file of motif finding programs.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- MEME: MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> for m in motifs.parse(open("Motif/alignace.out"),"AlignAce"):
... print m.consensus
TCTACGATTGAG
CTGCAGCTAGCTACGAGTGAG
GTGCTCTAAGCATAGTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAGGTGCCGGAG
GCGCGTCGCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GGGATCAGAGGGCCG
TGGAGGCGGGG
GACCAGAGCTTCGCATGGGGG
GGCGTGCGTG
GCTGGTTGCTGTTCATTAGG
GCCGGCGGCAGCTAAAAGGG
GAGGCCGGGGAT
CGACTCGTGCTTAGAAGG
"""
format = format.lower()
if format == "alignace":
from Bio.motifs import alignace
record = alignace.read(handle)
return record
elif format == "meme":
from Bio.motifs import meme
record = meme.read(handle)
return record
elif format == "mast":
from Bio.motifs import mast
record = mast.read(handle)
return record
elif format == "transfac":
from Bio.motifs import transfac
record = transfac.read(handle)
return record
elif format in ('pfm', 'sites', 'jaspar'):
from Bio.motifs import jaspar
record = jaspar.read(handle, format)
return record
else:
raise ValueError("Unknown format %s" % format)
def get_motifs(meme_data_dir, e_val_threshold):
'''
Parses the MEME output for the motifs.
Parameters
----------
meme_data_dir: str
The path to the directory where the MEME results are stored (namely, the meme.xml file)
e_val_threshold: float
The maximum e-value for any motif that is returned.
Returns
-------
motifs: [Motifs]
An array of Motif objects corresponding the motifs that were parsed from the MEME analysis.
'''
#List of Motif objects that met the threshold
motifs_in_record = []
records = []
#Pull all of the records from the MEME output file
with open(meme_data_dir + 'meme.xml') as f:
try:
records = meme.read(f)
except:
print('Error with parsing MEME output.')
if len(records) == 0:
return motifs_in_record
#Pull out motifs that meet the e value threhold
for motif in records:
if motif.evalue <= e_val_threshold:
motifs_in_record.append(motif)
return motifs_in_record
def parse(handle, format, strict=True):
"""Parse an output file from a motif finding program.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- ClusterBuster: Cluster Buster position frequency matrix format
- XMS: XMS matrix format
- MEME: MEME output file motif
- MINIMAL: MINIMAL MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm-four-columns: Generic position-frequency matrix format with four columns. (cisbp, homer, hocomoco, neph, tiffin)
- pfm-four-rows: Generic position-frequency matrix format with four row. (scertf, yetfasco, hdpi, idmmpmm, flyfactor survey)
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> with open("motifs/alignace.out") as handle:
... for m in motifs.parse(handle, "AlignAce"):
... print(m.consensus)
...
TCTACGATTGAG
CTGCACCTAGCTACGAGTGAG
GTGCCCTAAGCATACTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAAGTGCCGGAG
GCACGTCCCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GAGATCAGAGGGCCG
TGGACGCGGGG
GACCAGAGCCTCGCATGGGGG
AGCGCGCGTG
GCCGGTTGCTGTTCATTAGG
ACCGACGGCAGCTAAAAGGG
GACGCCGGGGAT
CGACTCGCGCTTACAAGG
If strict is True (default), the parser will raise a ValueError if the
file contents does not strictly comply with the specified file format.
"""
format = format.lower()
if format == "alignace":
from Bio.motifs import alignace
return alignace.read(handle)
elif format == "meme":
from Bio.motifs import meme
return meme.read(handle)
elif format == "minimal":
from Bio.motifs import minimal
return minimal.read(handle)
elif format == "clusterbuster":
from Bio.motifs import clusterbuster
return clusterbuster.read(handle)
elif format in ("pfm-four-columns", "pfm-four-rows"):
from Bio.motifs import pfm
return pfm.read(handle, format)
elif format == "xms":
from Bio.motifs import xms
return xms.read(handle)
elif format == "mast":
from Bio.motifs import mast
return mast.read(handle)
elif format == "transfac":
from Bio.motifs import transfac
return transfac.read(handle, strict)
elif format in ("pfm", "sites", "jaspar"):
from Bio.motifs import jaspar
return jaspar.read(handle, format)
else:
raise ValueError("Unknown format %s" % format)
def parse(handle, format, strict=True):
"""Parse an output file from a motif finding program.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- MEME: MEME output file motif
- MINIMAL: MINIMAL MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> with open("Motif/alignace.out") as handle:
... for m in motifs.parse(handle, "AlignAce"):
... print(m.consensus)
...
TCTACGATTGAG
CTGCAGCTAGCTACGAGTGAG
GTGCTCTAAGCATAGTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAGGTGCCGGAG
GCGCGTCGCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GGGATCAGAGGGCCG
TGGAGGCGGGG
GACCAGAGCTTCGCATGGGGG
GGCGTGCGTG
GCTGGTTGCTGTTCATTAGG
GCCGGCGGCAGCTAAAAGGG
GAGGCCGGGGAT
CGACTCGTGCTTAGAAGG
If strict is True (default), the parser will raise a ValueError if the
file contents does not strictly comply with the specified file format.
"""
format = format.lower()
if format == "alignace":
from Bio.motifs import alignace
record = alignace.read(handle)
return record
elif format == "meme":
from Bio.motifs import meme
record = meme.read(handle)
return record
elif format == "minimal":
from Bio.motifs import minimal
record = minimal.read(handle)
return record
elif format == "mast":
from Bio.motifs import mast
record = mast.read(handle)
return record
elif format == "transfac":
from Bio.motifs import transfac
record = transfac.read(handle, strict)
return record
elif format in ('pfm', 'sites', 'jaspar'):
from Bio.motifs import jaspar
record = jaspar.read(handle, format)
return record
else:
raise ValueError("Unknown format %s" % format)
def test_meme_parser_5_0_4(self):
"""Parse motifs/meme_v_5_0_4.txt file."""
handle = open("motifs/meme_v_5_0_4.txt")
record = meme.read(handle)
self.assertEqual(record.version, '5.0.4')
self.assertEqual(record.datafile, 'example.fasta')
self.assertEqual(record.alphabet, IUPAC.unambiguous_dna)
self.assertEqual(len(record.sequences), 10)
self.assertEqual(record.sequences[0], 'SEQ1;')
self.assertEqual(record.sequences[1], 'SEQ2;')
self.assertEqual(record.sequences[2], 'SEQ3;')
self.assertEqual(record.sequences[3], 'SEQ4;')
self.assertEqual(record.sequences[4], 'SEQ5;')
self.assertEqual(record.sequences[5], 'SEQ6;')
self.assertEqual(record.sequences[6], 'SEQ7;')
self.assertEqual(record.sequences[7], 'SEQ8;')
self.assertEqual(record.sequences[8], 'SEQ9;')
self.assertEqual(record.sequences[9], 'SEQ10;')
self.assertEqual(record.command, 'meme -dna example.fasta')
self.assertEqual(len(record), 1)
motif = record[0]
self.assertEqual(motif.name, "Motif CTCAATCGTA")
self.assertEqual(record["Motif CTCAATCGTA"], motif)
self.assertEqual(motif.num_occurrences, 10)
self.assertAlmostEqual(motif.evalue, 1.1e-22)
self.assertEqual(motif.alphabet, IUPAC.unambiguous_dna)
self.assertEqual(len(motif.instances), 10)
self.assertAlmostEqual(motif.instances[0].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[1].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[2].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[3].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[4].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[5].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[6].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[7].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[8].pvalue, 1.96e-06)
self.assertAlmostEqual(motif.instances[9].pvalue, 1.96e-06)
self.assertEqual(motif.instances[0].sequence_name, 'SEQ10;')
self.assertEqual(motif.instances[1].sequence_name, 'SEQ9;')
self.assertEqual(motif.instances[2].sequence_name, 'SEQ8;')
self.assertEqual(motif.instances[3].sequence_name, 'SEQ7;')
self.assertEqual(motif.instances[4].sequence_name, 'SEQ6;')
self.assertEqual(motif.instances[5].sequence_name, 'SEQ5;')
self.assertEqual(motif.instances[6].sequence_name, 'SEQ4;')
self.assertEqual(motif.instances[7].sequence_name, 'SEQ3;')
self.assertEqual(motif.instances[8].sequence_name, 'SEQ2;')
self.assertEqual(motif.instances[9].sequence_name, 'SEQ1;')
self.assertEqual(motif.instances[0].start, 1)
self.assertEqual(motif.instances[1].start, 1)
self.assertEqual(motif.instances[2].start, 1)
self.assertEqual(motif.instances[3].start, 1)
self.assertEqual(motif.instances[4].start, 1)
self.assertEqual(motif.instances[5].start, 1)
self.assertEqual(motif.instances[6].start, 1)
self.assertEqual(motif.instances[7].start, 1)
self.assertEqual(motif.instances[8].start, 1)
self.assertEqual(motif.instances[9].start, 1)
self.assertEqual(motif.instances[0].strand, '+')
self.assertEqual(motif.instances[1].strand, '+')
self.assertEqual(motif.instances[2].strand, '+')
self.assertEqual(motif.instances[3].strand, '+')
self.assertEqual(motif.instances[4].strand, '+')
self.assertEqual(motif.instances[5].strand, '+')
self.assertEqual(motif.instances[6].strand, '+')
self.assertEqual(motif.instances[7].strand, '+')
self.assertEqual(motif.instances[8].strand, '+')
self.assertEqual(motif.instances[9].strand, '+')
self.assertEqual(motif.instances[0].length, 10)
self.assertEqual(motif.instances[1].length, 10)
self.assertEqual(motif.instances[2].length, 10)
self.assertEqual(motif.instances[3].length, 10)
self.assertEqual(motif.instances[4].length, 10)
self.assertEqual(motif.instances[5].length, 10)
self.assertEqual(motif.instances[6].length, 10)
self.assertEqual(motif.instances[7].length, 10)
self.assertEqual(motif.instances[8].length, 10)
self.assertEqual(motif.instances[9].length, 10)
self.assertEqual(motif.instances[0].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[1].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[2].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[3].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[4].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[5].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[6].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[7].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[8].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[9].motif_name, 'Motif CTCAATCGTA')
self.assertEqual(motif.instances[0].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[1].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[2].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[3].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[4].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[5].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[6].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[7].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[8].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(motif.instances[9].alphabet, IUPAC.unambiguous_dna)
self.assertEqual(str(motif.instances[0]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[1]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[2]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[3]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[4]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[5]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[6]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[7]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[8]), "CTCAATCGTA")
self.assertEqual(str(motif.instances[9]), "CTCAATCGTA")
handle.close()
#Data Formats
#Josh Rudolph
#9/27/17
from Bio.motifs import meme
with open("test5.txt", 'r' ) as f:
record = meme.read(f)
print record
def parse(handle, format, strict=True):
"""Parse an output file from a motif finding program.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- MEME: MEME output file motif
- MINIMAL: MINIMAL MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> with open("Motif/alignace.out") as handle:
... for m in motifs.parse(handle, "AlignAce"):
... print(m.consensus)
...
TCTACGATTGAG
CTGCAGCTAGCTACGAGTGAG
GTGCTCTAAGCATAGTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAGGTGCCGGAG
GCGCGTCGCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GGGATCAGAGGGCCG
TGGAGGCGGGG
GACCAGAGCTTCGCATGGGGG
GGCGTGCGTG
GCTGGTTGCTGTTCATTAGG
GCCGGCGGCAGCTAAAAGGG
GAGGCCGGGGAT
CGACTCGTGCTTAGAAGG
If strict is True (default), the parser will raise a ValueError if the
file contents does not strictly comply with the specified file format.
"""
format = format.lower()
if format == "alignace":
from Bio.motifs import alignace
record = alignace.read(handle)
return record
elif format == "meme":
from Bio.motifs import meme
record = meme.read(handle)
return record
elif format == "minimal":
from Bio.motifs import minimal
record = minimal.read(handle)
return record
elif format == "mast":
from Bio.motifs import mast
record = mast.read(handle)
return record
elif format == "transfac":
from Bio.motifs import transfac
record = transfac.read(handle, strict)
return record
elif format in ('pfm', 'sites', 'jaspar'):
from Bio.motifs import jaspar
record = jaspar.read(handle, format)
return record
else:
raise ValueError("Unknown format %s" % format)
records = meme.read(f)
File "/home/issac/Desktop/soa/soa-venv/lib/python3.6/site-packages/Bio/motifs/meme.py", line 53, in read
__read_motifs(record, xml_tree, sequence_id_name_map)
File "/home/issac/Desktop/soa/soa-venv/lib/python3.6/site-packages/Bio/motifs/meme.py", line 176, in __read_motifs
motif = Motif(record.alphabet, instances)
File "/home/issac/Desktop/soa/soa-venv/lib/python3.6/site-packages/Bio/motifs/meme.py", line 67, in __init__
motifs.Motif.__init__(self, alphabet, instances)
File "/home/issac/Desktop/soa/soa-venv/lib/python3.6/site-packages/Bio/motifs/__init__.py", line 263, in __init__
counts = self.instances.count()
File "/home/issac/Desktop/soa/soa-venv/lib/python3.6/site-packages/Bio/motifs/__init__.py", line 219, in count
counts[letter][position] += 1
KeyError: 'K'
This error was thrown when attempting to parse the results for CLSTR4.
'''
from Bio.motifs import meme, Motif, Instances
from Bio import motifs
#Path to CLSTR4 meme output
meme_results = '/Users/ichaudr/Documents/UMBC/Lab-Erill/Isaac/issac-workspace-IE/soa/meme_bin/CLSTR4_meme_out/meme.xml'
with open(meme_results, 'r') as f:
try:
records = meme.read(f)
except:
print('error')
print('made it')
def parse(handle, format, strict=True):
"""Parse an output file from a motif finding program.
Currently supported formats (case is ignored):
- AlignAce: AlignAce output file format
- ClusterBuster: Cluster Buster position frequency matrix format
- XMS: XMS matrix format
- MEME: MEME output file motif
- MINIMAL: MINIMAL MEME output file motif
- MAST: MAST output file motif
- TRANSFAC: TRANSFAC database file format
- pfm-four-columns: Generic position-frequency matrix format with four columns. (cisbp, homer, hocomoco, neph, tiffin)
- pfm-four-rows: Generic position-frequency matrix format with four row. (scertf, yetfasco, hdpi, idmmpmm, flyfactor survey)
- pfm: JASPAR-style position-frequency matrix
- jaspar: JASPAR-style multiple PFM format
- sites: JASPAR-style sites file
As files in the pfm and sites formats contain only a single motif,
it is easier to use Bio.motifs.read() instead of Bio.motifs.parse()
for those.
For example:
>>> from Bio import motifs
>>> with open("motifs/alignace.out") as handle:
... for m in motifs.parse(handle, "AlignAce"):
... print(m.consensus)
...
TCTACGATTGAG
CTGCACCTAGCTACGAGTGAG
GTGCCCTAAGCATACTAGGCG
GCCACTAGCAGAGCAGGGGGC
CGACTCAGAGGTT
CCACGCTAAGAGAAGTGCCGGAG
GCACGTCCCTGAGCA
GTCCATCGCAAAGCGTGGGGC
GAGATCAGAGGGCCG
TGGACGCGGGG
GACCAGAGCCTCGCATGGGGG
AGCGCGCGTG
GCCGGTTGCTGTTCATTAGG
ACCGACGGCAGCTAAAAGGG
GACGCCGGGGAT
CGACTCGCGCTTACAAGG
If strict is True (default), the parser will raise a ValueError if the
file contents does not strictly comply with the specified file format.
"""
format = format.lower()
if format == "alignace":
from Bio.motifs import alignace
return alignace.read(handle)
elif format == "meme":
from Bio.motifs import meme
return meme.read(handle)
elif format == "minimal":
from Bio.motifs import minimal
return minimal.read(handle)
elif format == "clusterbuster":
from Bio.motifs import clusterbuster
return clusterbuster.read(handle)
elif format in ('pfm-four-columns', 'pfm-four-rows'):
from Bio.motifs import pfm
return pfm.read(handle, format)
elif format == "xms":
from Bio.motifs import xms
return xms.read(handle)
elif format == "mast":
from Bio.motifs import mast
return mast.read(handle)
elif format == "transfac":
from Bio.motifs import transfac
return transfac.read(handle, strict)
elif format in ('pfm', 'sites', 'jaspar'):
from Bio.motifs import jaspar
return jaspar.read(handle, format)
else:
raise ValueError("Unknown format %s" % format)
