def test_load_unaligned_seqs_from_json(self):
"""test loading an unaligned object from json file"""
with TemporaryDirectory(dir=".") as dirname:
json_path = os.path.join(dirname, "unaligned.json")
path = os.path.join(data_path, "brca1_5.paml")
unaligned = load_unaligned_seqs(path)
unaligned.write(json_path)
got = load_unaligned_seqs(json_path)
self.assertIsInstance(got, SequenceCollection)
self.assertEqual(got.to_dict(), unaligned.to_dict())
self.assertEqual(got.info["source"], path)
# tests json generated by make_record_for_json
uncompleted_record = make_record_for_json("delme", got, False)
uncompleted_record_path = os.path.join(dirname,
"uncompleted_record.json")
completed_record = make_record_for_json("delme", got, True)
completed_record_path = os.path.join(dirname,
"completed_record.json")
with open(uncompleted_record_path, "w") as out:
out.write(json.dumps(uncompleted_record))
with open(completed_record_path, "w") as out:
out.write(json.dumps(completed_record))
# tests when provided record json file is uncompleted
with self.assertRaises(TypeError):
load_unaligned_seqs(uncompleted_record_path)
# tests when provided record json is completed
got = load_unaligned_seqs(completed_record_path)
self.assertIsInstance(got, SequenceCollection)
self.assertEqual(got.to_dict(), unaligned.to_dict())
self.assertEqual(got.info["source"], path)
def test_load_aligned_seqs_from_json(self):
"""tests loading an aligned object from json file"""
with TemporaryDirectory(dir=".") as dirname:
path = os.path.join(data_path, "brca1_5.paml")
alignment = load_aligned_seqs(path,
array_align=False,
moltype="dna")
alignment_json_path = os.path.join(dirname, "alignment.json")
alignment.write(alignment_json_path)
array_alignment = load_aligned_seqs(path, moltype="dna")
array_alignment_json_path = os.path.join(dirname,
"array_alignment.json")
array_alignment.write(array_alignment_json_path)
# tests case Alignment
got = load_aligned_seqs(alignment_json_path)
self.assertIsInstance(got, Alignment)
self.assertEqual(got.moltype.label, "dna")
self.assertEqual(got.to_dict(), alignment.to_dict())
self.assertEqual(got.info["source"], path)
# tests case ArrayAlignment
got = load_aligned_seqs(array_alignment_json_path)
self.assertIsInstance(got, ArrayAlignment)
self.assertEqual(got.moltype.label, "dna")
self.assertEqual(got.to_dict(), array_alignment.to_dict())
self.assertEqual(got.info["source"], path)
# tests json generated by make_record_for_json
uncompleted_record = make_record_for_json("delme", got, False)
completed_record = make_record_for_json("delme", got, True)
uncompleted_record_path = os.path.join(dirname,
"uncompleted_record.json")
completed_record_path = os.path.join(dirname,
"completed_record.json")
with open(uncompleted_record_path, "w") as out:
out.write(json.dumps(uncompleted_record))
with open(completed_record_path, "w") as out:
out.write(json.dumps(completed_record))
# tests when provided record json file is uncompleted
with self.assertRaises(TypeError):
load_unaligned_seqs(uncompleted_record_path)
# tests when provided record json is completed
got = load_aligned_seqs(completed_record_path)
self.assertIsInstance(got, ArrayAlignment)
self.assertEqual(got.to_dict(), array_alignment.to_dict())
self.assertEqual(got.info["source"], path)
# tests wrong input json file
json_path = os.path.join(dirname, "unaligned.json")
path = os.path.join(data_path, "brca1_5.paml")
unaligned = load_unaligned_seqs(path)
unaligned.write(json_path)
with self.assertRaises(TypeError):
load_aligned_seqs(json_path)
def test_load_unaligned_seqs(self):
"""test loading unaligned from file"""
path = os.path.join(data_path, "brca1_5.paml")
got = load_unaligned_seqs(path)
self.assertIsInstance(got, SequenceCollection)
self.assertTrue("Human" in got.to_dict())
self.assertEqual(got.info["source"], path)
def pep2nuc(id, pep, nuc):
pro = load_aligned_seqs(pep, format='fasta', moltype='protein')
dna = load_unaligned_seqs(nuc, format='fasta', moltype='dna')
try:
dna_noStop = dna.trim_stop_codons()
print('Trim stop complete: ' + pep)
except ValueError as er:
print("\nERROR: Couldn't trim stop codons for sample " + id)
print("Protein file: " + pep + "\nNucleotide file: " + nuc)
print(er)
exit()
# pass
# Replace sequences
aln_dna = pro.replace_seqs(dna_noStop, aa_to_codon=True)
# Write to file
aln_dna.write(id + '_translated.fasta', format='fasta')
"""
Dotplot
=======
A technique (`Gibbs and McIntyre <https://www.ncbi.nlm.nih.gov/pubmed/5456129>`_) for comparing sequences. All ``cogent3`` sequence collections classes (``SequenceCollection``, ``Alignment`` and ``ArrayAlignment``) have a dotplot method.
The method returns a drawable, as demonstrated below between unaligned sequences.
"""
# %%
import os
from cogent3 import load_unaligned_seqs
seqs = load_unaligned_seqs("../../data/SCA1-cds.fasta", moltype="dna")
draw = seqs.dotplot()
draw.show()
#%%
# If sequence names are not provided, two randomly chosen sequences are selected (see below). The plot title reflects the parameter values for defining a match. ``window`` is the size of the sequence segments being compared. ``threshold`` is the number of exact matches within ``window`` required for the two sequence segments to be considered a match. ``gap`` is the size of a gap between adjacent matches before merging.
#
# Modifying the matching parameters
# #################################
#
# If we set window and threshold to be equal, this is equivalent to an exact match approach.
draw = seqs.dotplot(name1="Human", name2="Mouse", window=8, threshold=8)
draw.show()
#%%
# Displaying dotplot for the reverse complement
def test_load_unaligned_seqs_no_format(self):
"""test loading unaligned from file"""
with self.assertRaises(ValueError):
got = load_unaligned_seqs("somepath")
