def parse_fams_r2r(fam_groups, fam, basefolder, cpus=1):
"""Aligns each family with cm of each group and creates r2r for alignment
Parameters
----------
fam_groups : list of str
groups in the family
fam : str
name of the family
basefolder : str
path to the base output directory
"""
# Load family stockholm file
sto = next(
StockholmAlignment.from_file(
join(basefolder, fam, "bayesfold-aln.sto"), RNASequence))
# grab r2r weights information
r2r_counts = sto.gf["USE_THIS_WEIGHT_MAP"]
# write out degapped sequences
degapped = join(basefolder, fam, "degapped.fna")
with open(degapped, 'w') as fout:
fout.write(sto.degapped().to_fasta())
# apply r2r weights to each family and re-create r2r drawing
for group in fam_groups:
# align family sequences to cm for group
group_sto = join(basefolder, fam, "%s.sto" % group)
cmalign(degapped, join(basefolder, group, "cmfile.cm"), group_sto,
cpus)
# add weight to stockholm file and write back out
sto = StockholmAlignment.from_file(group_sto, RNASequence)
sto.gf["USE_THIS_WEIGHT_MAP"] = r2r_counts
with open(group_sto, 'w') as fout:
fout.write(str(sto))
# rebuild r2r with new alignment
make_r2r(group_sto, join(basefolder, fam), "%s_%s" % (fam, group))
def test_to_file(self):
st = StockholmAlignment(self.seqs, gc=self.GC, gf=self.GF, gs=self.GS,
gr=self.GR)
with tempfile.NamedTemporaryFile('r+') as temp_file:
st.to_file(temp_file)
temp_file.flush()
temp_file.seek(0)
obs = temp_file.read()
exp = ('# STOCKHOLM 1.0\n'
'#=GF AC RF00360\n'
'#=GF BM cmbuild -F CM SEED\n'
'#=GF BM cmsearch -Z 274931 -E 1000000\n'
'#=GF SQ 9\n'
'#=GF RN [1]\n'
'#=GF RM 11469857\n'
'#=GF RT TITLE1\n'
'#=GF RA Auth1;\n'
'#=GF RL J Mol Biol\n'
'#=GF RN [2]\n'
'#=GF RM 12007400\n'
'#=GF RT TITLE2\n'
'#=GF RA Auth2;\n'
'#=GF RL Cell\n'
'#=GS seq1 AC 111\n'
'#=GS seq2 AC 222\n'
'seq1 ACC-G-GGTA\n'
'#=GR seq1 SS 1110101111\n'
'seq2 TCC-G-GGCA\n'
'#=GR seq2 SS 0110101110\n'
'#=GC SS_cons (((....)))\n//')
self.assertEqual(obs, exp)
def test_from_file_GS(self):
"""Make sure GS lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\n#=GS seq2 AC 222\n#=GS seq1 AC 111\n"
"seq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, self.GS, {}, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GC(self):
"""Make sure GC lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\n"
"seq1 ACC-G-GGTA\nseq2 TCC-G-GGCA\n"
"#=GC SS_cons (((....)))\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, {}, {}, self.GC)
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GR(self):
"""Make sure GR lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\nseq1 ACC-G\n"
"#=GR seq1 SS 11101\nseq2 TCC-G\n"
"#=GR seq2 SS 01101\n\nseq1 -GGTA\n"
"#=GR seq1 SS 01111\nseq2 -GGCA\n"
"#=GR seq2 SS 01110\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, {}, self.GR, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_alignment(self):
"""make sure can parse basic sto file with interleaved alignment"""
sto = StringIO("# STOCKHOLM 1.0\n"
"seq1 ACC-G\n"
"seq2 TCC-G\n\n"
"seq1 -GGTA\n"
"seq2 -GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs)
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GF(self):
"""Make sure GF lines are parsed correctly"""
# remove rn line to make sure auto-added
self.GF.pop("RN")
sto = StringIO("# STOCKHOLM 1.0\n#=GF RN [1]\n#=GF RM 11469857\n"
"#=GF RT TITLE1\n#=GF RA Auth1;\n#=GF RL J Mol Biol\n"
"#=GF RN [2]\n#=GF RM 12007400\n#=GF RT TITLE2\n"
"#=GF RA Auth2;\n#=GF RL Cell\n#=GF AC RF00360\n"
"#=GF BM cmbuild -F CM SEED\n"
"#=GF BM cmsearch -Z 274931 -E 1000000\n#=GF SQ 9\n"
"seq1 ACC-G-GGTA\nseq2 TCC-G-GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, self.GF, {}, {}, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_multi(self):
"""Make sure yield works correctly with multi-alignment sto files"""
sto = StringIO("# STOCKHOLM 1.0\n#=GS seq2 AC 222\n#=GS seq1 AC 111\n"
"seq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n//\n"
"# STOCKHOLM 1.0\nseq1 ACC-G-GGTA\n"
"#=GR seq1 SS 1110101111\nseq2 TCC-G-GGCA\n"
"#=GR seq2 SS 0110101110\n//")
obs_sto = StockholmAlignment.from_file(sto, DNA)
count = 0
for obs in obs_sto:
if count == 0:
exp_sto = StockholmAlignment(self.seqs, {}, self.GS, {}, {})
self.assertEqual(obs, exp_sto)
elif count == 1:
exp_sto = StockholmAlignment(self.seqs, {}, {}, self.GR, {})
self.assertEqual(obs, exp_sto)
else:
raise AssertionError("More than 2 sto alignments parsed!")
count += 1
def setUp(self):
"""Setup for stockholm tests."""
self.seqs = [DNASequence("ACC-G-GGTA", id="seq1"),
DNASequence("TCC-G-GGCA", id="seq2")]
self.GF = OrderedDict([
("AC", "RF00360"),
("BM", ["cmbuild -F CM SEED",
"cmsearch -Z 274931 -E 1000000"]),
("SQ", "9"),
("RT", ["TITLE1", "TITLE2"]),
("RN", ["[1]", "[2]"]),
("RA", ["Auth1;", "Auth2;"]),
("RL", ["J Mol Biol", "Cell"]),
("RM", ["11469857", "12007400"]),
('RN', ['[1]', '[2]'])
])
self.GS = {"AC": OrderedDict([("seq1", "111"), ("seq2", "222")])}
self.GR = {"SS": OrderedDict([("seq1", "1110101111"),
("seq2", "0110101110")])}
self.GC = {"SS_cons": "(((....)))"}
self.st = StockholmAlignment(self.seqs, gc=self.GC, gf=self.GF,
gs=self.GS, gr=self.GR)
class StockholmAlignmentTests(TestCase):
"""Tests for stockholmAlignment object"""
def setUp(self):
"""Setup for stockholm tests."""
self.seqs = [DNASequence("ACC-G-GGTA", id="seq1"),
DNASequence("TCC-G-GGCA", id="seq2")]
self.GF = OrderedDict([
("AC", "RF00360"),
("BM", ["cmbuild -F CM SEED",
"cmsearch -Z 274931 -E 1000000"]),
("SQ", "9"),
("RT", ["TITLE1", "TITLE2"]),
("RN", ["[1]", "[2]"]),
("RA", ["Auth1;", "Auth2;"]),
("RL", ["J Mol Biol", "Cell"]),
("RM", ["11469857", "12007400"]),
('RN', ['[1]', '[2]'])
])
self.GS = {"AC": OrderedDict([("seq1", "111"), ("seq2", "222")])}
self.GR = {"SS": OrderedDict([("seq1", "1110101111"),
("seq2", "0110101110")])}
self.GC = {"SS_cons": "(((....)))"}
self.st = StockholmAlignment(self.seqs, gc=self.GC, gf=self.GF,
gs=self.GS, gr=self.GR)
def test_retrieve_metadata(self):
self.assertEqual(self.st.gc, self.GC)
self.assertEqual(self.st.gf, self.GF)
self.assertEqual(self.st.gs, self.GS)
self.assertEqual(self.st.gr, self.GR)
def test_from_file_alignment(self):
"""make sure can parse basic sto file with interleaved alignment"""
sto = StringIO("# STOCKHOLM 1.0\n"
"seq1 ACC-G\n"
"seq2 TCC-G\n\n"
"seq1 -GGTA\n"
"seq2 -GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs)
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GF(self):
"""Make sure GF lines are parsed correctly"""
# remove rn line to make sure auto-added
self.GF.pop("RN")
sto = StringIO("# STOCKHOLM 1.0\n#=GF RN [1]\n#=GF RM 11469857\n"
"#=GF RT TITLE1\n#=GF RA Auth1;\n#=GF RL J Mol Biol\n"
"#=GF RN [2]\n#=GF RM 12007400\n#=GF RT TITLE2\n"
"#=GF RA Auth2;\n#=GF RL Cell\n#=GF AC RF00360\n"
"#=GF BM cmbuild -F CM SEED\n"
"#=GF BM cmsearch -Z 274931 -E 1000000\n#=GF SQ 9\n"
"seq1 ACC-G-GGTA\nseq2 TCC-G-GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, self.GF, {}, {}, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GC(self):
"""Make sure GC lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\n"
"seq1 ACC-G-GGTA\nseq2 TCC-G-GGCA\n"
"#=GC SS_cons (((....)))\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, {}, {}, self.GC)
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GS(self):
"""Make sure GS lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\n#=GS seq2 AC 222\n#=GS seq1 AC 111\n"
"seq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, self.GS, {}, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_GR(self):
"""Make sure GR lines are parsed correctly"""
sto = StringIO("# STOCKHOLM 1.0\nseq1 ACC-G\n"
"#=GR seq1 SS 11101\nseq2 TCC-G\n"
"#=GR seq2 SS 01101\n\nseq1 -GGTA\n"
"#=GR seq1 SS 01111\nseq2 -GGCA\n"
"#=GR seq2 SS 01110\n//")
obs_sto = next(StockholmAlignment.from_file(sto, DNA))
exp_sto = StockholmAlignment(self.seqs, {}, {}, self.GR, {})
self.assertEqual(obs_sto, exp_sto)
def test_from_file_multi(self):
"""Make sure yield works correctly with multi-alignment sto files"""
sto = StringIO("# STOCKHOLM 1.0\n#=GS seq2 AC 222\n#=GS seq1 AC 111\n"
"seq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n//\n"
"# STOCKHOLM 1.0\nseq1 ACC-G-GGTA\n"
"#=GR seq1 SS 1110101111\nseq2 TCC-G-GGCA\n"
"#=GR seq2 SS 0110101110\n//")
obs_sto = StockholmAlignment.from_file(sto, DNA)
count = 0
for obs in obs_sto:
if count == 0:
exp_sto = StockholmAlignment(self.seqs, {}, self.GS, {}, {})
self.assertEqual(obs, exp_sto)
elif count == 1:
exp_sto = StockholmAlignment(self.seqs, {}, {}, self.GR, {})
self.assertEqual(obs, exp_sto)
else:
raise AssertionError("More than 2 sto alignments parsed!")
count += 1
def test_parse_gf_multiline_nh(self):
"""Makes sure a multiline NH code is parsed correctly"""
sto = ["#=GF TN MULTILINE TREE",
"#=GF NH THIS IS FIRST", "#=GF NH THIS IS SECOND",
"#=GF AC 1283394"]
exp = {'TN': 'MULTILINE TREE',
'NH': 'THIS IS FIRST THIS IS SECOND',
'AC': '1283394'}
self.assertEqual(self.st._parse_gf_info(sto), exp)
def test_parse_gf_multiline_cc(self):
"""Makes sure a multiline CC code is parsed correctly"""
sto = ["#=GF CC THIS IS FIRST", "#=GF CC THIS IS SECOND"]
exp = {'CC': 'THIS IS FIRST THIS IS SECOND'}
self.assertEqual(self.st._parse_gf_info(sto), exp)
def test_parse_gf_info_nongf(self):
"""Makes sure error raised if non-GF line passed"""
sto = ["#=GF AC BLAAAAAAAHHH", "#=GC HUH THIS SHOULD NOT BE HERE"]
with self.assertRaises(StockholmParseError):
self.st._parse_gf_info(sto)
def test_parse_gf_info_malformed(self):
"""Makes sure error raised if too short a line passed"""
sto = ["#=GF AC", "#=GF"]
with self.assertRaises(StockholmParseError):
self.st._parse_gf_info(sto)
def test_parse_gc_info_nongf(self):
"""Makes sure error raised if non-GC line passed"""
sto = ["#=GC AC BLAAAAAAAHHH", "#=GF HUH THIS SHOULD NOT BE HERE"]
with self.assertRaises(StockholmParseError):
self.st._parse_gf_info(sto)
def test_parse_gc_info_strict_len(self):
"""Make sure error raised if GC lines bad length and strict parsing"""
sto = ["#=GC SS_cons (((..)))"]
with self.assertRaises(StockholmParseError):
self.st._parse_gc_info(sto, seqlen=20, strict=True)
def test_parse_gc_info_strict_duplicate(self):
"""Make sure error raised if GC lines repeated"""
sto = ["#=GC SS_cons (((..)))", "#=GC SS_cons (((..)))"]
with self.assertRaises(StockholmParseError):
self.st._parse_gc_info(sto, seqlen=8, strict=True)
def test_parse_gc_info_malformed(self):
"""Makes sure error raised if too short a line passed"""
sto = ["#=GC AC BLAAAAAAAHHH", "#=GC"]
with self.assertRaises(StockholmParseError):
self.st._parse_gc_info(sto)
def test_parse_gs_gr_info_mixed(self):
"""Makes sure error raised if mixed GS and GR lines passed"""
sto = ["#=GS seq1 AC BLAAA", "#=GR seq2 HUH THIS SHOULD NOT BE HERE"]
with self.assertRaises(StockholmParseError):
self.st._parse_gs_gr_info(sto)
def test_parse_gs_gr_info_malformed(self):
"""Makes sure error raised if too short a line passed"""
sto = ["#=GS AC BLAAAAAAAHHH", "#=GS"]
with self.assertRaises(StockholmParseError):
self.st._parse_gs_gr_info(sto)
def test_parse_gs_gr_info_strict(self):
"""Make sure error raised if GR lines bad length and strict parsing"""
sto = ["#=GR seq1 SS 10101111", "#=GR seq2 SS 01101"]
with self.assertRaises(StockholmParseError):
self.st._parse_gs_gr_info(sto, seqlen=20, strict=True)
def test_str(self):
""" Make sure stockholm with all information contained is formatted
correctly """
st = StockholmAlignment(self.seqs, gc=self.GC, gf=self.GF, gs=self.GS,
gr=self.GR)
obs = str(st)
exp = ('# STOCKHOLM 1.0\n'
'#=GF AC RF00360\n'
'#=GF BM cmbuild -F CM SEED\n'
'#=GF BM cmsearch -Z 274931 -E 1000000\n'
'#=GF SQ 9\n'
'#=GF RN [1]\n'
'#=GF RM 11469857\n'
'#=GF RT TITLE1\n'
'#=GF RA Auth1;\n'
'#=GF RL J Mol Biol\n'
'#=GF RN [2]\n'
'#=GF RM 12007400\n'
'#=GF RT TITLE2\n'
'#=GF RA Auth2;\n'
'#=GF RL Cell\n'
'#=GS seq1 AC 111\n'
'#=GS seq2 AC 222\n'
'seq1 ACC-G-GGTA\n'
'#=GR seq1 SS 1110101111\n'
'seq2 TCC-G-GGCA\n'
'#=GR seq2 SS 0110101110\n'
'#=GC SS_cons (((....)))\n//')
self.assertEqual(obs, exp)
def test_str_gc(self):
""" Make sure stockholm with only GC information contained is formatted
correctly """
st = StockholmAlignment(self.seqs, gc=self.GC, gf=None, gs=None,
gr=None)
obs = str(st)
exp = ("# STOCKHOLM 1.0\nseq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n"
"#=GC SS_cons (((....)))\n//")
self.assertEqual(obs, exp)
def test_str_gf(self):
""" Make sure stockholm with only GF information contained is formatted
correctly """
st = StockholmAlignment(self.seqs, gc=None, gf=self.GF, gs=None,
gr=None)
obs = str(st)
exp = ('# STOCKHOLM 1.0\n'
'#=GF AC RF00360\n'
'#=GF BM cmbuild -F CM SEED\n'
'#=GF BM cmsearch -Z 274931 -E 1000000\n'
'#=GF SQ 9\n'
'#=GF RN [1]\n'
'#=GF RM 11469857\n'
'#=GF RT TITLE1\n'
'#=GF RA Auth1;\n'
'#=GF RL J Mol Biol\n'
'#=GF RN [2]\n'
'#=GF RM 12007400\n'
'#=GF RT TITLE2\n'
'#=GF RA Auth2;\n'
'#=GF RL Cell\n'
'seq1 ACC-G-GGTA\n'
'seq2 TCC-G-GGCA\n//')
self.assertEqual(obs, exp)
def test_str_gs(self):
""" Make sure stockholm with only GS information contained is formatted
correctly """
st = StockholmAlignment(self.seqs, gc=None, gf=None, gs=self.GS,
gr=None)
obs = str(st)
exp = ('# STOCKHOLM 1.0\n'
'#=GS seq1 AC 111\n'
'#=GS seq2 AC 222\n'
'seq1 ACC-G-GGTA\n'
'seq2 TCC-G-GGCA\n//')
self.assertEqual(obs, exp)
def test_str_gr(self):
""" Make sure stockholm with only GR information contained is formatted
correctly """
st = StockholmAlignment(self.seqs, gc=None, gf=None, gs=None,
gr=self.GR)
obs = str(st)
exp = ("# STOCKHOLM 1.0\nseq1 ACC-G-GGTA\n"
"#=GR seq1 SS 1110101111\nseq2 TCC-G-GGCA\n"
"#=GR seq2 SS 0110101110\n//")
self.assertEqual(obs, exp)
def test_str_trees(self):
""" Make sure stockholm with trees printed correctly"""
GF = OrderedDict({"NH": ["IMATREE", "IMATREETOO"],
"TN": ["Tree2", "Tree1"]})
st = StockholmAlignment(self.seqs, gc=None, gf=GF, gs=None,
gr=None)
obs = str(st)
exp = ("# STOCKHOLM 1.0\n#=GF TN Tree2\n#=GF NH IMATREE\n#=GF TN Tree1"
"\n#=GF NH IMATREETOO\nseq1 ACC-G-GGTA\n"
"seq2 TCC-G-GGCA\n//")
self.assertEqual(obs, exp)
