def setUp(self):
ref_seq = Seq.Seq('GA' * 9 + 'GC' * 6 + 'GT' * 15)
query_seq = 'AA' * 4 + 'GA' * 5 + 'AC' + 'GC' * 5 + 'GT' * 15
aln_string = '>seq1\n{0}'.format(query_seq)
self.aln = Alignment(helpers.parse_fasta(aln_string).values(),
reference_sequence=ref_seq)
self.mutation_patterns = [mut_pattern.GA, mut_pattern.GM]
def setUp(self):
aln_string = """
>seq1
GTCAGTCAGTCAGTCACCCC
>seq2
GTCAGTCAGTCAGTCACCCC
>seq3
ATCAATCAGTCAATCACCCC
"""
self.seqs = helpers.parse_fasta(aln_string)
self.aln = Alignment(self.seqs.values())
def setUp(self):
aln_string = """
>seq1
GGTGACGCT
>seq2
AGTAACGCT
>seq3
GGTAACACT
"""
ref_seq = Seq.Seq('GGTGACGCT')
self.aln = Alignment(helpers.parse_fasta(aln_string).values(),
reference_sequence=ref_seq)
def setUp(self):
ref_seq = helpers.parse_fasta("""
>all
GGGGGGGGGTGTGTGTGT""")
self.aln = Alignment(helpers.parse_fasta("""
>seq1
GGGGGGGGGTGTGTGTGT
>seq2
AGAGAGAGGTGTGTGTGT
>seq3
GGGGGGGGGTATATATAT
""").values(),
reference_sequence=ref_seq['all'])
def setUp(self):
aln_string = """
>seq1
GTCAGTCAGTCAGTCA
GTCAGTCAGTCAGTCA
>seq2
GTCAGTCAGTCAGTCA
GTCAGTCAGTCAGTCA
>seq3
ATCAATCAGTCAATCG
ATCAATCAGTCAATCG"""
self.seqs = helpers.parse_fasta_list(aln_string)
self.aln = Alignment(self.seqs)
def split(args):
hm_col_reader = csv.DictReader(args.columns)
hm_columns = map(lambda x: int(x['column']), hm_col_reader)
hm_columns = list(set(hm_columns))
seq_records = SeqIO.parse(args.alignment, 'fasta')
aln = Alignment(seq_records)
aln.split_hypermuts(hm_columns=hm_columns)
fn_base = path.join(args.out_dir, args.prefix)
hm_pos_handle = open(fn_base + '.pos.fasta', 'w')
hm_neg_handle = open(fn_base + '.neg.fasta', 'w')
AlignIO.write(aln.hm_pos_aln, hm_pos_handle, 'fasta')
AlignIO.write(aln.hm_neg_aln, hm_neg_handle, 'fasta')
for handle in [args.alignment, args.columns, hm_pos_handle, hm_neg_handle]:
handle.close()
def analyze(args):
import logging
logging.captureWarnings(True)
# Fetch sequence records and analysis patterns
seq_records = SeqIO.to_dict(SeqIO.parse(args.alignment, 'fasta'))
patterns = [mut_pattern.patterns[p] for p in args.patterns]
pattern_names = [p.name for p in patterns]
prefix = path.join(args.out_dir, args.prefix)
analysis_settings = dict(rpr_cutoff=args.rpr_cutoff,
significance_level=args.significance_level,
quants=args.quants,
pos_quants_only=args.pos_quants_only,
caller=args.caller,
prior=args.prior,
cdfs=args.cdfs,
quadr_maxiter=args.quadr_maxiter,
optim_maxiter=args.optim_maxiter)
# Need to think about how best to fork things here; for instance, might make sense to let the user specify
# the initial clusters for whatever reason... However, specifying the reference sequences shouldn't make
# any sense there
if args.reference_sequences:
reference_sequences = SeqIO.to_dict(
SeqIO.parse(args.reference_sequences, 'fasta'))
else:
reference_sequences = None
# This lets the cluster map be optional, so that this script can be used
# for naive hm filtering/analysis
cluster_map = load_cluster_map(
args.cluster_map,
cluster_col=args.cluster_col) if args.cluster_map else None
alignments = AlignmentSet(seq_records,
cluster_map,
consensus_threshold=args.consensus_threshold,
reference_sequences=reference_sequences)
# Create the analysis generator
analysis = alignments.multiple_context_analysis(patterns,
**analysis_settings)
if args.cluster_threshold:
for hm_it in range(args.cluster_iterations - 1):
print " ..On hm/cluster iteration", hm_it
# Grab the HM columns from the most recent analysis and split out the pos sites
hm_columns = []
for result in analysis:
hm_columns += result['call']['mut_columns']
hm_neg_aln = Alignment(
seq_records.values()).split_hypermuts(hm_columns).hm_neg_aln
# Cluster with the specified settings
clustering = alnclst.Clustering(hm_neg_aln, args.cluster_threshold,
args.consensus_threshold)
clustering = clustering.recenter(args.recentering_iterations)
clustering.merge_small_clusters(args.min_per_cluster)
cluster_map = parse_clusters(clustering.mapping_iterator(),
cluster_key=0,
sequence_key=1)
# Create the Alignment set
clustered_alignment = AlignmentSet(
seq_records,
cluster_map,
consensus_threshold=args.consensus_threshold)
analysis = clustered_alignment.multiple_context_analysis(
patterns, **analysis_settings)
# write out the final clusters
clusterout_handle = file(prefix + '.clst.csv', 'w')
clustering.write(clusterout_handle)
if args.interactive:
local = copy.copy(locals())
import hyperfreq
local.update(
dict(hyperfreq=hyperfreq,
Alignment=Alignment,
AlignmentSet=AlignmentSet,
mut_pattern=mut_pattern,
write_analysis=write_analysis))
code.interact(local=local)
# Write the final analysis to file
write_analysis(analysis,
prefix,
pattern_names,
args.quants,
args.cdfs,
call_only=args.call_only)
if args.write_references:
write_reference_seqs(alignments, prefix)
# Closing files
args.alignment.close()
if args.cluster_map:
args.cluster_map.close()
