def test_run_local_alignment():
seq_list = get_seq_list("./NC_000913.fna.gz", "./candidate_list.table")
# seq_list holds tuples of (name, seq_obj)
seq_file_name = "./tmp/%s.fasta" % seq_list[0][0]
base_record = SeqRecord(seq_list[0][1],
id=seq_file_name,
name=seq_file_name)
SeqIO.write(base_record, seq_file_name, "fasta")
local_alignment_list = \
run_local_alignment(seq_file_name, "./genome_list.table")
print "*" * 100
print "local alignments results"
print "*" * 100
for row in local_alignment_list:
print row
records_for_emma = \
prepare_for_multiple_aignment(base_record, local_alignment_list)
print "*" * 100
print "records for emma"
print "*" * 100
for record in records_for_emma:
print record
print "*" * 100
print "Running Emma"
print "*" * 100
run_multiple_sequence_alignment(records_for_emma)
def test_run_local_alignment():
seq_list = get_seq_list("./NC_000913.fna.gz", "./candidate_list.table")
# seq_list holds tuples of (name, seq_obj)
seq_file_name = "./tmp/%s.fasta" % seq_list[0][0]
base_record = SeqRecord(seq_list[0][1], id=seq_file_name, name=seq_file_name)
SeqIO.write(base_record, seq_file_name, "fasta")
local_alignment_list = \
run_local_alignment(seq_file_name, "./genome_list.table")
print "*" * 100
print "local alignments results"
print "*" * 100
for row in local_alignment_list:
print row
records_for_emma = \
prepare_for_multiple_aignment(base_record, local_alignment_list)
print "*" * 100
print "records for emma"
print "*" * 100
for record in records_for_emma:
print record
print "*" * 100
print "Running Emma"
print "*" * 100
run_multiple_sequence_alignment(records_for_emma)
def run(base_genome_file,
candidate_list_file,
workdir,
genome_list_file,
project_to_taxamonies_file,
tree_file):
os.system("mkdir -p %s" % workdir)
os.system("mkdir -p %s" % os.path.join(workdir, "logs"))
os.system("mkdir -p %s" % os.path.join(workdir, "aln"))
os.system("mkdir -p %s" % os.path.join(workdir, "stats"))
os.system("mkdir -p %s" % os.path.join(workdir, "results"))
candidates_path = os.path.join(workdir, "candiates")
os.system("mkdir -p %s" % candidates_path)
seq_list = get_seq_list(base_genome_file, candidate_list_file)
conv_table = build_project_id_to_tax_id_dictionary(project_to_taxamonies_file)
secondary_conv_table = \
build_secondary_project_id_to_tax_id_dictionary(project_to_taxamonies_file)
# seq_list holds tuples of (name, seq_obj)
for seq in seq_list:
candid_workdir = os.path.join(candidates_path, seq[0])
os.system("mkdir -p %s" % candid_workdir)
print seq
# Generate sequence file
seq_file_name = "%s/%s.fasta" % (candid_workdir, seq[0])
base_record = SeqRecord(seq[1], id=seq[0], name=seq[0])
SeqIO.write(base_record, seq_file_name, "fasta")
# Create local alignments for the sequence
local_alignment_list = \
run_local_alignment(seq_file_name, genome_list_file, WORK_DIR)
print "*" * 100
print "local alignments results"
print "*" * 100
for row in local_alignment_list:
print row
# Generate histogram
generate_score_histogram("%s/stats/%s.png" % (workdir, seq[0]), local_alignment_list)
# Exctract only the significant alignments
records_for_emma = \
prepare_for_multiple_aignment(local_alignment_list,
conv_table,
secondary_conv_table)
print "*" * 100
print "records for emma"
print "*" * 100
for record in records_for_emma:
print record
print "*" * 100
print "Running Emma"
print "*" * 100
# Run emma
run_multiple_sequence_alignment(records_for_emma,
"%s/emma.aln" % candid_workdir,
"%s/emma.dnd" % candid_workdir,
candid_workdir)
# Run Rate4Site
rate_runner = Rate4Site("%s/emma.aln" % candid_workdir,
tree_file,
"./rate4site64")
rate_runner.runRate(outname="%s/results/%s.rate" % (workdir, seq[0]))
