def run_papara(tree: str, ref_msa: dict, study_fasta: str, out_dir: str,
threads=1, print_cmds=False):
'''Run PaPaRa to place study sequences into reference multiple-sequence
alignment (MSA). Will return dictionary of the the output MSA (sequence ids
as keys). Expects path to tree and study FASTA as strings. Expects
reference MSA as a dictionary output by read_fasta. This MSA will be
converted to phylip format before running PaPaRa.'''
# Get absolute paths to input files.
tree = path.abspath(tree)
study_fasta = path.abspath(study_fasta)
# Change working directory to out directory (but keep track of original).
# This is necessary because PaPaRa outputs into the current working
# directory.
orig_wd = getcwd()
chdir(out_dir)
# Convert ref sequences from MSA FASTA to phylip.
write_phylip(ref_msa, "ref_seqs.phylip")
# Make call to papara to place sequences (outputs phylip format).
system_call_check("papara -t " + tree + " -s ref_seqs.phylip " +
"-q " + study_fasta + " -j " + str(threads) +
" -n out", print_command=print_cmds,
print_stdout=print_cmds, print_stderr=print_cmds)
# Change back to original working directory.
chdir(orig_wd)
# Read in papara phylip output and return.
return(read_phylip(path.join(out_dir, "papara_alignment.out"),
check_input=True))
def test_read_write_phylip(self):
'''Basic test that Phylip files are read and written correctly.'''
test_seqs_dict = {
"seq1": "GNATNGAC",
"seq2": "GTCGTGGC",
"seq3": "GNCTGAGA"
}
# Write these sequences temp file and then read them back in again.
with TemporaryDirectory() as temp_dir:
outfile = path.join(temp_dir, "test.phylip")
write_phylip(test_seqs_dict, outfile)
test_seqs_dict_in = read_phylip(outfile)
self.assertEqual(test_seqs_dict, test_seqs_dict_in)