def find_homologs(query_file,
subject_genome,
e_value,
max_hits,
working_dir,
blast_mat_root,
wordsize,
percent_aligned,
extra_params={},
require_hit=False,
DEBUG=True):
"""BLAST query_file against subject_genome
query_file -- .nuc file or other FASTA file to BLAST against all files in file_list
subject_genome -- path to a KEGG .nuc file or other FASTA formated file.
e-value -- e-value threshold for blasts
percent_aligned -- minumum percent alignment, between 0.0 and 1.0
max_hits,blast_mat_root,extra_params -- these are passed along to blastn
DEBUG -- if True, display debugging output
"""
start_time = time()
raw_blast_output = []
seqs = open(query_file, "U").readlines()
if DEBUG:
print "BLASTING %s vs. %s" % (query_file, subject_genome)
blast_db = subject_genome
raw_output_data = blast_genome(seqs,
blast_db,
e_value,
max_hits,
wordsize,
working_dir,
blast_mat_root,
extra_params,
DEBUG=DEBUG)
if DEBUG:
print "Length of raw BLAST results:", len(raw_output_data)
curr_blast_result = BlastResult(raw_output_data)
align_filter = make_percent_align_filter(percent_aligned)
# should a mismatch filter be added?
filtered_ids, removed_ids = query_ids_from_blast_result(curr_blast_result,
align_filter,
DEBUG=DEBUG)
return raw_output_data, filtered_ids, removed_ids
def setUp(self):
self.blast_lines = BLAST_LINES
self.blast_result = BlastResult(self.blast_lines)
fd, self.subjectdb_fp = mkstemp(prefix='ExcludeByBlastTests_',
suffix='.fasta')
close(fd)
fd, self.query_fp = mkstemp(prefix='ExcludeByBlastTests_',
suffix='.fasta')
close(fd)
fd, self.query2_fp = mkstemp(prefix='ExcludeByBlastTests_',
suffix='.fasta')
close(fd)
open(self.subjectdb_fp, "w").writelines(TEST_BLAST_DB_LINES)
open(self.query_fp, "w").writelines(TEST_BLAST_DB_LINES)
open(self.query2_fp, "w").writelines(TEST_BLAST_DB2_LINES)
self._paths_to_clean_up = [
self.subjectdb_fp, self.query_fp, self.query2_fp
]