def main():
if len(sys.argv) != 4:
logging.error('Wrong count of arguments')
print(usage())
sys.exit()
_, fasta_filename, score_matrix_filename, method = sys.argv
method = method.lower()
if method not in METHODS:
logging.error('Wrong method for cluster')
print(usage())
sys.exit()
logging.info('Load fasta file')
sequences = read_fasta(fasta_filename)
logging.info('Finish load fasta file')
logging.info('Load score matrix')
score_matrix = read_score_matrix(score_matrix_filename)
logging.info('Finish load score matrix')
logging.info('Start progressive alignment with method ' + method)
result_sequences = METHODS[method](sequences, score_matrix)
logging.info('Finish progressive alignment')
for sequence in result_sequences:
print('>' + sequence.name)
print(sequence.seq)
logging.info('Done.')
def main():
if len(sys.argv) != 3:
print("Usage: bait_frequency.py file.fsl genes.fa")
sys.exit(-1)
fsl_file = sys.argv[1]
target_to_id = read_fsl(fsl_file)
fasta_file = sys.argv[2]
genes, name_map = readers.read_fasta(fasta_file, shorten=True, max_length_shorten=False)
terms = ontology_common.parse_obo('new_combined.obo')
baits_for_class = collections.defaultdict(set)
for gene in genes.keys():
name = gene
found = name in target_to_id
if found:
results = target_to_id[name]
for result in results:
for cl in ontology_common.get_class(result[0], terms):
baits_for_class[cl].add(result[1])
#print(name, len(results))
else:
print(name, '0')
print()
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' in terms[k]['name'][0]:
print(terms[k]['name'][0], len(v))
total_baits += len(v)
print("Total counts for gene class ", total_baits)
print()
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' not in terms[k]['name'][0]:
print(terms[k]['name'][0], len(v))
total_baits += len(v)
print("Total counts for mechanism ", total_baits)
def main():
# for each sequence, see if there is a match with any consensus sequence
amr = readers.read_fasta(file='../combined.fasta')
#amr = readers.read_fasta(file='../test.combined.fasta')
consensus = readers.read_fasta(file='../bait.fasta')
#consensus = readers.read_fasta(file='../test.clstr.fasta')
not_found = 0
for name, gene in amr.items():
found = False
for cluster in consensus.values():
if match(gene, cluster):
found = True
break
if not found:
not_found += 1
print('Not found: %s' % name)
print(not_found)
def main():
# for each sequence, see if there is a match with any consensus sequence
amr = readers.read_fasta(file='../combined.fasta')
#amr = readers.read_fasta(file='../test.combined.fasta')
consensus = readers.read_fasta(file='../bait.fasta')
#consensus = readers.read_fasta(file='../test.clstr.fasta')
not_found = 0
for name, gene in amr.items():
found = False
for cluster in consensus.values():
if match(gene, cluster):
found = True
break
if not found:
not_found += 1
print('Not found: %s' % name)
print(not_found)
def main():
if len(sys.argv) != 3:
print("Usage: bait_topmatch.py file.fsl baits.fasta")
sys.exit(-1)
fsl_file = sys.argv[1]
matched_baits = read_fsl(fsl_file)
baits = readers.read_fasta(file=sys.argv[2])
for b in baits.keys():
if b not in matched_baits:
print(b)
def main():
if len(sys.argv) != 3:
print("Usage: bait_topmatch.py file.fsl baits.fasta")
sys.exit(-1)
fsl_file = sys.argv[1]
matched_baits = read_fsl(fsl_file)
baits = readers.read_fasta(file=sys.argv[2])
for b in baits.keys():
if b not in matched_baits:
print(b)
def main():
if len(sys.argv) < 3 or len(sys.argv) > 4:
print("Usage: functional_test.py [-protein] results.scan seq.fasta")
sys.exit(-1)
protein = True if sys.argv[1] == '-protein' else False
if protein:
scan_file = sys.argv[2]
fasta_file = sys.argv[3]
protein_map = {
} # place to store mapping of protein name to dna name for genes
else:
scan_file = sys.argv[1]
fasta_file = sys.argv[2]
genes = readers.read_fasta(fasta_file)
positive_count = 0
negative_count = 0
for gene in genes.keys():
if 'True' in gene:
positive_count += 1
elif 'False' in gene:
negative_count += 1
if protein:
names = gene.split('>')
protein_map[names[0].strip()] = names[1].strip()
id_to_target, target_to_id = readers.read_scan_results(0,
scan_file,
protein=protein)
false_positive = 0
true_positive = 0
already_seen_protein = set(
) # We don't want to double count if we have seen the same gene
for key in target_to_id.keys():
if protein:
key = protein_map[key]
if key in already_seen_protein:
continue
else:
already_seen_protein.add(key)
if key.startswith('False'):
false_positive += 1
elif key.startswith('True'):
true_positive += 1
print("True Positive: %d/%d(%f); False Positive: %d/%d(%f)" %
(true_positive, positive_count,
float(true_positive) / positive_count, false_positive,
negative_count, float(false_positive) / negative_count))
def main():
if len(sys.argv) != 3:
print("Usage: bait_frequency.py file.fsl genes.fa")
sys.exit(-1)
fsl_file = sys.argv[1]
target_to_id = read_fsl(fsl_file)
fasta_file = sys.argv[2]
genes, name_map = readers.read_fasta(fasta_file,
shorten=True,
max_length_shorten=False)
terms = ontology_common.parse_obo('new_combined.obo')
baits_for_class = collections.defaultdict(set)
for gene in genes.keys():
name = gene
found = name in target_to_id
if found:
results = target_to_id[name]
for result in results:
for cl in ontology_common.get_class(result[0], terms):
baits_for_class[cl].add(result[1])
#print(name, len(results))
else:
print(name, '0')
print()
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' in terms[k]['name'][0]:
print(terms[k]['name'][0], len(v))
total_baits += len(v)
print("Total counts for gene class ", total_baits)
print()
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' not in terms[k]['name'][0]:
print(terms[k]['name'][0], len(v))
total_baits += len(v)
print("Total counts for mechanism ", total_baits)
output = ''.join([gen_random_sequence(prefix_len),
seq,
gen_random_sequence(suffix_len)])
return "> %d:%d?%s?%s\n%s" %(prefix_len, len(seq) + prefix_len, target, name, output)
def unit_test():
pattern = 'AAAAAA'
value = gen_test(pattern, 'adr001', 'test')
lines = value.split('\n')
offset, target, name = lines[0][1:].split('?', 2)
start, end = offset.split(':')
start = int(start)
end = int(end)
if lines[1][start:end] == pattern:
print("Success")
else:
print(lines[1][start:end])
#unit_test()
id_to_name = readers.read_grouping()
name_to_seq = readers.read_fasta()
for id, names in id_to_name.items():
with open('../test/%s.fa' % id, 'w+') as fasta:
for name in names:
seq = name_to_seq[name]
value = gen_test(seq, id, name)
fasta.write(value + '\n')
def main():
if len(sys.argv) < 3 or len(sys.argv) > 4:
print(
"Usage: functional_compare.py [-fsl] [-protein] results.scan seq.fasta"
)
sys.exit(-1)
fsl = True if sys.argv[1] == '-fsl' else False
protein = True if sys.argv[1] == '-protein' else False
if fsl:
fsl_file = sys.argv[2]
fasta_file = sys.argv[3]
elif protein:
scan_file = sys.argv[2]
fasta_file = sys.argv[3]
else:
scan_file = sys.argv[1]
fasta_file = sys.argv[2]
genes = readers.read_fasta(fasta_file)
if fsl:
target_to_id = read_fsl(fsl_file)
else:
id_to_target, target_to_id = readers.read_scan_results(0,
scan_file,
protein=protein)
if protein:
readers.change_RF_to_ARO(target_to_id)
already_seen_protein = set(
) # We don't want to double count if we have seen the same gene
terms = ontology_common.parse_obo('new_combined.obo')
false_positive = 0
true_positive = 0
false_negative = 0
for gene in genes.keys():
if protein:
names = gene.split('>')
gene = names[1].strip()
name = names[0].strip()
if gene in already_seen_protein:
continue
else:
already_seen_protein.add(gene)
else:
name = gene
found = name in target_to_id
if found:
antibiotic = gene.split('_')[1]
functional_antibiotic = antibiotic_code[antibiotic]
results = target_to_id[name]
results.sort(key=lambda l: l[1], reverse=True)
index = 0
while index < len(results):
result = results[index]
index += 1
id = result[0]
# remove formatting used by hmm
if 's' in id:
id = id.replace('ARO', 'ARO:')
id = id.split('s')[0]
if ';' in id:
# resfams can have a list of ids associated with a gene
classes = [
terms[p]['name'] for i in id.split(';')
for p in ontology_common.get_class(i, terms)
]
drugs = set()
for i in id.split(';'):
drugs |= ontology_common.get_resistance(
ontology_common.get_lineage(i, terms), terms)
else:
classes = [
terms[p]['name']
for p in ontology_common.get_class(id, terms)
]
drugs = ontology_common.get_resistance(
ontology_common.get_lineage(id, terms), terms)
identified = False
for drug in drugs:
for d in ontology_common.get_lineage(drug, terms):
for fd in ontology_common.get_lineage(
functional_antibiotic[1], terms):
if d == fd and d not in [
'ARO:1000001', 'ARO:1000003', 'Unknown'
]:
identified = True
if identified:
true_positive += 1
break
else:
false_negative += 1
if found and not identified:
print(gene, functional_antibiotic, id, classes, drugs)
false_positive += 1
print('False negative: %d; False Positive:%d; True Positive:%d' %
(false_negative, false_positive, true_positive))
import readers import sys # read input files name_to_sequence, name_map = readers.read_fasta(sys.argv[1], shorten=True) id_to_name = readers.read_cluster(sys.argv[2]) # create fasta files for each id readers.create_fasta_file_for_each_id(name_to_sequence, id_to_name, sys.argv[3], name_map)
def main():
if len(sys.argv) < 3 or len(sys.argv) > 4:
print("Usage: functional_compare.py [-fsl] [-protein] results.scan seq.fasta")
sys.exit(-1)
fsl = True if sys.argv[1] == '-fsl' else False
protein = True if sys.argv[1] == '-protein' else False
if fsl:
fsl_file = sys.argv[2]
fasta_file = sys.argv[3]
elif protein:
scan_file = sys.argv[2]
fasta_file = sys.argv[3]
else:
scan_file = sys.argv[1]
fasta_file = sys.argv[2]
genes = readers.read_fasta(fasta_file)
if fsl:
target_to_id = read_fsl(fsl_file)
else:
id_to_target, target_to_id = readers.read_scan_results(0, scan_file, protein=protein)
if protein:
readers.change_RF_to_ARO(target_to_id)
already_seen_protein = set() # We don't want to double count if we have seen the same gene
terms = ontology_common.parse_obo('new_combined.obo')
false_positive = 0
true_positive = 0
false_negative = 0
for gene in genes.keys():
if protein:
names = gene.split('>')
gene = names[1].strip()
name = names[0].strip()
if gene in already_seen_protein:
continue
else:
already_seen_protein.add(gene)
else:
name = gene
found = name in target_to_id
if found:
antibiotic = gene.split('_')[1]
functional_antibiotic = antibiotic_code[antibiotic]
results = target_to_id[name]
results.sort(key=lambda l: l[1], reverse=True)
index = 0
while index < len(results):
result = results[index]
index += 1
id = result[0]
# remove formatting used by hmm
if 's' in id:
id = id.replace('ARO', 'ARO:')
id = id.split('s')[0]
if ';' in id:
# resfams can have a list of ids associated with a gene
classes = [terms[p]['name'] for i in id.split(';') for p in ontology_common.get_class(i, terms)]
drugs = set()
for i in id.split(';'):
drugs |= ontology_common.get_resistance(ontology_common.get_lineage(i, terms), terms)
else:
classes = [terms[p]['name'] for p in ontology_common.get_class(id, terms)]
drugs = ontology_common.get_resistance(ontology_common.get_lineage(id, terms), terms)
identified = False
for drug in drugs:
for d in ontology_common.get_lineage(drug, terms):
for fd in ontology_common.get_lineage(functional_antibiotic[1], terms):
if d == fd and d not in ['ARO:1000001', 'ARO:1000003', 'Unknown']:
identified = True
if identified:
true_positive += 1
break
else:
false_negative += 1
if found and not identified:
print(gene, functional_antibiotic, id, classes, drugs)
false_positive += 1
print('False negative: %d; False Positive:%d; True Positive:%d' % (false_negative, false_positive, true_positive))
import sys
import readers
import pairwise_alignment
import pgma
import neighbor_joining
if len(sys.argv) < 4:
print("Usage: python progressive_alignment.py <seqs.fasta> <score_matrix> <upgma|wpgma|nj>")
exit()
else:
fasta_filename = sys.argv[1]
matrix_filename = sys.argv[2]
tree_type = sys.argv[3]
print("Read fasta...")
names, seqs = readers.read_fasta(fasta_filename)
print("Read score matrix...")
score_matrix = readers.read_matrix(matrix_filename)
print("Align sequences...")
if tree_type == "wpgma":
names, seqs = pgma.pgma(names, seqs, score_matrix, 'w')
elif tree_type == "upgma":
names, seqs = pgma.pgma(names, seqs, score_matrix, 'u')
elif tree_type == "nj":
names, seqs = neighbor_joining.neigbor_joining(names, seqs, score_matrix)
else:
print("Error: Unkonwn option. Choose upgma, wpgma or nj.")
exit()
out_filename = fasta_filename.split('.')[0] + "_aligned.fasta"
with open(out_filename, 'w') as out:
import readers
import sys
# read input files
name_to_sequence = readers.read_fasta(sys.argv[1])
id_to_name = readers.read_grouping(sys.argv[2])
# create fasta files for each id
readers.create_fasta_file_for_each_id(name_to_sequence, id_to_name,
sys.argv[3])