def main():
if len(sys.argv) != 2:
print("Usage: bait_topmatch.py file.fsl")
sys.exit(-1)
fsl_file = sys.argv[1]
total = read_fsl(fsl_file)
terms = ontology_common.parse_obo('new_combined.obo')
baits_for_class = collections.defaultdict(int)
for gene in total.keys():
for cl in ontology_common.get_class(gene, terms):
baits_for_class[cl] += total[gene]
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' in terms[k]['name'][0]:
print(terms[k]['name'][0], v)
total_baits += 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], v)
total_baits += v
print("Total counts for mechanism ", total_baits)
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():
if len(sys.argv) != 2:
print("Usage: bait_topmatch.py file.fsl")
sys.exit(-1)
fsl_file = sys.argv[1]
total = read_fsl(fsl_file)
terms = ontology_common.parse_obo('new_combined.obo')
baits_for_class = collections.defaultdict(int)
for gene in total.keys():
for cl in ontology_common.get_class(gene, terms):
baits_for_class[cl] += total[gene]
total_baits = 0
for k, v in baits_for_class.items():
if 'resistance gene' in terms[k]['name'][0]:
print(terms[k]['name'][0], v)
total_baits += 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], v)
total_baits += v
print("Total counts for mechanism ", total_baits)
def main():
terms = ontology_common.parse_obo('new_combined.obo')
with open('mismatch.csv') as f:
headers = f.readline()
more_general = 0
shared_ancestor = 0
print(
"Gene,Expected ID,Found ID,Common Class,Common Class Description")
while True:
line = f.readline()
if not line:
break
id, actual, name = line.strip().split(',', 2)
#id = id.replace('ARO', 'ARO:')
#id = id.split('s')[0]
#actual = actual.replace('ARO', 'ARO:')
#actual = actual.split('s')[0]
#id_parents = [p for p in get_lineage(id, terms)]
#print(id_parents, [l for l in get_lineage(actual, terms)])
ancestor = determine_ancestor(id, actual, terms)
if ancestor == actual:
more_general += 1
elif ancestor is None:
print('%s,%s,%s,%s,%s' % (name, id, actual, ancestor, "none"))
elif "ARO" in ancestor and ancestor != 'ARO:3000000':
shared_ancestor += 1
else:
#description = terms[actual]['def'][0] if terms.get(actual) else "No Description"
print('%s,%s,%s,%s' % (name, id, actual, ancestor))
print("More general:%d, Shared grouping:%d" %
(more_general, shared_ancestor))
def hyperbolic_tree():
# outputs json hierarchy used by hyperbolic tree
terms = ontology_common.parse_obo('../new_combined.obo')
ids = get_ids(sys.argv[1])
print("code_hierarchy_data = ")
print(json.dumps(root, indent=4, separators=(',', ': ')))
def main():
if len(sys.argv) != 2:
print("Usage: bait_count.py master_amr_parsed.tsv")
sys.exit(-1)
count_file = sys.argv[1]
name_to_count = read_count(count_file)
groups = readers.read_grouping('grouping.csv', short=True, map_name=True, strip_colon=False)
terms = ontology_common.parse_obo('new_combined.obo')
baits_for_class = collections.defaultdict(int)
for gene, count in name_to_count.items():
group = groups[gene]
for cl in ontology_common.get_class(group, terms):
baits_for_class[cl] += count
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], v)
total_baits += 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], v)
total_baits += v
print("Total counts for mechanism ", total_baits)
def main():
terms = ontology_common.parse_obo('new_combined.obo')
with open('mismatch.csv') as f:
headers = f.readline()
more_general = 0
shared_ancestor = 0
print("Gene,Expected ID,Found ID,Common Class,Common Class Description")
while True:
line = f.readline()
if not line:
break
id, actual, name = line.strip().split(',', 2)
#id = id.replace('ARO', 'ARO:')
#id = id.split('s')[0]
#actual = actual.replace('ARO', 'ARO:')
#actual = actual.split('s')[0]
#id_parents = [p for p in get_lineage(id, terms)]
#print(id_parents, [l for l in get_lineage(actual, terms)])
ancestor = determine_ancestor(id, actual, terms)
if ancestor == actual:
more_general += 1
elif ancestor is None:
print('%s,%s,%s,%s,%s' % (name, id, actual, ancestor, "none"))
elif "ARO" in ancestor and ancestor != 'ARO:3000000':
shared_ancestor += 1
else:
#description = terms[actual]['def'][0] if terms.get(actual) else "No Description"
print('%s,%s,%s,%s' % (name, id, actual, ancestor))
print("More general:%d, Shared grouping:%d" % (more_general, shared_ancestor))
def doughnut():
# outputs json hierarchy with count used by doughnut graph
terms = ontology_common.parse_obo('../new_combined.obo')
counts = get_counts(sys.argv[1])
root, nodes = build_tree(counts, terms)
fill_children(root, nodes, terms)
print("code_hierarchy_data = ")
print(json.dumps(root, indent=4, separators=(',', ': ')))
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():
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))
def main():
terms = ontology_common.parse_obo('new_combined.obo')
for l in ontology_common.get_lineage(sys.argv[1], terms):
print(l)
# This file prints out all of the CARD entries that are children of the root entry
import ontology_common
def find_children(parent):
for k, v in terms.items():
if 'is_a' in v:
for value in v['is_a']:
id = value.split()
if id[0] == parent:
print("'%s': %s," % (k, v['name']))
terms = ontology_common.parse_obo('../aro.obo')
find_children('ARO:3000000')
# This file prints out all of the CARD entries that are children of the root entry
import ontology_common
def find_children(parent):
for k, v in terms.items():
if 'is_a' in v:
for value in v['is_a']:
id = value.split()
if id[0] == parent:
print("'%s': %s," % (k, v['name']))
terms = ontology_common.parse_obo('../aro.obo')
find_children('ARO:3000000')
def main():
terms = ontology_common.parse_obo('new_combined.obo')
for l in ontology_common.get_lineage(sys.argv[1], terms):
print(l)
def main():
terms = ontology_common.parse_obo('new_combined.obo')
categories(terms)
def main():
terms = ontology_common.parse_obo('new_combined.obo')
categories(terms)
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))