args['strip'], is_enum=args['enumerate'])
dsb_baseline = DomainSetBuilder(cons_baseline, args['win'], args['max_g'],
args['strip'], is_enum=args['enumerate'])
# dsb_baseline = DomainSetBuilder(win=args['win'], max_gap=args['max_g'],
# is_enum=args['enumerate'], consensus=cons_baseline,
# is_strip=args['strip'])
domains_query = dsb_query.build() # build abundance counts
domains_baseline = dsb_baseline.build()
status_message('Identifying domains', 'OK')
db = DomainAbundanceBuilder(query=domains_query, baseline=domains_baseline)
domains = db.build() # build contingency matrices
dpp = DomainPrettyPrinter(domains = domains, pval = args['p'],
out=args['o'])
dpp.display() # pretty-print domains
status_message('Domain over-representation computation complete ', 'OK')
else:
args.update({'f':args['query'],'f2':args['baseline'],'a':None})
input_state = InputWrapperState(args)
#input_state.assign_matrix() # parse in-built or custom matrix
targets = input_state.parse_fasta(input_state.fname)
baselines = input_state.parse_fasta(input_state.fname2)
if not args['overlap']:
target_names = list([target.name for target in targets])
baselines = list([baseline for baseline in baselines if baseline.name not in target_names])
extract_and_analyze_domains(targets,baselines,input_state)
status_message('Domain analysis via multiple runs complete ', 'OK')
except (IOError, KeyboardInterrupt, IndexError) as e:
print(str(e))
def cluster_domains(domain_occurrences,node_types,subsmat,args):
'''
A class that finds pairwise edit distances between domains and clusters them, does so for each domain length.
Returns a domain-seed keyed dictionary of domain lists (clusters).
'''
# Set the minimum size at which domains should be clustered
min_domain_size = 7 # maybe should be 8
print("Clustering domains")
# Set up pairwise alignment args
domain_args = {'f':None,'f2':None,'a':None,'subsmat':subsmat,'gap':-1,'gapopen':0,'matrix':None,'custom':None,'o':None,'n':args['n'],'node_types':None}
input_state = InputWrapperState(domain_args)
input_state.subsmat = subsmat
domains = list([domain for domain in domain_occurrences.keys()])
# Cluster results via average distance criterion
#linkages = cluster.hierarchy.average(distance_mat)
### Split domains up by size first, then cluster those that are large enough
# Determine max length
print("Domains: "+str(domains))
min_length = min(len(domain) for domain in domains)
max_length = max(len(domain) for domain in domains)
clusters_by_length = {}
# Move short domains into their own clusters
for length in range(min_length,min_domain_size):
domains_sub = list([domain for domain in domains if len(domain) == length])
clusters = {}
for domain in domains_sub:
clusters[domain] = [domain]
clusters_by_length[length] = clusters
# Cluster domains that are long enough for each size
for length in range(min_domain_size,max_length+1):
domains_sub = list([domain for domain in domains if len(domain) == length])
#domains_ns = list([NeuriteSequence("D"+str(i),domains[i]) for i in range(len(domains))])
domains_ns = list([NeuriteSequence(domains_sub[i],domains_sub[i]) for i in range(len(domains_sub))])
domain_id_map = {domains_sub[i]:i for i in range(len(domains_sub))}
driver = PairwiseDriver(domains_ns, domains_ns, input_state, store_pairwise=True, score_type='num_gaps')
driver.start()
distance_mat = driver.get_score_matrix()
'''
Determine clusters from hierarchy ???
Use abundance sort and then UCLUST
- First and subsequent sequences are seeds unless they are close enough to an existing seed,
in which case they are merged with the seed's cluster.
- Domains shorter than min_domain_size go in their own separate clusters.
- Domains that are exact sub- or super-sequences of a domain already in a cluster are excluded
'''
# First sort domains by occurrence frequency, requires creating tuples from domain and occurrence count
domain_tuples = []
for domain in domains_sub:
domain_tuples.append((domain,domain_occurrences[domain]))
sorted_tuples = sorted(domain_tuples, key=lambda domain_tup: (domain_tup[1],len(domain_tup[0])), reverse=True)
sorted_domains = list([tup[0] for tup in sorted_tuples])
if len(sorted_domains) > 0:
# UCLUST implementation
separates = {}
clusters = {sorted_domains[0]:list([sorted_domains[0]])}
for domain in sorted_domains[1:]:
domain_pos = domain_id_map[domain]
closest_cluster = -1,1000
if len(domain) < min_domain_size:
separates[domain] = list([domain])
else:
for seed in clusters:
seed_pos = domain_id_map[seed]
dist = max(distance_mat[domain_pos][seed_pos],distance_mat[seed_pos][domain_pos])
if dist <= max_cluster_dist and dist < closest_cluster[1]:
closest_cluster = seed,dist
if closest_cluster[0] == -1:
# If not close enough to any existing seed, add new cluster
clusters[domain] = list([domain])
else:
# Otherwise add it to the cluster it's closest to
clusters[closest_cluster[0]].append(domain)
clusters_by_length[length] = clusters
return clusters_by_length
consensus_object = msa_driver.build_consensus(args['thresh'],args['type'])
# Write MSA and consensus to file
consensus_fact = ConsensusFilterFactory(msa_driver,consensus_object)
consensus_fact.write(fname=args['build'])
#consensus_fact = ConsensusFilterFactory(driver.alns, driver.composite, args['thresh'], args['type'])
#consensus_fact.build_consensus()
#consensus_fact.write(fname=args['build']) # write analysis
if __name__ == '__main__':
try:
args = AlignmentCommandParser().parse_args()
AlignmentArgumentValidator(args) # test all arguments are correct
print('spaghetti - v.' + str(version) + '\n=================')
input_state = InputWrapperState(args)
input_state.assign_matrix() # parse in-built or custom matrix
targets = input_state.parse_fasta(input_state.fname) # next, parse fasta file
if input_state.fname2 is None:
queries = targets
else:
queries = input_state.parse_fasta(input_state.fname2)
if args['mode'] == 'local':
run_local(targets, queries, input_state)
elif args['mode'] == 'msa': # start multiple-sequence alignment (MSA)
run_msa(queries, input_state)
except (IOError, KeyboardInterrupt, IndexError) as e:
print(str(e)+'\n')
