def main(target_id, in_file, api_key):
cache_dir = os.path.join(os.getcwd(), "cache")
uniprot_retriever = UniprotRestRetrieval(cache_dir)
cur_db = shelve.open("%s.db" % os.path.splitext(in_file)[0])
# load the database
with open(in_file) as in_handle:
in_handle.readline() # header
for index, line in enumerate(in_handle):
uniprot_id = line.split()[0].strip()
if uniprot_id not in cur_db.keys():
cur_terms = get_description_terms(uniprot_retriever,
uniprot_id, api_key)
if len(cur_terms) > 0:
cur_db[uniprot_id] = cur_terms
# cluster and print out cluster details
term_matrix, uniprot_ids = organize_term_array(cur_db)
cluster_ids, error, nfound = Cluster.kcluster(term_matrix,
nclusters=10, npass=20, method='a', dist='e')
cluster_dict = collections.defaultdict(lambda: [])
for i, cluster_id in enumerate(cluster_ids):
cluster_dict[cluster_id].append(uniprot_ids[i])
for cluster_group in cluster_dict.values():
if target_id in cluster_group:
for item in cluster_group:
print item, cur_db[item]
cur_db.close()
def main(ipr_number, num_clusters):
db_dir = os.path.join(os.getcwd(), "db")
cur_db = shelve.open(os.path.join(db_dir, ipr_number))
tax_graph = build_tax_graph(cur_db)
uniprot_ids = []
info_array = []
for db_domain in cur_db.keys():
if not cur_db[db_domain].get("is_uniref_child", ""):
uniprot_ids.append(db_domain)
db_item = cur_db[db_domain]
cur_cluster_info = [
float(db_item["charge"]),
float(db_item["charge_region"]) * 10.0,
len(db_item.get("db_refs", [])) * 5.0,
calc_domain_distance(db_item) * 100.0,
#max(len(db_item.get("string_interactors", [])) - 1, 0),
]
info_array.append(cur_cluster_info)
info_array = numpy.array(info_array)
print 'Num genes', len(info_array), num_clusters
cluster_ids, error, nfound = Cluster.kcluster(info_array,
nclusters=num_clusters, npass=50)#, method='a', dist='c')
#tree = Cluster.treecluster(info_array, method='a', dist='c')
#cluster_ids = tree.cut(num_clusters)
cluster_dict = collections.defaultdict(lambda: [])
for i, cluster_id in enumerate(cluster_ids):
cluster_dict[cluster_id].append(uniprot_ids[i])
for index, cluster_group in enumerate(cluster_dict.values()):
print '***********', index
org_dists = []
for uniprot_id in cluster_group:
org = cur_db[uniprot_id]["org_scientific_name"]
distance = networkx.dijkstra_path_length(tax_graph, 'Mus musculus',
org)
org_dists.append((distance, org, uniprot_id))
org_dists.sort()
members = []
for d, o, u in org_dists:
members.append(dict(organism=o,
uniprot_id=get_uniprot_links([u]),
alt_names=get_alt_names(cur_db[u]),
alt_ids=get_uniprot_links(cur_db[u].get("uniref_children", [])),
charge=cur_db[u]["charge"],
charge_region="%0.2f" % cur_db[u]["charge_region"],
domains=len(cur_db[u].get("db_refs", [])),
interactions=get_string_link(u,
max(len(cur_db[u].get("string_interactors", [])) - 1, 0)),
description=cur_db[u].get("function_descr", " "),
c_distance="%0.2f" % calc_domain_distance(cur_db[u]),
))
with open("%s-cluster%s.html" % (ipr_number, index), "w") as out_handle:
tmpl = Template(cluster_template)
out_handle.write(tmpl.render(cluster_members=members))
def cluster_kernels(kernels_array, k=kmeans_k, times=1):
print "start clustering"
clusterid = []
error_best = float('inf')
for i in range(times):
clusterid_single, error, nfound = Cluster.kcluster(kernels_array, nclusters=k, dist='a')
if error < error_best:
clusterid = clusterid_single
error_best = error
print 'error:', error_best
cdata, cmask = Cluster.clustercentroids(kernels_array, clusterid=clusterid, )
print "end clustering"
return clusterid, cdata
def main(ipr_number, num_clusters, out_dir):
charge_window = 75
db_dir = os.path.join(os.getcwd(), "db")
cur_db = shelve.open(os.path.join(db_dir, ipr_number))
tax_graph = build_tax_graph(cur_db)
uniprot_ids = []
info_array = []
for db_domain in cur_db.keys():
if not cur_db[db_domain].get("is_uniref_child", ""):
uniprot_ids.append(db_domain)
db_item = cur_db[db_domain]
cur_cluster_info = [
float(db_item["charge"]),
float(db_item["charge_region"]) * 10.0,
len(db_item.get("db_refs", [])) * 5.0,
calc_domain_distance(db_item) * 50.0,
#max(len(db_item.get("string_interactors", [])) - 1, 0),
]
info_array.append(cur_cluster_info)
info_array = numpy.array(info_array)
print 'Num genes', len(info_array), num_clusters
cluster_ids, error, nfound = Cluster.kcluster(
info_array, nclusters=num_clusters, npass=50) #, method='a', dist='c')
#tree = Cluster.treecluster(info_array, method='a', dist='c')
#cluster_ids = tree.cut(num_clusters)
cluster_dict = collections.defaultdict(lambda: [])
for i, cluster_id in enumerate(cluster_ids):
cluster_dict[cluster_id].append(uniprot_ids[i])
out_seq_file = os.path.join(out_dir, "%s-seqs.fa" % (ipr_number))
out_seq_handle = open(out_seq_file, "w")
for index, cluster_group in enumerate(cluster_dict.values()):
print '***********', index
org_dists = []
for uniprot_id in cluster_group:
org = cur_db[uniprot_id]["org_scientific_name"]
distance = networkx.dijkstra_path_length(tax_graph, 'Mus musculus',
org)
org_dists.append((distance, org, uniprot_id))
org_dists.sort()
members = []
for d, o, u in org_dists:
charge_plot_img = calc_charge_plot(u, cur_db[u], charge_window,
out_dir)
base, ext = os.path.splitext(charge_plot_img)
disorder_plot_img = "%s-idr%s" % (base, ext)
rec = Fasta.Record()
rec.title = u
rec.sequence = cur_db[u]["seq"]
out_seq_handle.write(str(rec) + "\n")
members.append(
dict(
organism=o,
uniprot_id=get_uniprot_links([u]),
alt_names=get_alt_names(cur_db[u]),
alt_ids=get_uniprot_links(cur_db[u].get(
"uniref_children", [])),
charge=cur_db[u]["charge"],
charge_region="%0.2f" % cur_db[u]["charge_region"],
charge_plot_img=charge_plot_img,
disorder_plot_img=disorder_plot_img,
domains=len(cur_db[u].get("db_refs", [])),
interactions=get_string_link(
u,
max(
len(cur_db[u].get("string_interactors", [])) - 1,
0)),
description=cur_db[u].get("function_descr", " "),
c_distance="%0.2f" % calc_domain_distance(cur_db[u]),
))
with open(
os.path.join(out_dir,
"%s-cluster%s.html" % (ipr_number, index)),
"w") as out_handle:
tmpl = Template(cluster_template)
out_handle.write(tmpl.render(cluster_members=members))
