def get_ontology():
from biana.biana_commands import available_sessions, create_new_session
# Create a new BIANA session
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=DEFAULT_UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
ontology = objSession.get_ontology(ontology_name="psimiobo", root_attribute_values = [4])
print map(int, ontology.get_all_linked_attributes())
ontology = objSession.dbAccess.get_ontology(ontology_name="psimiobo", root_attribute_values = [45], load_external_entities=True)
#ontology = objSession.dbAccess.get_ontology(ontology_name="psimiobo", root_attribute_values = [59, 109, 63], load_external_entities=True)
print map(lambda x: (int(x[0]), x[1]), ontology.get_linked_attr_and_description_tuples())
return
def get_human_interactome(include_string=False):
from biana.biana_commands import available_sessions, create_new_session
identifier_description_list = [("taxid", "9606")]
relation_type_list = ["interaction"] #,"reaction"] # ["interaction","reaction","complex","pathway"]
level = 0
# Create a new BIANA session
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list=identifier_description_list, attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
uESet1 = objSession.get_user_entity_set("User_Entity_Set_1")
print "# of nodes: ", uESet1.getSize()
if include_string:
# Duplicate the User Entity Set (group of biomolecules) in this session
uESet2 = objSession.duplicate_user_entity_set(user_entity_set_id="User_Entity_Set_1", new_user_entity_set_id="User_Entity_Set_2")
# Fetch relations (except STRING) of biomolecules in 1st set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of experimental edges: ", uESet1.getNumberEdges()
# Fetch relations (only STRING with scores > 700) of biomolecules in 2nd set
relation_type_list = ["functional_association"]
#objSession.create_network( user_entity_set_id = "User_Entity_Set_2" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[("stringscore",">700")], include_relations_last_level=True, use_self_relations=True)
objSession.create_network( user_entity_set_id = "User_Entity_Set_2" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of string edges: ", uESet2.getNumberEdges()
uESet3 = objSession.get_union_of_user_entity_set_list(user_entity_set_list=["User_Entity_Set_1", "User_Entity_Set_2"], include_relations=True, new_user_entity_set_id="User_Entity_Set_3")
objSession.remove_user_entity_set(user_entity_set_id="User_Entity_Set_1")
objSession.remove_user_entity_set(user_entity_set_id="User_Entity_Set_2")
# Export all the information of this set and its network to a file in a tab separated format
#objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_3", out_method=open("network.out", "w").write, node_attributes = ["uniprotaccession"], participant_attributes = [], relation_attributes=["stringscore"], include_relation_ids=False, include_participant_ids=False, include_relation_type=True, include_relation_sources=True, output_1_value_per_attribute=False, output_format="tabulated", include_participant_tags=False, include_relation_tags=False)
objSession.output_user_entity_set_network_in_sif_format(user_entity_set_id = "User_Entity_Set_3", output_path = "./", output_prefix = "human_with_string", node_attributes = [], participant_attributes = [], relation_attributes=["pubmed", "method_id","stringscore"], output_1_value_per_attribute=False, include_tags=False)
else:
# Fetch relations (except STRING) of biomolecules in 1st set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of experimental edges: ", uESet1.getNumberEdges()
# Output set details - all nodes
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("human_nodes.tsv", "w").write, attributes=["uniprotaccession", "geneid", "ensembl", "genesymbol", "go", "hgnc", "disease", "proteinsequence"], include_level_info=False, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False)
# Export sequences of entries in this set as a FASTA file
#objSession.output_user_entity_set_sequences_in_fasta(user_entity_set_id="User_Entity_Set_1", only_selected = False, out_method=open("human_fasta.txt",'w').write, type="proteinsequence") #, attributes=["uniprotaccession"])
# Export all the information of this set and its network to a file in a tab separated format
objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method=open("human_network.out", "w").write, node_attributes = ["uniprotaccession"], participant_attributes = [], relation_attributes=[], include_relation_ids=False, include_participant_ids=False, include_relation_type=True, include_relation_sources=True, output_1_value_per_attribute=False, output_format="tabulated", include_participant_tags=False, include_relation_tags=False)
objSession.output_user_entity_set_network_in_sif_format(user_entity_set_id = "User_Entity_Set_1", output_path = "./", output_prefix = "human", node_attributes = [], participant_attributes = [], relation_attributes=["pubmed", "method_id"], output_1_value_per_attribute=False, include_tags=False)
return
def select_and_create_subset_from_set():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import sets
identifier_description_list = [("genesymbol", "rad2"), ("genesymbol", "rad1")]
identifier_description_list2 = [("genesymbol", "rad1")]
relation_type_list = ["interaction"]
# Create a new BIANA session
objSession = create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list = identifier_description_list, external_entity_attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
# Create another User Entity Set (group of biomolecules) in this session
uESet2 = objSession.create_new_user_entity_set( identifier_description_list = identifier_description_list2, external_entity_attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_2")
# Select all User Entities in the second User Entity Set
user_entities_to_select = uESet2.get_user_entity_ids()
objSession.select_user_entities_from_user_entity_set("User_Entity_Set_1", user_entities_to_select, clear_previous_selection=True)
# Create a new User Entity Set from selected User Entities in the first User Entity Set
objSession.get_sub_user_entity_set(user_entity_set_id = "User_Entity_Set_1", include_relations=False, new_user_entity_set_id="User_Entity_Set_3")
# Output set details
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_3", out_method = open("nodes.out", "w").write, attributes=["genesymbol", "uniprotaccession", "hgnc"], include_level_info=True, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=True, output_1_value_per_attribute=False, include_command_in_rows=False)
def duplicate_and_randomize_network():
from biana.biana_commands import create_new_session, administration, available_sessions
from biana.BianaObjects import BianaSessionManager
import sets
identifier_description_list = [("genesymbol", "rad2")]
identifier_description_list2 = [("genesymbol", "rad1")]
relation_type_list = ["interaction"]
# Create a new BIANA session
objSession = create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list = identifier_description_list, external_entity_attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
# Get relations of biomolecules in this set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = 1, relation_type_list= relation_type_list, include_relations_last_level = False, use_self_relations = False)
# Duplicate (could be used to keep a copy before randomization) the User Entity Set (group of biomolecules) in this session
uESet2 = objSession.duplicate_user_entity_set(user_entity_set_id="User_Entity_Set_1", new_user_entity_set_id="User_Entity_Set_2")
# Randomize the network of the User Entity Set based on the given randomization type
objSession.randomize_user_entity_set_network(user_entity_set_id="User_Entity_Set_1", type_randomization="random")
# Output network details
objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method=open("network.out", "w").write, node_attributes = ["uniprotaccession"], participant_attributes = [], relation_attributes=[], allowed_relation_types="all", include_relation_ids=False, include_participant_ids=False, include_relation_type=True, include_relation_sources=True, output_1_value_per_attribute=False, output_format="tabulated", only_selected=True, substitute_node_attribute_if_not_exists=False)
def create_session():
from biana.biana_commands import available_sessions, create_new_session
# Create a new BIANA session
t1 = clock()
create_new_session(sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=DEFAULT_UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
t2 = clock()
print "Time: ", t2 - t1
return
def get_seed_connected_nodes():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import sets
import biana.utilities.identifier_utilities as id_utils
t_init = time.clock()
relation_type_list = ["interaction"] # ["reaction","complex","pathway","interaction"]
# Create a new BIANA session
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
#identifier_description_list = id_utils.read_identifier_list_from_file("/home/emre/arastirma/colloboration/seeds_intracranial_and_aneurysm_and_mesh_genetics.txt", "genesymbol")
identifier_description_list = id_utils.read_identifier_list_from_file("/home/emre/arastirma/colloboration/subarachnoid_and_hemorrhage_or_haemorrhage_and_mesh_genetics.seeds", "genesymbol")
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list = identifier_description_list, external_entity_attribute_restriction_list=[("taxid","9606")], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
t_1 = time.clock()
# Get relations of biomolecules in this set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = 1, relation_type_list= relation_type_list, include_relations_last_level = False, use_self_relations = False)
t_2 = time.clock()
print "t_network:", t_2-t_1
# Select seeds and nodes connected by seeds in the network of this User Entity Set
user_entities_to_print = sets.Set(uESet1.get_user_entity_ids(level=0))|uESet1.get_user_entity_ids_by_linker_degree_cutoff(2)
objSession.select_user_entities_from_user_entity_set("User_Entity_Set_1", user_entities_to_print, clear_previous_selection=True)
objSession.tag_selected_user_entities(user_entity_set_id="User_Entity_Set_1", tag="seed+connected")
t_3 = time.clock()
print "t_connected:", t_3-t_2
# Output set details - only selected nodes
#objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("nodes_selected.out", "w").write, attributes=["genesymbol", "uniprotaccession", "hgnc"], include_level_info=True, include_degree_info=True, level=None, only_selected=True, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=True, output_1_value_per_attribute=False, include_command_in_rows=False)
# Output set details - all nodes
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("nodes.out", "w").write, attributes=["genesymbol", "uniprotaccession", "hgnc"], include_level_info=True, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=True, output_1_value_per_attribute=False, include_command_in_rows=False)
t_4 = time.clock()
print "t_nodes:", t_4-t_3
# Output network details
objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method=open("network.out", "w").write, node_attributes = [], participant_attributes = [], relation_attributes=["Method_id"], allowed_relation_types="all", include_relation_ids=False, include_participant_ids=True, include_relation_type=True, include_relation_sources=True, output_1_value_per_attribute=False, output_format="tabulated", only_selected=False, substitute_node_attribute_if_not_exists=True, include_participant_tags=False, include_relation_tags = False, include_unconnected_nodes=False)
t_5 = time.clock()
print "t_network:", t_5-t_4
def create_session():
from biana.biana_commands import available_sessions, create_new_session
# Create a new BIANA session
t1 = clock()
create_new_session(
sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=DEFAULT_UNIFICATION_PROTOCOL,
)
objSession = available_sessions["biana_session"]
t2 = clock()
print "Time: ", t2 - t1
return
def get_intersection_of_3_set():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import biana.utilities.identifier_utilities as id_utils
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
objSession.create_new_user_entity_set( identifier_description_list = id_utils.read_identifier_list_from_file(BONE_FILE, id_type="uniprotaccession"), external_entity_attribute_restriction_list=[("taxid","9606")], id_type="embedded",new_user_entity_set_id="bone")
objSession.create_new_user_entity_set( identifier_description_list = id_utils.read_identifier_list_from_file(LIVER_FILE, id_type="uniprotaccession"), external_entity_attribute_restriction_list=[("taxid","9606")], id_type="embedded",new_user_entity_set_id="liver")
objSession.create_new_user_entity_set( identifier_description_list = id_utils.read_identifier_list_from_file(LUNG_FILE, id_type="uniprotaccession"), external_entity_attribute_restriction_list=[("taxid","9606")], id_type="embedded",new_user_entity_set_id="lung")
print "Bone - Liver - Lung User Entity Sets are created..", objSession
objSession.create_network( user_entity_set_id = "bone" , level = 1 , relation_type_list=["complex","interaction","pathway","reaction"] , include_relations_last_level = True , use_self_relations = False)
objSession.create_network( user_entity_set_id = "liver" , level = 1 , relation_type_list=["complex","interaction","pathway","reaction"] , include_relations_last_level = True , use_self_relations = False)
objSession.create_network( user_entity_set_id = "lung" , level = 1 , relation_type_list=["complex","interaction","pathway","reaction"] , include_relations_last_level = True , use_self_relations = False)
print "Bone - Liver - Lung Networks are created..", objSession
objSession.get_intersection_of_user_entity_set_list([objSession.get_user_entity_set("bone"), objSession.get_user_entity_set("liver"), objSession.get_user_entity_set("lung")], include_relations=True, new_user_entity_set_id="intersection")
objSession.get_intersection_of_user_entity_set_list([objSession.get_user_entity_set("bone"), objSession.get_user_entity_set("liver")], include_relations=True, new_user_entity_set_id="bone_liver")
objSession.get_intersection_of_user_entity_set_list([objSession.get_user_entity_set("bone"), objSession.get_user_entity_set("lung")], include_relations=True, new_user_entity_set_id="bone_lung")
objSession.get_intersection_of_user_entity_set_list([objSession.get_user_entity_set("liver"), objSession.get_user_entity_set("lung")], include_relations=True, new_user_entity_set_id="liver_lung")
print "Intersections are created..", objSession
return
def create_interactome_using_biana(taxids = [9606], node_file_prefix="human_nodes", network_files_prefix="human_network", network_type="experimental", load_from_saved_session = False):
"""
Creates ppi specific to an organism network files using BIANA
taxids: List of id(s) of taxonomy identifier of the organism(s) whose
interactome (and in case of more than one organism) interactions
between their interactome) will be created
Node file: node_file_prefix.tsv (as tab seperated values)
Edge files: network_files_prefix.sif (network in sif format), network_file_prefix_attribute.eda (Cytoscape edge attribute files for each attribute)
Network type: "experimental" (type interaction, all ppi db but string) | "functional" (type functional_association, only string) | "all" (experimental + functional)
"""
from biana.biana_commands import available_sessions, create_new_session, save_session, load_session
from biana.BianaObjects import BianaSessionManager
#DB_NAME = "test_biana"
#DB_HOST = "127.0.0.1"
#DB_USER = "******"
#DB_PASS = "******"
#UNIFICATION_PROTOCOL = "(p2)(noself)(noprevious)uniprot_seqtax_geneid_scoppdb"
identifier_description_list = [ ("taxid", taxid) for taxid in taxids ]
level = 0
relation_type_list = []
relation_attribute_restriction_list = []
node_attributes=["uniprotaccession", "geneid", "ensembl", "genesymbol", "go", "hgnc", "disease", "proteinsequence"]
relation_attributes=["pubmed", "method_id"]
if network_type == "functional":
relation_type_list = ["functional_association"]
relation_attributes.extend(["stringscore", "stringscore_neighborhood", "stringscore_fusion", "stringscore_cooccurence", "stringscore_experimental", "stringscore_db", "stringscore_textmining"])
# Uncommet below for only relations from STRING with score > 700
#relation_attribute_restriction_list=[("stringscore",">700")]
elif network_type == "experimental":
relation_type_list = ["interaction"] #,"reaction"] # ["interaction","reaction","complex","pathway"]
elif network_type == "all":
relation_type_list ["interaction", "functional_association"]
else:
raise ValueError("Unrecognized network_type!")
if load_from_saved_session:
load_session(network_files_prefix + "_session.dat")
objSession = available_sessions["biana_session"]
else:
# Create a new BIANA session
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list=identifier_description_list, attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
print "# of nodes: ", objSession.get_user_entity_set("User_Entity_Set_1").getSize()
# Fetch relations of biomolecules in the set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list = relation_attribute_restriction_list, include_relations_last_level=True, use_self_relations=True)
print "# of edges: ", objSession.get_user_entity_set("User_Entity_Set_1").getNumberEdges()
# Save the session
save_session("biana_session", network_files_prefix + "_session.dat")
# Output set details - all nodes
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open(node_file_prefix + ".tsv", "w").write, attributes=node_attributes, include_level_info=False, include_degree_info=False, level=None, only_selected=False, output_format="tabulated", include_tags_info = False, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False, output_only_native_values=False)
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open(node_file_prefix + "_only_native.tsv", "w").write, attributes=["uniprotaccession"], include_level_info=False, include_degree_info=False, level=None, only_selected=False, output_format="tabulated", include_tags_info = False, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False, output_only_native_values=True)
# Export all the information of this set and its network to a file in a tab separated format
objSession.output_user_entity_set_network_in_sif_format(user_entity_set_id = "User_Entity_Set_1", output_path = "./", output_prefix = network_files_prefix, node_attributes = [], participant_attributes = [], relation_attributes = relation_attributes, output_1_value_per_attribute = False, include_tags = False)
## Export sequences of entries in this set as a FASTA file
#objSession.output_user_entity_set_sequences_in_fasta(user_entity_set_id="User_Entity_Set_1", only_selected = False, out_method=open("human_fasta.txt",'w').write, type="proteinsequence") #, attributes=["uniprotaccession"])
## Export all the information of this set and its network to a file in a tab separated format
#available_sessions["biana_session"].output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method = open(network_files_prefix + ".tsv", "w").write, node_attributes = [], participant_attributes = [], relation_attributes = ["method_id"], allowed_relation_types = "all", include_relation_ids = False, include_participant_ids = True, include_relation_type = True, include_relation_sources = True, output_1_value_per_attribute = False, output_format = "tabulated", only_selected = False, substitute_node_attribute_if_not_exists = False, include_participant_tags = False, include_relation_tags = False, include_unconnected_nodes=False)
return
def duplicate_and_randomize_network():
from biana.biana_commands import create_new_session, administration, available_sessions
from biana.BianaObjects import BianaSessionManager
import sets
identifier_description_list = [("genesymbol", "rad2")]
identifier_description_list2 = [("genesymbol", "rad1")]
relation_type_list = ["interaction"]
# Create a new BIANA session
objSession = create_new_session(
sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL,
)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list,
external_entity_attribute_restriction_list=[],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_1",
)
# Get relations of biomolecules in this set
objSession.create_network(
user_entity_set_id="User_Entity_Set_1",
level=1,
relation_type_list=relation_type_list,
include_relations_last_level=False,
use_self_relations=False,
)
# Duplicate (could be used to keep a copy before randomization) the User Entity Set (group of biomolecules) in this session
uESet2 = objSession.duplicate_user_entity_set(
user_entity_set_id="User_Entity_Set_1", new_user_entity_set_id="User_Entity_Set_2"
)
# Randomize the network of the User Entity Set based on the given randomization type
objSession.randomize_user_entity_set_network(user_entity_set_id="User_Entity_Set_1", type_randomization="random")
# Output network details
objSession.output_user_entity_set_network(
user_entity_set_id="User_Entity_Set_1",
out_method=open("network.out", "w").write,
node_attributes=["uniprotaccession"],
participant_attributes=[],
relation_attributes=[],
allowed_relation_types="all",
include_relation_ids=False,
include_participant_ids=False,
include_relation_type=True,
include_relation_sources=True,
output_1_value_per_attribute=False,
output_format="tabulated",
only_selected=True,
substitute_node_attribute_if_not_exists=False,
)
def get_intersection_of_3_set():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import biana.utilities.identifier_utilities as id_utils
create_new_session(sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
objSession.create_new_user_entity_set(
identifier_description_list=id_utils.read_identifier_list_from_file(
BONE_FILE, id_type="uniprotaccession"),
external_entity_attribute_restriction_list=[("taxid", "9606")],
id_type="embedded",
new_user_entity_set_id="bone")
objSession.create_new_user_entity_set(
identifier_description_list=id_utils.read_identifier_list_from_file(
LIVER_FILE, id_type="uniprotaccession"),
external_entity_attribute_restriction_list=[("taxid", "9606")],
id_type="embedded",
new_user_entity_set_id="liver")
objSession.create_new_user_entity_set(
identifier_description_list=id_utils.read_identifier_list_from_file(
LUNG_FILE, id_type="uniprotaccession"),
external_entity_attribute_restriction_list=[("taxid", "9606")],
id_type="embedded",
new_user_entity_set_id="lung")
print "Bone - Liver - Lung User Entity Sets are created..", objSession
objSession.create_network(
user_entity_set_id="bone",
level=1,
relation_type_list=["complex", "interaction", "pathway", "reaction"],
include_relations_last_level=True,
use_self_relations=False)
objSession.create_network(
user_entity_set_id="liver",
level=1,
relation_type_list=["complex", "interaction", "pathway", "reaction"],
include_relations_last_level=True,
use_self_relations=False)
objSession.create_network(
user_entity_set_id="lung",
level=1,
relation_type_list=["complex", "interaction", "pathway", "reaction"],
include_relations_last_level=True,
use_self_relations=False)
print "Bone - Liver - Lung Networks are created..", objSession
objSession.get_intersection_of_user_entity_set_list(
[
objSession.get_user_entity_set("bone"),
objSession.get_user_entity_set("liver"),
objSession.get_user_entity_set("lung")
],
include_relations=True,
new_user_entity_set_id="intersection")
objSession.get_intersection_of_user_entity_set_list(
[
objSession.get_user_entity_set("bone"),
objSession.get_user_entity_set("liver")
],
include_relations=True,
new_user_entity_set_id="bone_liver")
objSession.get_intersection_of_user_entity_set_list(
[
objSession.get_user_entity_set("bone"),
objSession.get_user_entity_set("lung")
],
include_relations=True,
new_user_entity_set_id="bone_lung")
objSession.get_intersection_of_user_entity_set_list(
[
objSession.get_user_entity_set("liver"),
objSession.get_user_entity_set("lung")
],
include_relations=True,
new_user_entity_set_id="liver_lung")
print "Intersections are created..", objSession
return
def simple_session():
from biana.biana_commands import administration, available_sessions, create_new_session, save_session, load_session
from biana.BianaObjects import BianaSessionManager
# Remove comment below to load data from previous session
#load_session("/home/user/test.dat")
identifier_description_list = [("gi", "1019412")
] #[("disease", "alzheimer")]
relation_type_list = ["interaction"
] # ["reaction","complex","pathway","interaction"]
# Create a new BIANA session
create_new_session(sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list,
attribute_restriction_list=[],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_1")
uESet1 = objSession.get_user_entity_set("User_Entity_Set_1")
# Export sequences of entries in this set as a FASTA file
objSession.output_user_entity_set_sequences_in_fasta(
user_entity_set_id="User_Entity_Set_1",
only_selected=False,
out_method=open("test_fasta.txt", 'w').write,
type="proteinsequence",
attributes=["uniprotAccession"])
# Instead of exporting the set as a FASTA file, remove comment below to export it as a tab separated file
#objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("nodes.out", "w").write, attributes=["hgnc", "taxid"], include_level_info=True, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False)
# Fetch relations of biomolecules in this set
objSession.create_network(user_entity_set_id="User_Entity_Set_1",
level=1,
relation_type_list=relation_type_list,
include_relations_last_level=True,
use_self_relations=True)
# Instead of creating network from existing relations, remove comment below make predictions based on shared attribute
#objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = 1 , include_relations_last_level = False , use_self_relations = False , expansion_relation_type_list = ["interaction"] , expansion_attribute_list = [ [("cog", [])] ], expansion_level = 2 )
# Export all the information of this set and its network to a file in a tab separated format
objSession.output_user_entity_set_network(
user_entity_set_id="User_Entity_Set_1",
out_method=open("network.out", "w").write,
node_attributes=["uniprotaccession"],
participant_attributes=[],
relation_attributes=[],
allowed_relation_types="all",
include_relation_ids=False,
include_participant_ids=False,
include_relation_type=True,
include_relation_sources=True,
output_1_value_per_attribute=False,
output_format="tabulated",
only_selected=False,
substitute_node_attribute_if_not_exists=False)
#objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method=open("network.out", "w").write, node_attributes = ["uniprotaccession"], relation_attributes=["psimi_name"], include_relation_sources=True, output_format="tabulated")
# Remove comment below to save this session for later use
#save_session("biana_session", "/home/user/test.dat")
return
def get_seed_connected_nodes():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import sets
import biana.utilities.identifier_utilities as id_utils
t_init = time.clock()
relation_type_list = ["interaction"
] # ["reaction","complex","pathway","interaction"]
# Create a new BIANA session
create_new_session(sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
#identifier_description_list = id_utils.read_identifier_list_from_file("/home/emre/arastirma/colloboration/seeds_intracranial_and_aneurysm_and_mesh_genetics.txt", "genesymbol")
identifier_description_list = id_utils.read_identifier_list_from_file(
"/home/emre/arastirma/colloboration/subarachnoid_and_hemorrhage_or_haemorrhage_and_mesh_genetics.seeds",
"genesymbol")
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list,
external_entity_attribute_restriction_list=[("taxid", "9606")],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_1")
t_1 = time.clock()
# Get relations of biomolecules in this set
objSession.create_network(user_entity_set_id="User_Entity_Set_1",
level=1,
relation_type_list=relation_type_list,
include_relations_last_level=False,
use_self_relations=False)
t_2 = time.clock()
print "t_network:", t_2 - t_1
# Select seeds and nodes connected by seeds in the network of this User Entity Set
user_entities_to_print = sets.Set(uESet1.get_user_entity_ids(
level=0)) | uESet1.get_user_entity_ids_by_linker_degree_cutoff(2)
objSession.select_user_entities_from_user_entity_set(
"User_Entity_Set_1",
user_entities_to_print,
clear_previous_selection=True)
objSession.tag_selected_user_entities(
user_entity_set_id="User_Entity_Set_1", tag="seed+connected")
t_3 = time.clock()
print "t_connected:", t_3 - t_2
# Output set details - only selected nodes
#objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("nodes_selected.out", "w").write, attributes=["genesymbol", "uniprotaccession", "hgnc"], include_level_info=True, include_degree_info=True, level=None, only_selected=True, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=True, output_1_value_per_attribute=False, include_command_in_rows=False)
# Output set details - all nodes
objSession.output_user_entity_set_details(
user_entity_set_id="User_Entity_Set_1",
out_method=open("nodes.out", "w").write,
attributes=["genesymbol", "uniprotaccession", "hgnc"],
include_level_info=True,
include_degree_info=True,
level=None,
only_selected=False,
output_format="tabulated",
include_tags_info=True,
include_tags_linkage_degree_info=[],
substitute_node_attribute_if_not_exists=True,
output_1_value_per_attribute=False,
include_command_in_rows=False)
t_4 = time.clock()
print "t_nodes:", t_4 - t_3
# Output network details
objSession.output_user_entity_set_network(
user_entity_set_id="User_Entity_Set_1",
out_method=open("network.out", "w").write,
node_attributes=[],
participant_attributes=[],
relation_attributes=["Method_id"],
allowed_relation_types="all",
include_relation_ids=False,
include_participant_ids=True,
include_relation_type=True,
include_relation_sources=True,
output_1_value_per_attribute=False,
output_format="tabulated",
only_selected=False,
substitute_node_attribute_if_not_exists=True,
include_participant_tags=False,
include_relation_tags=False,
include_unconnected_nodes=False)
t_5 = time.clock()
print "t_network:", t_5 - t_4
def old_create_human_interactome_using_biana(node_file_prefix="human_nodes", network_files_prefix="human_network", include_string=False): #, load_from_saved_session=False):
"""
Creates human ppi network files using BIANA
Node file: node_file_prefix.tsv (as tab seperated values)
Edge files: network_files_prefix.sif (network in sif format), network_file_prefix_attribute.eda (Cytoscape edge attribute files for each attribute)
"""
from biana.biana_commands import available_sessions, create_new_session, save_session, load_session
from biana.BianaObjects import BianaSessionManager
DB_NAME = "test_biana"
DB_HOST = "127.0.0.1"
DB_USER = "******"
DB_PASS = "******"
UNIFICATION_PROTOCOL = "(p2)(noself)(noprevious)uniprot_seqtax_geneid_scoppdb"
identifier_description_list = [("taxid", "9606")]
relation_type_list = ["interaction"] #,"reaction"] # ["interaction","reaction","complex","pathway"]
level = 0
#if load_from_saved_session:
# load_session(network_files_prefix + "_session.dat")
# return
# Create a new BIANA session
create_new_session(sessionID="biana_session",dbname=DB_NAME, dbhost=DB_HOST, dbuser=DB_USER, dbpassword=DB_PASS, unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set( identifier_description_list=identifier_description_list, attribute_restriction_list=[], id_type="embedded", new_user_entity_set_id="User_Entity_Set_1")
uESet1 = objSession.get_user_entity_set("User_Entity_Set_1")
print "# of nodes: ", uESet1.getSize()
if include_string:
# Duplicate the User Entity Set (group of biomolecules) in this session
uESet2 = objSession.duplicate_user_entity_set(user_entity_set_id="User_Entity_Set_1", new_user_entity_set_id="User_Entity_Set_2")
# Fetch relations (except STRING) of biomolecules in 1st set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of experimental edges: ", uESet1.getNumberEdges()
# Fetch relations (only STRING with scores > 700) of biomolecules in 2nd set
relation_type_list = ["functional_association"]
#objSession.create_network( user_entity_set_id = "User_Entity_Set_2" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[("stringscore",">700")], include_relations_last_level=True, use_self_relations=True)
objSession.create_network( user_entity_set_id = "User_Entity_Set_2" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of string edges: ", uESet2.getNumberEdges()
uESet3 = objSession.get_union_of_user_entity_set_list(user_entity_set_list=["User_Entity_Set_1", "User_Entity_Set_2"], include_relations=True, new_user_entity_set_id="User_Entity_Set_3")
objSession.remove_user_entity_set(user_entity_set_id="User_Entity_Set_1")
objSession.remove_user_entity_set(user_entity_set_id="User_Entity_Set_2")
# Output set details - all nodes
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_3", out_method = open(node_file_prefix+".tsv", "w").write, attributes=["uniprotaccession", "geneid", "ensembl", "genesymbol", "go", "hgnc", "disease", "proteinsequence"], include_level_info=False, include_degree_info=False, level=None, only_selected=False, output_format="tabulated", include_tags_info = False, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False)
# Export all the information of this set and its network to a file in a tab separated format
#objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_3", out_method=open("network.out", "w").write, node_attributes = ["uniprotaccession"], participant_attributes = [], relation_attributes=["stringscore"], include_relation_ids=False, include_participant_ids=False, include_relation_type=True, include_relation_sources=True, output_1_value_per_attribute=False, output_format="tabulated", include_participant_tags=False, include_relation_tags=False)
objSession.output_user_entity_set_network_in_sif_format(user_entity_set_id = "User_Entity_Set_3", output_path = "./", output_prefix = network_files_prefix, node_attributes = [], participant_attributes = [], relation_attributes=["pubmed", "method_id","stringscore"], output_1_value_per_attribute=False, include_tags=False)
else:
# Fetch relations (except STRING) of biomolecules in 1st set
objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = level, relation_type_list=relation_type_list, relation_attribute_restriction_list=[], include_relations_last_level=True, use_self_relations=True)
print "# of experimental edges: ", uESet1.getNumberEdges()
## Get tags for each node - seed, connected, whatever...
#user_entities_to_print = set(available_sessions["biana_session"].get_user_entity_set(user_entity_set_id = "User_Entity_Set_1").get_user_entity_ids(level=0)) | set(available_sessions["biana_session"].get_user_entity_set(user_entity_set_id = "User_Entity_Set_1").get_user_entity_ids_by_linker_degree_cutoff(2))
#available_sessions["biana_session"].select_user_entities_from_user_entity_set("User_Entity_Set_1", user_entities_to_print, clear_previous_selection = True)
#objSession.tag_selected_user_entities(user_entity_set_id="User_Entity_Set_1", tag="seed+connected")
# Output set details - all nodes
objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open(node_file_prefix + ".tsv", "w").write, attributes=["uniprotaccession", "geneid", "ensembl", "genesymbol", "go", "hgnc", "disease", "proteinsequence"], include_level_info=False, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False)
## Export sequences of entries in this set as a FASTA file
#objSession.output_user_entity_set_sequences_in_fasta(user_entity_set_id="User_Entity_Set_1", only_selected = False, out_method=open("human_fasta.txt",'w').write, type="proteinsequence") #, attributes=["uniprotaccession"])
# Export all the information of this set and its network to a file in a tab separated format
objSession.output_user_entity_set_network_in_sif_format(user_entity_set_id = "User_Entity_Set_1", output_path = "./", output_prefix = network_files_prefix, node_attributes = [], participant_attributes = [], relation_attributes=["pubmed", "method_id"], output_1_value_per_attribute=False, include_tags=False)
available_sessions["biana_session"].output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method = open(network_files_prefix + ".tsv", "w").write, node_attributes = [], participant_attributes = [], relation_attributes = ["method_id"], allowed_relation_types = "all", include_relation_ids = False, include_participant_ids = True, include_relation_type = True, include_relation_sources = True, output_1_value_per_attribute = False, output_format = "tabulated", only_selected = False, substitute_node_attribute_if_not_exists = False, include_participant_tags = False, include_relation_tags = False, include_unconnected_nodes=False)
# Save the session
save_session("biana_session", network_files_prefix + "_session.dat")
return
def select_and_create_subset_from_set():
from biana.biana_commands import administration, available_sessions, create_new_session
from biana.BianaObjects import BianaSessionManager
import sets
identifier_description_list = [("genesymbol", "rad2"),
("genesymbol", "rad1")]
identifier_description_list2 = [("genesymbol", "rad1")]
relation_type_list = ["interaction"]
# Create a new BIANA session
objSession = create_new_session(sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list,
external_entity_attribute_restriction_list=[],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_1")
# Create another User Entity Set (group of biomolecules) in this session
uESet2 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list2,
external_entity_attribute_restriction_list=[],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_2")
# Select all User Entities in the second User Entity Set
user_entities_to_select = uESet2.get_user_entity_ids()
objSession.select_user_entities_from_user_entity_set(
"User_Entity_Set_1",
user_entities_to_select,
clear_previous_selection=True)
# Create a new User Entity Set from selected User Entities in the first User Entity Set
objSession.get_sub_user_entity_set(
user_entity_set_id="User_Entity_Set_1",
include_relations=False,
new_user_entity_set_id="User_Entity_Set_3")
# Output set details
objSession.output_user_entity_set_details(
user_entity_set_id="User_Entity_Set_3",
out_method=open("nodes.out", "w").write,
attributes=["genesymbol", "uniprotaccession", "hgnc"],
include_level_info=True,
include_degree_info=True,
level=None,
only_selected=False,
output_format="tabulated",
include_tags_info=True,
include_tags_linkage_degree_info=[],
substitute_node_attribute_if_not_exists=True,
output_1_value_per_attribute=False,
include_command_in_rows=False)
def simple_session():
from biana.biana_commands import administration, available_sessions, create_new_session, save_session, load_session
from biana.BianaObjects import BianaSessionManager
# Remove comment below to load data from previous session
# load_session("/home/user/test.dat")
identifier_description_list = [("gi", "1019412")] # [("disease", "alzheimer")]
relation_type_list = ["interaction"] # ["reaction","complex","pathway","interaction"]
# Create a new BIANA session
create_new_session(
sessionID="biana_session",
dbname=DB_NAME,
dbhost=DB_HOST,
dbuser=DB_USER,
dbpassword=DB_PASS,
unification_protocol=UNIFICATION_PROTOCOL,
)
objSession = available_sessions["biana_session"]
# Create a new User Entity Set (group of biomolecules) in this session
uESet1 = objSession.create_new_user_entity_set(
identifier_description_list=identifier_description_list,
attribute_restriction_list=[],
id_type="embedded",
new_user_entity_set_id="User_Entity_Set_1",
)
uESet1 = objSession.get_user_entity_set("User_Entity_Set_1")
# Export sequences of entries in this set as a FASTA file
objSession.output_user_entity_set_sequences_in_fasta(
user_entity_set_id="User_Entity_Set_1",
only_selected=False,
out_method=open("test_fasta.txt", "w").write,
type="proteinsequence",
attributes=["uniprotAccession"],
)
# Instead of exporting the set as a FASTA file, remove comment below to export it as a tab separated file
# objSession.output_user_entity_set_details(user_entity_set_id = "User_Entity_Set_1", out_method = open("nodes.out", "w").write, attributes=["hgnc", "taxid"], include_level_info=True, include_degree_info=True, level=None, only_selected=False, output_format="tabulated", include_tags_info = True, include_tags_linkage_degree_info=[], substitute_node_attribute_if_not_exists=False, output_1_value_per_attribute=False, include_command_in_rows=False)
# Fetch relations of biomolecules in this set
objSession.create_network(
user_entity_set_id="User_Entity_Set_1",
level=1,
relation_type_list=relation_type_list,
include_relations_last_level=True,
use_self_relations=True,
)
# Instead of creating network from existing relations, remove comment below make predictions based on shared attribute
# objSession.create_network( user_entity_set_id = "User_Entity_Set_1" , level = 1 , include_relations_last_level = False , use_self_relations = False , expansion_relation_type_list = ["interaction"] , expansion_attribute_list = [ [("cog", [])] ], expansion_level = 2 )
# Export all the information of this set and its network to a file in a tab separated format
objSession.output_user_entity_set_network(
user_entity_set_id="User_Entity_Set_1",
out_method=open("network.out", "w").write,
node_attributes=["uniprotaccession"],
participant_attributes=[],
relation_attributes=[],
allowed_relation_types="all",
include_relation_ids=False,
include_participant_ids=False,
include_relation_type=True,
include_relation_sources=True,
output_1_value_per_attribute=False,
output_format="tabulated",
only_selected=False,
substitute_node_attribute_if_not_exists=False,
)
# objSession.output_user_entity_set_network(user_entity_set_id = "User_Entity_Set_1", out_method=open("network.out", "w").write, node_attributes = ["uniprotaccession"], relation_attributes=["psimi_name"], include_relation_sources=True, output_format="tabulated")
# Remove comment below to save this session for later use
# save_session("biana_session", "/home/user/test.dat")
return
