def create_keggids_csv(filename, org):
'''
Extract keggids for an organism and save it to a csv file
args: filename is the file containing gene name/ locus for all the organism genes
org is the abrievation of the organism in kegg
'''
#Open csv as panda dataframe (df)
df = pd.read_csv(filename, sep="\t", tupleize_cols=1)
gene_list = tuple(df['Locus'].tolist())
bid_list = tuple(df['Locus tag'].tolist())
kid_list = []
k = KEGG()
#find keggid for each genes
for gene in bid_list:
kstrg = (k.find(org, gene))
kid_list.append(kstrg.split()[1])
#create new df and save it to csv
new_df = pd.DataFrame(columns=['gene', 'b_id', 'kegg_id'])
new_df.gene = gene_list
new_df.b_id = bid_list
new_df.kegg_id = kid_list
new_df.to_csv("ecoli_keggids.csv", sep="\t", index=False)
def queryKegg(theIDs):
print("Currently querying KEGG...")
k = KEGG()
keggData = list()
IDlist = list()
for id in theIDs:
ids = id[3:]
query = k.find("acb", ids)
query = query.split('\t')
finalQuery = query[0]
data = k.get(finalQuery)
dictData = k.parse(data)
keggData.append(dictData)
IDlist.append(ids)
return keggData, IDlist
def search(query,
source="wikipathways",
result_format="xml",
species=None,
genes=None,
user=None):
path_array = []
if source.lower() in ["wikipathways", "all"] and species is None:
url = "http://webservice.wikipathways.org/"
ext = "/findPathwaysByText?query=" + str(query)
r = requests.get(url + ext,
headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
tree = ET.ElementTree(ET.fromstring(r.text))
root = tree.getroot()
for child in root:
temp_path_dict = {}
for subchild in child:
if subchild.tag == "{http://www.wikipathways.org/webservice}id":
temp_path_dict["identifier"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}score":
temp_path_dict["score"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}url":
temp_path_dict["url"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}name":
temp_path_dict["name"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}species":
temp_path_dict["species"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}revision":
temp_path_dict["revision"] = subchild.text
temp_path = gnomics.objects.pathway.Pathway(
identifier=temp_path_dict["identifier"],
identifier_type="WikiPathways ID",
name=temp_path_dict["name"],
taxon=temp_path_dict["species"],
source="WikiPathways")
if temp_path_dict["identifier"] not in path_array:
path_array.append(temp_path)
elif source.lower() in ["wikipathways", "all"] and species is not None:
url = "http://webservice.wikipathways.org/"
ext = "/findPathwaysByText?query=" + str(query) + "&species=" + str(
species)
r = requests.get(url + ext,
headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
tree = ET.ElementTree(ET.fromstring(r.text))
root = tree.getroot()
path_array = []
for child in root:
temp_path_dict = {}
for subchild in child:
if subchild.tag == "{http://www.wikipathways.org/webservice}id":
temp_path_dict["identifier"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}score":
temp_path_dict["score"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}url":
temp_path_dict["url"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}name":
temp_path_dict["name"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}species":
temp_path_dict["species"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}revision":
temp_path_dict["revision"] = subchild.text
temp_path = gnomics.objects.pathway.Pathway(
identifier=temp_path_dict["identifier"],
identifier_type="WikiPathways ID",
name=temp_path_dict["name"],
taxon=temp_path_dict["species"],
source="WikiPathways")
if temp_path_dict["identifier"] not in path_array:
path_array.append(temp_path)
if source.lower() in ["kegg", "all"] and genes is not None:
k = KEGG()
elif source.lower() in ["kegg", "all"] and genes is None:
k = KEGG()
list_of_pathways = k.find("pathway", query)
temp_path_list = list_of_pathways.split("\n")
for thing in temp_path_list:
temp_split = thing.split("\t")
if len(temp_split) != 1:
path_id = temp_split[0].strip().split(":")[1]
path_name = temp_split[1].strip()
if "map" in path_id:
temp_path = gnomics.objects.pathway.Pathway(
identifier=path_id,
identifier_type="KEGG MAP PATHWAY ID",
source="KEGG",
name=path_name)
path_array.append(temp_path)
elif "ko" in path_id:
temp_path = gnomics.objects.pathway.Pathway(
identifier=path_id,
identifier_type="KEGG KO PATHWAY ID",
source="KEGG",
name=path_name)
path_array.append(temp_path)
elif "ec" in path_id:
temp_path = gnomics.objects.pathway.Pathway(
identifier=path_id,
identifier_type="KEGG EC PATHWAY ID",
source="KEGG",
name=path_name)
path_array.append(temp_path)
elif "rn" in path_id:
temp_path = gnomics.objects.pathway.Pathway(
identifier=path_id,
identifier_type="KEGG RN PATHWAY ID",
source="KEGG",
name=path_name)
path_array.append(temp_path)
else:
print(k.get(path_id))
return path_array
class KEGGPathways:
"""
KEGG PATHWAY Database API
"""
def __init__(self, organism="H**o sapiens"):
self.database = KEGG()
self.organism = self.get_organism_code(organism.lower())
def search_by_gene(self, gene_name: str):
"""
Args:
gene_name: gene name (ex. 'BRCA2')
Returns:
Dictionary with ids of all pathways containing given gene as keys and their full names as values.
"""
try:
pathways = self.database.get_pathway_by_gene(
gene_name, self.organism)
return pathways if pathways else {}
except AttributeError:
return {}
def get_pathway(self, pathway_id: str, self_loops: bool = False):
"""
Args:
pathway_id: KEGG pathway id (ex. 'hsa04110')
self_loops: information about whether or not include self loops in returned graph
Returns:
`networkx.DiGraph` object: Directed graph depicting pathway, with a comma-separated string
containing gene names as graph nodes and directed edges representing interactions between genes.
Each edge has weight 'type', which is a list of interaction types between two nodes.
"""
G = nx.DiGraph()
try:
pathway = self.database.parse_kgml_pathway(pathway_id)
except TypeError:
# incorrect pathway_id
pathway = None
if pathway:
names = {}
for entry in pathway['entries']:
# only intra-pathway interactions taken into account
if entry['gene_names']:
names[entry['id']] = {
'name': entry['gene_names'],
'type': entry['type']
}
for rel in pathway['relations']:
if rel['entry1'] in names.keys(
) and rel['entry2'] in names.keys():
e1 = names[rel['entry1']]['name']
e2 = names[rel['entry2']]['name']
G.add_node(e1, type=names[rel['entry1']]['type'])
G.add_node(e2, type=names[rel['entry2']]['type'])
if G.has_edge(e1, e2):
G[e1][e2]['type'] = G[e1][e2]['type'] + [rel['name']]
else:
# assumption of interaction direction entry1 -> entry2 #TODO: validate
if e1 != e2 or (e1 == e2 and self_loops):
G.add_edge(e1, e2, type=[rel['name']])
not_gene_nodes = []
for node in G.nodes():
# only interactions between genes
if G.node[node]['type'] != 'gene':
for in_edge in G.in_edges(node):
for out_edge in G.out_edges(node):
if in_edge[0] != out_edge[1] or (
in_edge[0] == out_edge[1] and self_loops):
G.add_edge(in_edge[0],
out_edge[1],
type=['indirect'])
not_gene_nodes.append(node)
G.remove_nodes_from(not_gene_nodes)
return G
def fetch_organism_codes(self):
"""
Returns:
Dictionary with organisms as keys, and KEGG organism codes as values
{ 'h**o sapiens' : 'hsa',
'human' : 'hsa',
...
}
"""
codes = {}
for line in self.database.list('organism').split('\n'):
if line:
code = line.split('\t')[1]
org = line.split('\t')[2]
if '(' in org:
org = [x.strip().lower() for x in org[:-1].split('(')]
for o in org:
codes[o] = code
else:
codes[org] = code
return codes
def get_organism_code(self, org: str):
"""
Args:
org: organism name (ex. 'H**o sapiens', 'human') - lowercase and uppercase optional
Returns:
str: KEGG organism code
"""
codes = self.fetch_organism_codes()
try:
return codes[org]
except KeyError:
print('Invalid organism name.')
raise
def get_gene_code(self, gen: str):
"""
Args:
gen: gene name (ex. 'FGR', 'NIPAL1')
Returns:
KEGG gene code
"""
code_gen = self.database.find(self.organism, gen)
if code_gen == str('\n'):
code_gen = str()
print('Invalid gene name: ' + str(gen))
return code_gen
def search(query, source="wikipathways", result_format="xml", species=None, genes=None, user=None):
path_array = []
if source.lower() in ["wikipathways", "all"] and species is None:
url = "http://webservice.wikipathways.org/"
ext = "/findPathwaysByText?query=" + str(query)
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
tree = ET.ElementTree(ET.fromstring(r.text))
root = tree.getroot()
for child in root:
temp_path_dict = {}
for subchild in child:
if subchild.tag == "{http://www.wikipathways.org/webservice}id":
temp_path_dict["identifier"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}score":
temp_path_dict["score"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}url":
temp_path_dict["url"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}name":
temp_path_dict["name"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}species":
temp_path_dict["species"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}revision":
temp_path_dict["revision"] = subchild.text
temp_path = gnomics.objects.pathway.Pathway(identifier = temp_path_dict["identifier"], identifier_type = "WikiPathways ID", name = temp_path_dict["name"], taxon = temp_path_dict["species"], source = "WikiPathways")
if temp_path_dict["identifier"] not in path_array:
path_array.append(temp_path)
elif source.lower() in ["wikipathways", "all"] and species is not None:
url = "http://webservice.wikipathways.org/"
ext = "/findPathwaysByText?query=" + str(query) + "&species=" + str(species)
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
tree = ET.ElementTree(ET.fromstring(r.text))
root = tree.getroot()
path_array = []
for child in root:
temp_path_dict = {}
for subchild in child:
if subchild.tag == "{http://www.wikipathways.org/webservice}id":
temp_path_dict["identifier"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}score":
temp_path_dict["score"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}url":
temp_path_dict["url"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}name":
temp_path_dict["name"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}species":
temp_path_dict["species"] = subchild.text
elif subchild.tag == "{http://www.wikipathways.org/webservice}revision":
temp_path_dict["revision"] = subchild.text
temp_path = gnomics.objects.pathway.Pathway(identifier = temp_path_dict["identifier"], identifier_type = "WikiPathways ID", name = temp_path_dict["name"], taxon = temp_path_dict["species"], source = "WikiPathways")
if temp_path_dict["identifier"] not in path_array:
path_array.append(temp_path)
if source.lower() in ["kegg", "all"] and genes is not None:
k = KEGG()
elif source.lower() in ["kegg", "all"] and genes is None:
k = KEGG()
list_of_pathways = k.find("pathway", query)
temp_path_list = list_of_pathways.split("\n")
for thing in temp_path_list:
temp_split = thing.split("\t")
if len(temp_split) != 1:
path_id = temp_split[0].strip().split(":")[1]
path_name = temp_split[1].strip()
if "map" in path_id:
temp_path = gnomics.objects.pathway.Pathway(identifier=path_id, identifier_type="KEGG MAP PATHWAY ID", source="KEGG", name=path_name)
path_array.append(temp_path)
elif "ko" in path_id:
temp_path = gnomics.objects.pathway.Pathway(identifier=path_id, identifier_type="KEGG KO PATHWAY ID", source="KEGG", name=path_name)
path_array.append(temp_path)
elif "ec" in path_id:
temp_path = gnomics.objects.pathway.Pathway(identifier=path_id, identifier_type="KEGG EC PATHWAY ID", source="KEGG", name=path_name)
path_array.append(temp_path)
elif "rn" in path_id:
temp_path = gnomics.objects.pathway.Pathway(identifier=path_id, identifier_type="KEGG RN PATHWAY ID", source="KEGG", name=path_name)
path_array.append(temp_path)
else:
print(k.get(path_id))
return path_array
