def load_kegg(gene, organism):
k = KEGG()
result_line = ''
try:
a = k.get_pathway_by_gene(gene, organism)
if a:
k_list = list(a.values())
result_line = ', '.join(k_list)
except:
print(" Gene '{0}' is not in KEGG database".format(gene))
return result_line
def kegg(inputInteractions):
from bioservices.kegg import KEGG
k = KEGG()
interactions = []
for items in inputInteractions:
print(items[1].getName())
try:
pathways = k.get_pathway_by_gene(items[1].getName(), "hsa")
#print(pathways)
if pathways:
for key, value in list(pathways.items()):
interactions.append([items[0], value])
except AttributeError:
print("Gene name error!!!!!!!!!")
return interactions
else:
blast_text = 'NULL'
if pfamHits.get(ids) != None:
pfam_text = pfamHits[ids]
else:
pfam_text = 'NULL'
if prositeHits.get(ids) != None:
prosite_text = prositeHits[ids]
else:
prosite_text = 'NULL'
# Get the KEGG hits
kegg = KEGG()
kegg_text = ''
gene_id = gene_ids[ids]
KEGG_IDs = kegg.get_pathway_by_gene(gene_id, "acb")
if KEGG_IDs != None:
for KEGG_ID in KEGG_IDs:
kegg_text += KEGG_IDs[KEGG_ID] + ' [' + KEGG_ID + ']; '
kegg_text = kegg_text[:-2]
else:
kegg_text = 'NULL'
comments = 'NULL'
row = ids + '\t' + blast_text + '\t' + pfam_text + '\t' + prosite_text + '\t' + kegg_text + '\t' + GO_IDs + '\t' + comments + '\n'
output.write(row)
output.close()
# extract all relations from all pathways
from bioservices.kegg import KEGG
kegg = KEGG()
output = open("/home/enrico/Desktop/Snakemake/Kegg.txt", 'w')
input = open("/home/enrico/Desktop/Snakemake/RNA-Seq-counts.txt",
"r",
encoding="latin-1")
line = input.readline().strip()
Header = input.readline().strip()
try:
while line:
line = input.readline().strip()
ID, WCFS1_glc_1, WCFS1_glc_2, WCFS1_rib_1, WCFS1_rib_2, NC8_glc_1, NC8_glc_2, NC8_rib_1, NC8_rib_2 = line.strip(
).split("\t")
res = str(kegg.get_pathway_by_gene(ID, "lpl")).strip('[]')
if res != "None":
output.write(ID + "\t" + res + "\n")
else:
output.write(ID + "\t" + "No pathway found" + "\n")
except:
pass
input.close()
output.close()
else:
dr['refseq_genomic'] = 'NA'
dr['refseq_rna'] = 'NA'
dr['refseq_protein'] = 'NA'
# go
if dq.has_key('go'):
dr['go.cc'] = str(ld2dl(dq['go']['CC'])).replace('u"', "").replace(
'"', "").replace("u'", "").replace(
"'", "") if dq['go'].has_key('CC') else 'NA'
dr['go.mf'] = str(ld2dl(dq['go']['MF'])).replace('u"', "").replace(
'"', "").replace("u'", "").replace(
"'", "") if dq['go'].has_key('MF') else 'NA'
dr['go.bp'] = str(ld2dl(dq['go']['BP'])).replace('u"', "").replace(
'"', "").replace("u'", "").replace(
"'", "") if dq['go'].has_key('BP') else 'NA'
else:
dr['go.cc'] = 'NA'
dr['go.mf'] = 'NA'
dr['go.bp'] = 'NA'
# kegg
if len(re.findall(kt + ':' + dr['entrezgene'] + "\t", kge)) != 0:
dr['kegg'] = str(kg.get_pathway_by_gene(dr['entrezgene'], kt)).replace(
'u"', "").replace('"', "").replace("u'", "").replace("'", "")
else:
dr['kegg'] = 'NA'
sys.stderr.write("\t".join([dr[kr] for kr in lr]) + "\n") # write
if fi != "-":
f.close()
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
len(A)
# In[79]:
#pwd
# In[81]:
with open('./pathway_baicalin_386_genes.txt', 'w') as f:
for i in A:
try:
listname = Symbol.get(i)
n = str(listname[0])
if (n != 'nan'):
j = k.get_pathway_by_gene(n, "hsa")
if (j != None):
for keys, values in j.items():
print(n, keys, values, sep="\t")
#f.write("%s \n" %n)
#for keys,values in j.items():
# f.write("%s %s %s\n" %(n,keys,values))
except AttributeError as err:
print('error')
# In[134]:
#Print algorithms
#for i in A:
# try:
# listname=Symbol.get(i)
