def __init__(self, email: str, query_str: str, outprefix: str) -> None:
"""
Initialize class
:param gene_list:
"""
self.paths = PhenoXPaths(outprefix)
self.query_str = query_str
self.email = email
def __init__(self, cluster_dict: Dict, meta_dict: Dict,
outprefix: str) -> None:
"""
Initialize class
:param cluster_dict: key=cluster_ids, value=list of GDS ids
:param meta_dict: key=gds_ids, value=list of gds metrics (n_samples, dates, GPLs)
:param meta_list: index list of gds categories
"""
self.paths = PhenoXPaths(outprefix)
self.clusters = cluster_dict
self.num_clusters = len(cluster_dict)
self.meta_dict = meta_dict
self.meta_list = ('Sample N', 'Submission Age', 'GPL')
def __init__(self, outprefix: str):
"""
Initialize MeSH search tool
"""
paths = PhenoXPaths(outprefix)
mesh_json_path = os.path.join(paths.data_dir, 'mesh.json')
self.mesh = dict()
if not os.path.exists(mesh_json_path):
mesh_bin_file = glob.glob(os.path.join(paths.data_dir, '*.bin'))
if mesh_bin_file:
self._parse_mesh_bin(mesh_bin_file[0], mesh_json_path)
self.mesh = json.load(open(mesh_json_path, 'r'))
def __init__(self, outprefix, term, email, tool="phenotypeXpression", efetch_batch=5000, elink_batch=100):
Entrez.email = email
Entrez.tool = tool
self.efetch_batch = efetch_batch
self.elink_batch = elink_batch
self.db = 'geoprofiles'
self.paths = PhenoXPaths(outprefix)
term_name = term.replace(' ', '-')
self.hcluster_file = os.path.join(
self.paths.output_dir, "{}_{}_hierarchical_clusters.pdf".format(self.paths.outprefix, term_name)
)
self.tree_file = os.path.join(
self.paths.output_dir, "{}_{}_newick_tree.txt".format(self.paths.outprefix, term_name)
)
self.heatmap_file = os.path.join(
self.paths.output_dir, "{}_{}_heatmap.pdf".format(self.paths.outprefix, term_name)
)
self.dist_graph_file = os.path.join(
self.paths.output_dir, "{}_{}_dist_graph.pdf".format(self.paths.outprefix, term_name)
)
def __init__(self, email: str, outprefix: str):
Entrez.email = email
self.paths = PhenoXPaths(outprefix)
self.pmid_abstracts = dict()
# disease and human phenotype NER
self.pmid_dner = {}
# raw entity text
self.pmid_ent_text = {}
self.dner_cluster = {}
self.total_dner = []
self.nlp = spacy.load('en')
self.id2kw = pickle.load(
open(os.path.join(self.paths.data_dir, 'id2kw_dict.pkl'), 'rb'))
self.kw2id = pickle.load(
open(os.path.join(self.paths.data_dir, 'kw2id_dict.pkl'), 'rb'))
entity = Entity(keywords_list=list(self.kw2id.keys()), label='DO/HPO')
self.nlp.add_pipe(entity, last=True)
# read synonyms from HGNC
with open(os.path.join(self.paths.data_dir, 'hgnc_synonyms.json'),
'r') as f:
hgnc_syn = f.read()
self.hgnc = json.loads(hgnc_syn)
import os
import json
from phenox.paths import PhenoXPaths
paths = PhenoXPaths()
hgnc_json_file = os.path.join(paths.data_dir, 'hgnc.json')
hgnc_syn_file = os.path.join(paths.data_dir, 'hgnc_synonyms.json')
with open(hgnc_json_file, 'r') as f:
text = f.read()
hgnc = json.loads(text)
num_entries = hgnc['response']['numFound']
data = hgnc['response']['docs']
hgnc_dict = dict()
for entry in data:
try:
symbol = entry['symbol']
alias_symbol = entry['alias_symbol'] if 'alias_symbol' in entry else []
prev_symbol = entry['prev_symbol'] if 'prev_symbol' in entry else []
name = entry['name']
prev_name = entry['prev_name'] if 'prev_name' in entry else []
hgnc_dict[symbol] = {
'names': [name] + prev_name,
'aliases': alias_symbol + prev_symbol
def __init__(self, outprefix: str):
self.paths = PhenoXPaths(outprefix)