#!/usr/bin/env python
# coding: utf-8

# In[1]:


import io
import gzip

import pandas
import requests
import networkx

import eutility
import cooccurrence


# In[ ]:





# In[ ]:





# # Tissues

# In[3]:


# Read MeSH UBERON Anatomical structures
url = 'https://raw.githubusercontent.com/dhimmel/uberon/7de0ed6238c26ea82accae6fc57accd1b845111d/data/mesh-map.tsv'
uberon_df = pandas.read_table(url)
uberon_df.head()


# In[5]:


rows_out = list()

for i, row in uberon_df.iterrows():
    term_query = '{tissue}[MeSH Terms:noexp]'.format(tissue = row.mesh_name.lower())
    payload = {'db': 'pubmed', 'term': term_query}
    pmids = eutility.esearch_query(payload, retmax = 5000, sleep=2)
    row['term_query'] = term_query
    row['n_articles'] = len(pmids)
    row['pubmed_ids'] = '|'.join(pmids)
    rows_out.append(row)
    print('{} articles for {}'.format(len(pmids), row.mesh_name))

uberon_pmids_df = pandas.DataFrame(rows_out)


# In[6]:


with gzip.open('data/uberon-pmids.tsv.gz', 'w') as write_file:
    write_file = io.TextIOWrapper(write_file)
    uberon_pmids_df.to_csv(write_file, sep='\t', index=False)

uberon_pmids_df.head()


# # Tissue-Disease Cooccurrence

# In[2]:


uberon_df, uberon_to_pmids = cooccurrence.read_pmids_tsv('data/uberon-pmids.tsv.gz', key='mesh_id')
disease_df, disease_to_pmids = cooccurrence.read_pmids_tsv('data/disease-pmids.tsv.gz', key='doid_code')


# In[7]:


cooc_df = cooccurrence.score_pmid_cooccurrence(disease_to_pmids, uberon_to_pmids, 'doid_code', 'mesh_id')


# In[ ]:





# In[8]:


cooc_df = uberon_df[['mesh_id', 'mesh_name']].drop_duplicates().merge(cooc_df)
cooc_df = disease_df[['doid_code', 'doid_name']].drop_duplicates().merge(cooc_df)
cooc_df = cooc_df.sort(['doid_name', 'p_fisher'])
cooc_df.to_csv('data/disease-uberon-cooccurrence.tsv', index=False, sep='\t')
cooc_df.head()


# In[ ]: