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

# In[1]:


import os
import gzip
import re
import pandas


# In[2]:


# Download human entrez gene information
url = 'ftp://ftp.ncbi.nih.gov/gene/DATA/GENE_INFO/Mammalia/Homo_sapiens.gene_info.gz'
get_ipython().system(' wget --timestamping --directory-prefix download/ $url')


# In[3]:


# Read Entrez info dataset
path = os.path.join('download', 'Homo_sapiens.gene_info.gz')

with gzip.open(path, 'rt') as read_file:
    matches = re.match(r'#Format: (.+) \(', next(read_file))
    columns = matches.group(1).split(' ')
    gene_df = pandas.read_table(read_file, names = columns, na_values=['-'])

len(gene_df)


# In[4]:


# extract symbols and xrefs
xref_rows = list()
symbol_rows = list()

for i, series in gene_df.iterrows():
    gene_id = series.GeneID
    
    # symbols
    symbol = series.Symbol
    if pandas.notnull(symbol):
        symbol_rows.append((gene_id, 'symbol', symbol))
    
    # synonyms
    synonyms = series.Synonyms
    if pandas.notnull(synonyms):
        for synonym in synonyms.split('|'):
            symbol_rows.append((gene_id, 'synonym', synonym))

    # xrefs
    dbXrefs = series.dbXrefs
    if pandas.notnull(dbXrefs):
        for xref in dbXrefs.split('|'):
            db, ref = xref.split(':', 1)
            xref_rows.append((gene_id, db, ref))

xref_df = pandas.DataFrame(xref_rows, columns=['GeneID', 'resource', 'identifier'])
xref_df.to_csv('data/xrefs-human.tsv', sep='\t', index=False)

symbol_df = pandas.DataFrame(symbol_rows, columns=['GeneID', 'type', 'symbol'])
symbol_df.to_csv('data/symbols-human.tsv', sep='\t', index=False)


# In[6]:


xref_df.head()


# In[7]:


symbol_df.head()


# In[5]:


# save a select columnset
columns = ['tax_id', 'GeneID', 'Symbol', 'chromosome', 'map_location', 'type_of_gene', 'description']
select_df = gene_df[columns]
select_df.to_csv('data/genes-human.tsv', sep='\t', index=False)
select_df.head()