Script used in http://blog.matteoferla.com/2016/05/gene-symbol-poetry.html

gene_symbol_poetry

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#Written for python 3, not tested under 2.
"""
Finds all gene symbols (`get_all_genes()` method) and find the genes in common with the word list.
"""
__author__ = "Matteo Ferla. [Github](https://github.com/matteoferla)"
__email__ = "matteo.ferla@gmail.com"
__date__ = "10/05/16"

N = "\n"
T = "\t"
#N = "<br/>

import csv,os

def get_all_genes(out_fp='symbol.txt'):
    """
    Requires the all.ptt folder downloaded from FTP of NCBI.
    """
    genebag=set()
    os.chdir('all.ptt')
    for dp in os.scandir():
        if dp.is_dir():
            os.chdir(dp.name)
            for fp in os.listdir():
                if fp.find(".ptt") != -1:
                    fh=open(fp, "r")
                    next(fh)
                    next(fh)
                    for gene in csv.DictReader(fh, dialect='excel-tab'):
                        genebag.add(gene['Gene'])
            os.chdir('..')
    os.chdir('..')
    open(out_fp,'w').write("\n".join(genebag))

def get_all_commonon(gene_fp='symbol.txt',word_fp='en.txt'):
    def genecase(name):
        return name[0:3].lower()+name[3:].upper()
    def parse_to_set(fp):
        return set({x.replace('\n','').lower() for x in open(fp).readlines()})
    genebag=parse_to_set(gene_fp)
    wordbag=parse_to_set(word_fp)
    print("\n".join(genecase(x) for x in sorted(genebag.intersection(wordbag))))

if __name__ == "__main__":
    get_all_genes()
    get_all_commonon()