# Usage: python exclude_edges.py edges.txt
#
# Purpose: Exclude the edge whose TF is in exclude_tf_list, since we want to hide unpublished data.  Don't distinguish +/- edges.
#          For a TF-Target pair, use the edge that has largest value of metric.  If correlation is negative, use its absolute value.
#
# Created by Hui on 5 Jan 2018

import os, sys

def remove_minus(s):
    ''' Remove the minus sign in s  '''
    index = s.find('-')
    return s[index+1:]


def neg2pos(s):
    s = s.strip()
    lst = s.split('\t')
    x = float(lst[2])
    if x < 0:
        lst[2] = remove_minus(lst[2])
    return '\t'.join(lst)


def make_edge_dict(fname, exclude_lst):
    d = {}
    f = open(fname)
    for line in f:
        line = line.strip()
        lst = line.split('\t')
        tf_id = lst[1].split()[0]
        if not tf_id in exclude_lst:
            target_id = lst[0].split()[0]
            metric = float(lst[8])        
            k = tf_id + '.' + target_id
            if not k in d:
                d[k] = {}
                d[k]['metric']  = metric
                d[k]['line'] = neg2pos(line) # make the third field (correlation) positive if it is negative. Indicate influence, not activation/repression.
            else:
                if d[k]['metric'] < metric:
                    d[k]['metric'] = metric
                    d[k]['line'] = neg2pos(line)
    f.close()
    return d
    

# main
exclude_tf_list = ['AT4G26840', 'AT3G18550']
edge_file_name = sys.argv[1]
d = make_edge_dict(edge_file_name, exclude_tf_list)
f = open(edge_file_name, 'w') # this will make edge.txt empty
for k in sorted(d.keys()):
    f.write('%s\n' % d[k]['line'])
f.close()