def ribosome_cut(species):
coor_dic = sqlcommon.as_coor(species)
fna_dic = sqlcommon.as_fna(coor_dic, species)
if species == "hs":
file_array = ['SRR970538.fdp', 'SRR970490.fdp', 'SRR970565.fdp', 'SRR970561.fdp', 'SRR970587.fdp', 'SRR970588.fdp', 'H_Rep1.fdp', 'H_Rep2.fdp', 'N_Rep1.fdp', 'N_Rep2.fdp']
else:
file_array = ['SRR3208406.fdp']
f_ri_depth = "original_data/"
ri_depth_dic = {}
f_count = 0
# Open and read the file
for i in file_array:
with open(f_ri_depth + i, 'r') as fh:
data = csv.reader(fh)
for line in data:
print i
print line[0]
temp_array = line[0].split('\t')
temp_depth_array = [temp_array[1]]
if temp_array[1] != 'NA':
temp_ri_len = len(fna_dic[temp_array[0]]) + 1
for depth in line[1:temp_ri_len]:
temp_depth_array.append(depth)
temp_depth_str = ';'.join(temp_depth_array)
count_depth = len(temp_depth_str) / 5000;
for k in range(count_depth):
temp_key = temp_array[0] + "_" + str(k)
temp_split_str = temp_depth_str[k * 5000 : (k + 1) * 5000]
if not temp_key in ri_depth_dic:
ri_depth_dic[temp_key] = []
while f_count != len(ri_depth_dic[temp_key]):
ri_depth_dic[temp_key].append('')
ri_depth_dic[temp_key].append(temp_split_str)
temp_key = temp_array[0] + "_" + str(count_depth)
temp_split_str = temp_depth_str[count_depth * 5000::]
if not temp_key in ri_depth_dic:
ri_depth_dic[temp_key] = []
while f_count != len(ri_depth_dic[temp_key]):
ri_depth_dic[temp_key].append('')
ri_depth_dic[temp_key].append(temp_split_str)
if len(line) != len(fna_dic[temp_array[0]]):
print line
f_count += 1
fh.close()
return ri_depth_dic
if not coor_dic[q][0] in gene_uorf_list:
gene_uorf_list.append(coor_dic[q][0])
return uorf_dic
# ---------------- ---------------- ---------------- ---------------- #
# Main Program
# ---------------- ---------------- ---------------- ---------------- #
if __name__ == "__main__":
#./sql_main.py mouse
species = sys.argv[1]
gene_list = []
coor_dic = sqlcommon.as_coor(species)
nm_list = []
for nm in coor_dic.keys():
if coor_dic[nm][1] == 0:
del coor_dic[nm]
else:
if not coor_dic[nm][0] in gene_list:
gene_list.append(coor_dic[nm][0])
if not nm in nm_list:
nm_list.append(coor_dic[nm][1])
IREZone_dic = data_IRES_IREZone(species, coor_dic)
uorf_dic = data_uorf_sort(coor_dic, species)
all_data_dic = {}