# Now modified to enable the use of different sp. code dictionaries and group lists in analysis, determined by sys.argv[1] and sys.argv[2]..
import group
import sys
# sys.argv[1] must equal groups, alt_groups or alt_groups_18.
# sys.argv[2] must equal codes, alt_codes, or alt_codes_18.
# function_mappings and select_function() function are defined to map the sys.argvs from strings to actual functions.
# Comma-separated returns allow multiple returns from the same function (only just realised this).
function_mappings = {
'groups': group.groups(),
'alt_groups': group.alt_groups(),
'alt_groups_18': group.alt_groups_18(),
'codes': group.codes(),
'alt_codes': group.alt_codes(),
'alt_codes_18': group.alt_codes_18()
}
def select_function():
while True:
try:
return function_mappings[sys.argv[1]], function_mappings[
sys.argv[2]]
except KeyError:
print('Invalid function, try again.')
# select_function is called with the relevant group list and codes - these should correspond else the program may fail.
group_list, sp_codes = select_function()
query = []
import group
import glob
import re
codes = group.alt_codes_18()
sp_list = []
for sp in codes:
sp_list.append(sp)
to_parse = glob.glob("*.fal")
for sp in sp_list:
filename = "%s_total.txt" % sp
output = open(filename, "w")
k = 0
for file in to_parse:
species_present = []
with open(file) as f:
for line in f:
if line.startswith(">"):
fields = re.split("_", line)
species = fields[0][1:]
if sp == species:
if species not in species_present:
species_present.append(species)
outputWrite = output.write(f"{file}\n")
k += 1
outputWrite = output.write(f"{sp} total OGs: {k}")
output.close()
# This script will print out the groups present in certain OGs.
# Is only a temporary script - just needed to see the constituent taxa of 'Other' in certain OGs.
# The OGs in question are from 4-way ventral groove-bearing eukaryote sets.
import group
import re
vg = "setquery_outputs/ventral_groove/ventral_groove_minus_one.txt"
og_list = []
og_list = group.count_ogs(vg)
# Append str to og_list using list comprehension.
# Note: a for loop og + .fal will not keep the changes.
og_list = [og + ".fal" for og in og_list]
to_parse = og_list
code_map = group.alt_codes_18()
# Lifted from find_group.
for falfile in to_parse:
groups_present = []
with open(falfile) as f:
for line in f:
if line.startswith('>'):
fields = re.split('_', line) # Separates sp. code
species_code = fields[0][1:] # Removes '>'
for i in code_map: # Linking sp. code to group
gr = code_map[species_code]
if gr not in groups_present: # Adding to group array if new group
groups_present.append(gr)
print(falfile, groups_present)