def do_LIST(self, params):
if params:
self.writeline('501 command syntax error')
return
self.writeline('215 list of newsgroups follows')
for g in group.groups():
(lowest, highest, count) = g.article_range()
self.writeline('%s %s %s n' % (g.name, highest, lowest))
self.writeline('.')
import spgr # *** Calculates the proportion of shared genome for each eukaryote group. ***
import group
import parseTotal
groups = group.groups()
output = open("gr_prop_freq_output.txt", "w")
totaldic = parseTotal.parse_total()
for g in groups:
proplist = []
filename = "gr_" + g + ".txt"
res = spgr.gr_count(filename) # gr_count is carried out on the relevant output file.
total = totaldic[g] # Total genome size is accessed for each group
for name in res:
og = res[name] # Number of OGs shared with group g is compared for every group.
prop = round(int(og) / int(total) * 100, 2) # Proportion is calculated.
proplist.append(prop)
propdic = dict(zip(groups, proplist)) # Proportion dictionary is created.
print(propdic)
outputWrite = output.write(f"{g}\t{str(propdic)}\n")
output.close()
# *** setquery.py can be used to search presence of OGs for 3+ groups. This can be used to link OGs to particular character traits. ***
# 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()
# table4.py is modified from the earlier table files.
# Its purpose is to order and format the pairwise OG data so it enters R in the correct manner.
# This is the alternative to ordering and formatting in R, which I cannot do at this point.
# This script will serve my needs until I am more competent in R.
# minusown list is ordered differently due to differences in total OGs when own groups are excluded.
import re
import group
import glob
group_names = group.groups()
group_names.sort()
data = []
output = open("ordered_vector_data_minusown.txt", "w")
for name in group_names:
to_parse = glob.glob("*.txt")
for file in to_parse:
filename = file.split("_")
if name in filename:
with open(file) as f:
for line in f:
og = re.search(r"\w*:\s(\w*)", line)
if og:
data.append(og.group(1))
# This list can be modified as needed.
# At this time I have arranged the groups in order of total OGs shared.
# This will result in a more sensible-looking stacked barplot.
correct_order = [
"SAR", "Other", "Archaeplastida", "Haptista", "Obazoa", "Discoba",
"Ancyromonadida", "Cryptista", "Amoebozoa", "Metamonads", "Malawimonadidae"
# total.py is the new, integrated file that processes total OG data (formerly carried out by parseOG.py and groupdata.py).
# The related functions, parse_total() (from parseTotal.py) and parse_OG (from parseOG.py) are now incorporated into the group module.
# split_other_group() has also been added to group.py to include relevant subgroups from 'Other' in a new list.
import glob
import group
import re
# To be executed in total_genome dir.
# 18 groups list is currently being used.
to_parse = glob.glob("*_allOGs.txt")
output = open("/mnt/c/Users/scamb/Documents/uob_msc/Genome_Data/OG_arb-fal/new_outputs/summary_data/group_total.txt", "w")
original_groups = group.groups()
correct_order_groups_15 = ["SAR", "Haptista", "Archaeplastida", "Obazoa", "Telonemids", "Discoba", "Ancyromonadida", "Cryptista", "Atwista", "Amoebozoa", "Collodictyonids", "Metamonads", "Apusomonada", "Hemimastigophora", "Malawimonadidae"]
correct_order_groups_18 = ["Alveolata", "Stramenopiles", "Archaeplastida", "Obazoa", "Telonemids", "Discoba", "Centrohelids", "Ancyromonadida", "Cryptista", "Rhizaria", "Haptyophyta", "Atwista", "Amoebozoa", "Collodictyonids", "Metamonads", "Apusomonada", "Hemimastigophora", "Malawimonadidae"]
for file in to_parse:
name = re.split("_", file)
og = group.parse_OG(file)
outputWrite = output.write(f"{name[0]}\t{og}\n")
output.close()
# Writes out totals and own OGs to a file as a single vector.
# The data can then be processed in R.
own_OGs_to_parse = glob.glob("/mnt/c/Users/scamb/Documents/uob_msc/Genome_data/OG_arb-fal/new_outputs/*.txt")
totals_own_output = open("/mnt/c/Users/scamb/Documents/uob_msc/Genome_data/OG_arb-fal/new_outputs/summary_data/vector_totals_own_18.txt", "w")
# correct_order_groups must be at top of loop to ensure correct order is maintained.
# list of choice can be configured here.
for eugroup in correct_order_groups_18:
for art in g.article_numbers():
stat = os.stat(g.article_file(art))
if now - stat.st_mtime > lifetime:
to_remove.add(art)
if to_remove:
logger.info("Expiring in " + g.name)
index = g.load_eval("index", {})
# XXX might need to generate index if it didn't exist
g.saferemove("index")
for (id, art) in index.items():
if art in to_remove:
logger.info("Expiring article %s@%s (%s)"
% (id, g.name, art))
del index[id]
# XXX need to catch exceptions so we always save next art number
g.save("index", repr(index))
for art in to_remove:
g.delete_article(art)
finally:
g.lockfile.unlock()
for g in group.groups():
expire(g)
