def load_gene_expression_profile(gene_list_file_name, gene_expression_file_name, gene_filter_file_name=None, gene_list_path=None, gene_expression_path=None, gene_filter_path=None ,by_gene=False, list_mode = "FROM_DISK"):
stopwatch = Stopwatch()
stopwatch.start()
if list_mode == "ON_THE_FLY":
gene_list = gene_list_file_name
else:
gene_list = load_gene_list(gene_list_file_name=gene_list_file_name, gene_list_path=gene_list_path)
gene_list = [l.split(".")[0] for i, l in enumerate(gene_list)]
print stopwatch.stop("done loading gene list")
# random.shuffle(gene_list)
# gene_list = gene_list[:400]
if gene_filter_file_name:
stopwatch.start()
filter_gene_list = load_gene_list(gene_list_file_name=gene_filter_file_name, gene_list_path=gene_filter_path)
gene_list = [cur for cur in gene_list if cur in filter_gene_list]
print stopwatch.stop("done filter gene list")
if gene_expression_path == None:
gene_expression_path = os.path.join(constants.TCGA_DATA_DIR, gene_expression_file_name)
stopwatch.start()
f = open(gene_expression_path,'r')
expression_profiles_filtered = [l.strip().split() for i, l in enumerate(f) if i==0 or l[:l.strip().find('\t')].split(".")[0] in gene_list]
# or l.strip()[0:l.strip().find('\t')] in gene_list or l.strip()[0:l.strip().find('\t')].split(".")[0] in gene_list
f.close()
print stopwatch.stop("done filter gene expression")
if not by_gene:
stopwatch.start()
expression_profiles_filtered = np.flip(np.rot90(expression_profiles_filtered, k=1, axes=(1,0)),1)
print stopwatch.stop("done rotate gene expression")
return expression_profiles_filtered
async def _eval(ctx, *, code: str):
if not dev_check(ctx.author.id):
return await ctx.send(
f"Sorry, but you can't run this command because you ain't a developer! {bot.get_emoji(555121740465045516)}"
)
env = {
"bot": bot,
"ctx": ctx,
"channel": ctx.channel,
"author": ctx.author,
"guild": ctx.guild,
"message": ctx.message,
"msg": ctx.message,
"_": bot._last_result,
"source": inspect.getsource,
"src": inspect.getsource,
"session": bot.session,
"docs": lambda x: print(x.__doc__)
}
env.update(globals())
body = cleanup_code(code)
stdout = io.StringIO()
err = out = None
to_compile = f"async def func():\n{textwrap.indent(body, ' ')}"
stopwatch = Stopwatch().start()
try:
exec(to_compile, env)
except Exception as e:
stopwatch.stop()
err = await ctx.send(
f"**Error**```py\n{e.__class__.__name__}: {e}\n```\n**Type**```ts\n{Type(e)}```\n⏱ {stopwatch}"
)
return await ctx.message.add_reaction(bot.get_emoji(522530579627900938)
)
func = env["func"]
stopwatch.restart()
try:
with redirect_stdout(stdout):
ret = await func()
stopwatch.stop()
except Exception as e:
stopwatch.stop()
value = stdout.getvalue()
err = await ctx.send(
f"**Error**```py\n{value}{traceback.format_exc()}\n```\n**Type**```ts\n{Type(err)}```\n⏱ {stopwatch}"
)
else:
value = stdout.getvalue()
if ret is None:
if value:
try:
out = await ctx.send(
f"**Output**```py\n{value}```\n⏱ {stopwatch}")
except:
paginated_text = paginate(value)
for page in paginated_text:
if page == paginated_text[-1]:
out = await ctx.send(f"```py\n{page}\n```",
edit=False)
break
await ctx.send(f"```py\n{page}\n```", edit=False)
await ctx.send(f"⏱ {stopwatch}", edit=False)
else:
bot._last_result = ret
try:
out = await ctx.send(
f"**Output**```py\n{value}{ret}```\n**Type**```ts\n{Type(ret)}```\n⏱ {stopwatch}"
)
except:
paginated_text = paginate(f"{value}{ret}")
for page in paginated_text:
if page == paginated_text[-1]:
out = await ctx.send(f"```py\n{page}```", edit=False)
break
await ctx.send(f"```py\n{page}```", edit=False)
await ctx.send(f"**Type**```ts\n{Type(ret)}```\n⏱ {stopwatch}",
edit=False)
if out:
await ctx.message.add_reaction(bot.get_emoji(522530578860605442))
elif err:
await ctx.message.add_reaction(bot.get_emoji(522530579627900938))
else:
await ctx.message.add_reaction("\u2705")
def check_group_enrichment_goatools(tested_gene_file_name,
total_gene_file_name,
th=1):
if len(tested_gene_file_name) == 0 or len(total_gene_file_name) == 0:
return []
if type(total_gene_file_name) == str:
total_gene_list = load_gene_list(total_gene_file_name)
else:
total_gene_list = total_gene_file_name
if type(tested_gene_file_name) == str:
tested_gene_list = load_gene_list(tested_gene_file_name)
else:
tested_gene_list = tested_gene_file_name
if not os.path.exists(
os.path.join(constants.GO_DIR, constants.GO_FILE_NAME)):
download(constants.GO_OBO_URL, constants.GO_DIR)
obo_dag = GODag(os.path.join(constants.GO_DIR, constants.GO_FILE_NAME))
if not os.path.exists(
os.path.join(constants.GO_DIR,
constants.GO_ASSOCIATION_FILE_NAME)):
download(constants.GO_ASSOCIATION_GENE2GEO_URL, constants.GO_DIR)
with gzip.open(
os.path.join(
constants.GO_DIR,
os.path.basename(constants.GO_ASSOCIATION_GENE2GEO_URL)),
'rb') as f_in:
with open(
os.path.join(constants.GO_DIR,
constants.GO_ASSOCIATION_FILE_NAME),
'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
assoc = read_ncbi_gene2go(os.path.join(constants.GO_DIR,
constants.GO_ASSOCIATION_FILE_NAME),
no_top=True)
sw = Stopwatch()
sw.start()
g = GOEnrichmentStudy(
[int(cur) for cur in ensembl2entrez_convertor(total_gene_list)],
assoc,
obo_dag,
methods=[],
log=None) # "bonferroni", "fdr_bh"
g_res = g.run_study(
[int(cur) for cur in ensembl2entrez_convertor(tested_gene_list)])
print sw.stop("done GO analysis in ")
# GO_results = [(cur.NS, cur.GO, cur.goterm.name, cur.pop_count, cur.p_uncorrected, cur.p_fdr_bh) for cur in g_res if
# cur.p_fdr_bh <= 0.05]
GO_results = [(cur.NS, cur.GO, cur.goterm.name, cur.pop_count,
cur.p_uncorrected) for cur in g_res
if cur.p_uncorrected <= th]
hg_report = [{
HG_GO_ROOT: cur[0],
HG_GO_ID: cur[1],
HG_GO_NAME: cur[2],
HG_VALUE: cur[3],
HG_PVAL: cur[4],
HG_QVAL: 1
} for cur in GO_results] # , HG_QVAL : cur[5]
# hg_report.sort(key=lambda x: x[HG_QVAL])
hg_report.sort(key=lambda x: x[HG_PVAL])
if len(GO_results) > 0:
go_ns, go_terms, go_names, go_hg_value, uncorrectd_pvals = zip(
*GO_results) # , FDRs
else:
go_terms = []
uncorrectd_pvals = []
FDRs = []
go_names = []
go_ns = []
# output_rows = [("\r\n".join(e2g_convertor(tested_gene_list)), "\r\n".join(go_ns),
# "\r\n".join(go_terms), "\r\n".join(go_names), "\r\n".join(map(str, uncorrectd_pvals)),
# "\r\n".join(map(str, FDRs)))]
# print_to_excel(output_rows, str(tested_gene_file_name)[:10], str(total_gene_file_name)[:10])
return hg_report