From c33f2ad04667fd21fce6ec8eefa3694e2209a852 Mon Sep 17 00:00:00 2001
From: Niko <nikolaos.papadopoulos@univie.ac.at>
Date: Wed, 27 Nov 2024 20:45:06 +0100
Subject: [PATCH] now running on cluster
---
08-submission/gff-02-functional_annot.ipynb | 29 ++++++++-------------
1 file changed, 11 insertions(+), 18 deletions(-)
diff --git a/08-submission/gff-02-functional_annot.ipynb b/08-submission/gff-02-functional_annot.ipynb
index 1ab90de..c26e7eb 100644
--- a/08-submission/gff-02-functional_annot.ipynb
+++ b/08-submission/gff-02-functional_annot.ipynb
@@ -14,7 +14,7 @@
"metadata": {},
"outputs": [],
"source": [
- "from tqdm import tqdm\n",
+ "# from tqdm import tqdm # install it for nice progress bars\n",
"\n",
"import pandas as pd"
]
@@ -118,11 +118,11 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
- "best_per_gene = '/Users/npapadop/Documents/data/pycnogonum/draft/out.emapper.best.annotations'\n",
+ "best_per_gene = '/lisc/scratch/zoology/pycnogonum/genome/draft/annot_merge/emapper/out.emapper.best.annotations'\n",
"emapper = pd.read_csv(best_per_gene, sep='\\t', header=0)\n",
"\n",
"emapper['gene'] = emapper['#query'].apply(parse_gene_id)\n",
@@ -148,26 +148,19 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 7,
"metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "100%|██████████| 779251/779251 [00:04<00:00, 183551.40it/s]\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
- "gff_loc = '/Volumes/scratch/pycnogonum/genome/submission/merged_sorted.gff3'\n",
- "named_loc = '/Volumes/scratch/pycnogonum/genome/submission/merged_sorted_named.gff3'\n",
+ "gff_loc = '/lisc/scratch/zoology/pycnogonum/genome/submission/merged_sorted.gff3'\n",
+ "named_loc = '/lisc/scratch/zoology/pycnogonum/genome/submission/merged_sorted_named.gff3'\n",
"\n",
"with open(gff_loc, 'r') as gff:\n",
" with open(named_loc, 'w') as named:\n",
" gene = ''\n",
" mRNA = ''\n",
- " for line in tqdm(gff.readlines()):\n",
+ " # for line in tqdm(gff.readlines()):\n",
+ " for line in gff.readlines():\n",
" line = line.strip()\n",
" conditions_skip = line.startswith('#') or 'tRNA' in line or 'name=' in line\n",
" if not conditions_skip:\n",
@@ -190,7 +183,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "ascc24",
+ "display_name": "jupyterhub-5.1.0",
"language": "python",
"name": "python3"
},
@@ -204,7 +197,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.19"
+ "version": "3.12.4"
}
},
"nbformat": 4,
--
GitLab