From aa0a40fd8cccd19877488da18a7029673bc339d4 Mon Sep 17 00:00:00 2001
From: Niko <nikolaos.papadopoulos@univie.ac.at>
Date: Wed, 4 Dec 2024 17:32:24 +0100
Subject: [PATCH] adding more information to GFF and EMBL file
---
08-submission/gff-02-functional_annot.ipynb | 66 +++++++++++++++++++++
08-submission/gff-04-convert_to_embl.sh | 4 +-
2 files changed, 69 insertions(+), 1 deletion(-)
diff --git a/08-submission/gff-02-functional_annot.ipynb b/08-submission/gff-02-functional_annot.ipynb
index 590383e..dd80c03 100644
--- a/08-submission/gff-02-functional_annot.ipynb
+++ b/08-submission/gff-02-functional_annot.ipynb
@@ -136,6 +136,55 @@
" return None"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def find_EC(gene_id, lookup): # expects a protein-coding gene as input\n",
+ " \"\"\"Retrieve the EC number assigned by EggNOG-mapper for a certain gene ID.\n",
+ "\n",
+ " Parameters\n",
+ " ----------\n",
+ " gene_id : str\n",
+ " a P. litorale protein-coding gene ID\n",
+ " lookup : pd.DataFrame\n",
+ " the eggNOG-mapper output file, filtered to maximum one entry per gene ID\n",
+ "\n",
+ " Returns\n",
+ " -------\n",
+ " str\n",
+ " the EC number (if available) for the current gene (product).\n",
+ " \"\"\"\n",
+ " if gene_id in lookup.index:\n",
+ " ec = lookup.loc[gene_id]['EC']\n",
+ " if ec != '-':\n",
+ " return ec.split(',')\n",
+ " return None\n",
+ "\n",
+ "def find_PFAMs(gene_id, lookup): # expects a protein-coding gene as input\n",
+ " \"\"\"Retrieve the PFAM domains assigned by EggNOG-mapper for a certain gene ID.\n",
+ "\n",
+ " Parameters\n",
+ " ----------\n",
+ " gene_id : str\n",
+ " a P. litorale protein-coding gene ID\n",
+ " lookup : pd.DataFrame\n",
+ " the eggNOG-mapper output file, filtered to maximum one entry per gene ID\n",
+ "\n",
+ " Returns\n",
+ " -------\n",
+ " list\n",
+ " a list of PFAM domains (if available) associated with the gene (product).\n",
+ " \"\"\"\n",
+ " if gene_id in lookup.index:\n",
+ " pfam = lookup.loc[gene_id]['PFAMs']\n",
+ " if pfam != '-':\n",
+ " return pfam.split(',')\n",
+ " return None"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -157,6 +206,15 @@
"emapper.set_index('gene', inplace=True)"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "emapper.columns"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -203,6 +261,8 @@
" name = find_protein(gene, emapper)\n",
" line = f'{line};gene={name}'\n",
" description = find_description(gene, emapper)\n",
+ " ec_list = find_EC(gene, emapper)\n",
+ " pfams = find_PFAMs(gene, emapper)\n",
" if description:\n",
" line = f'{line};function={description}'\n",
" if name != f'Uncharacterised protein {gene}' or description:\n",
@@ -223,6 +283,12 @@
" line = f'{line};function={description}'\n",
" if name != f'Uncharacterised protein {gene}' or description:\n",
" line = f'{line};note=function predicted by EggNOG-mapper'\n",
+ " if ec_list is not None:\n",
+ " for ec in ec_list:\n",
+ " line = f'{line};EC_number=\"{ec}\"'\n",
+ " if pfams is not None:\n",
+ " for pfam in pfams:\n",
+ " line = f'{line};Dbxref=\"PFAM:{pfam}\"'\n",
" named.write(line + '\\n')"
]
}
diff --git a/08-submission/gff-04-convert_to_embl.sh b/08-submission/gff-04-convert_to_embl.sh
index 4b39f04..05d8ce7 100644
--- a/08-submission/gff-04-convert_to_embl.sh
+++ b/08-submission/gff-04-convert_to_embl.sh
@@ -23,4 +23,6 @@ EMBLmyGFF3 $GFF $GENOME \
-v \
-o result.embl
-gzip result.embl
\ No newline at end of file
+# when zipping: overwrite file if it already exists,
+# else the command will hang while waiting for confirmation
+gzip -f result.embl
\ No newline at end of file
--
GitLab