updating script

notebooks/gtdb.ipynb

@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -62,21 +62,22 @@
     "metadata_subset_df.append(metadata_df.drop_duplicates(subset='phylum', keep='first'))\n",
     "\n",
     "metadata_subset_df = pd.concat(metadata_subset_df)\n",
+    "metadata_subset_df['prefix'] = [genome_id[:2] for genome_id in metadata_subset_df.genome_id] \n",
     "metadata_subset_df.genome_id = [genome_id.replace('GB_', '').replace('RS_', '') for genome_id in metadata_subset_df.genome_id] # Remove the prefixes from the genome IDs. \n",
     "metadata_subset_df.set_index('genome_id').to_csv('../data/gtdb_subset.csv')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Generate a shell script to run on HPC to extract all genomes, proteins, and annotations from the complete GTDB directories to subset directories. \n",
     "script_path = '../scripts/bash/move-gtdb-subset-files.sh'\n",
     "with open(script_path, 'w') as f:\n",
-    "    for genome_id in metadata_subset_df.genome_id:\n",
-    "        cmd = f'grep -l {genome_id} ./gtdb_genomes/* | while read file_name; do mv \"$file_name\" ./gtdb_subset_genomes/; done'\n",
+    "    for row in metadata_subset_df.itertuples():\n",
+    "        cmd = f'mv ./gtdb_genomes/{row.prefix}_{row.genome_id}_genomic.fna.gz -t ./gtdb_subset_genomes/'\n",
     "        # f.write(cmd + '\\n')\n",
     "        # cmd = f'grep -l {genome_id} ./gtdb_proteins/ | while read file_name; do mv \"$file_name\" ./gtdb_subset_proteins/; done'\n",
     "        # f.write(cmd + '\\n')\n",