further cleanups, addition of analysis of reduced variants

Author: mdiberna

.gitignore

@@ -15,4 +15,5 @@ notebooks/**/
 
 # script outputs
 scripts/out
-scripts/results
+scripts/results
+scripts/results_reduced

notebooks/bed_cleanup.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,6 +12,13 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Full bed file"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -78,6 +85,80 @@
     "    for gene in gene_list:\n",
     "        f.write(gene + \"\\n\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Reduced bed file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input_bed = \"../data/ribosome_profiling/selected_truncations_JL.bed\"\n",
+    "output_bed = \"../data/ribosome_profiling/selected_truncations_JL_cleaned.bed\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fetching Ensembl reference data...\n",
+      "Retrieved 48379 mappings\n",
+      "\n",
+      "Cleanup Summary:\n",
+      "  Total entries: 28\n",
+      "  Invalid entries removed: 0\n",
+      "  Duplicates removed: 0\n",
+      "  Gene names updated: 2\n",
+      "  Valid entries in final file: 28\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'total': 28,\n",
+       " 'invalid_format': 0,\n",
+       " 'invalid_ensembl': 0,\n",
+       " 'duplicates': 0,\n",
+       " 'updated': 2,\n",
+       " 'valid': 28}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cleanup_bed(input_bed, output_bed, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "alt_isoforms = AlternativeIsoform()\n",
+    "alt_isoforms.load_bed(\n",
+    "    \"../data/ribosome_profiling/selected_truncations_JL_cleaned.bed\"\n",
+    ")\n",
+    "gene_list = alt_isoforms.get_gene_list()\n",
+    "\n",
+    "with open(\"../data/ribosome_profiling/gene_list_reduced.txt\", \"w\") as f:\n",
+    "    for gene in gene_list:\n",
+    "        f.write(gene + \"\\n\")"
+   ]
   }
  ],
  "metadata": {

scripts/analyze_truncations.sh renamed to scripts/analyze_truncations_full.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+#SBATCH --job-name=truncations          # Job name
+#SBATCH --partition=20                  # Partition name
+#SBATCH --ntasks=1                      # Run a single task
+#SBATCH --cpus-per-task=12              # Single CPU for the controller job
+#SBATCH --mem=12G                       # Memory for the controller job
+#SBATCH --time=24:00:00                 # Time limit (hrs:min:sec)
+#SBATCH --output=out/truncations-%j.out     # Standard output log
+
+# Activate conda environment (adjust path as needed)
+source ~/.bashrc
+conda activate swissisoform
+
+# Run the truncations script
+mkdir -p results_reduced
+
+# Run the analysis script
+python3 analyze_truncations.py '../data/ribosome_profiling/gene_list_reduced.txt' 'results_reduced'