{
"cells": [
{
"cell_type": "markdown",
"id": "b84b0de9",
"metadata": {},
"source": [
"# Rule-Based Model Example\n",
"\n",
"Inspect biological labels derived from learned rule cutoffs before HMM segmentation.\n",
"\n",
"This example loads a packaged saved model so that the focus stays on the demonstrated operation."
]
},
{
"cell_type": "markdown",
"id": "4e3f108f",
"metadata": {},
"source": [
"## Parameters\n",
"\n",
"Change these explicit values for your own data or output location."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9c0d4ba7",
"metadata": {},
"outputs": [],
"source": [
"from pathlib import Path\n",
"\n",
"from methylseg import MethylSegPathway, MethylStateAssignmentMethod, MethylationStates\n",
"from methylseg.helper_classes import DATA_DIR"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "05534bea",
"metadata": {},
"outputs": [],
"source": [
"REFERENCE_DIR = DATA_DIR / \"reference_files\"\n",
"OUTPUT_ROOT = Path(\"out\")\n",
"CHROM = \"chr1\"\n",
"\n",
"RESOLUTION = \"450k\"\n",
"SAMPLE_NAME = \"TCGA-BD-A3EP-01A\"\n",
"SAMPLE_FILE = REFERENCE_DIR / \"TCGA-BD-A3EP-01A_450k.tsv.gz\"\n",
"OUT_DIR = OUTPUT_ROOT / \"rule_based_model_example\""
]
},
{
"cell_type": "markdown",
"id": "5f85b923",
"metadata": {},
"source": [
"## Load a saved model and prepare the sample"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "dfdd1720",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'TCGA-BD-A3EP-01A'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = MethylSegPathway.get_pretrained_model(\n",
" out_dir=OUT_DIR,\n",
" resolution=RESOLUTION,\n",
")\n",
"sample_info, removed_df = MethylSegPathway.prepare_sample_info(\n",
" sample_name=SAMPLE_NAME,\n",
" sample_file=SAMPLE_FILE,\n",
" resolution=RESOLUTION,\n",
" min_coverage=10,\n",
")\n",
"sample_info.sample_id"
]
},
{
"cell_type": "markdown",
"id": "1f883f32",
"metadata": {},
"source": [
"## Rule-based labels and HMM regions"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5a5090c1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"PMD:\n",
"0.158 <= beta <= 0.743\n",
"AND (40kb_int_pct >= 0.616 AND 40kb_std <= 0.290 AND 40kb_high_pct <= 0.374 AND 40kb_low_pct <= 0.376) OR (450kb_int_pct >= 0.596 AND 450kb_std <= 0.199 AND 450kb_high_pct <= 0.208 AND 450kb_low_pct <= 0.249)\n",
"\n",
"Low methylation:\n",
"beta <= 0.158 AND NOT PMD\n",
"\n",
"Intermediate methylation:\n",
"0.158 < beta < 0.743 AND NOT PMD\n",
"\n",
"High methylation:\n",
"beta >= 0.743 AND NOT PMD\n",
"\n"
]
},
{
"data": {
"text/html": [
" \n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" \n",
"