{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Structural variation in the IGH region\n",
    "\n",
    "Here we visualize PacBio HiFi long-read sequencing data in the [immunoglobulin heavy chain (IGH)](https://www.ncbi.nlm.nih.gov/gene?Db=gene&Cmd=DetailsSearch&Term=3492) region, with [GENCODE](https://www.gencodegenes.org/) gene annotations. The sequencing data was generated from the HG002 individual from the [Genome in a Bottle](https://www.nist.gov/programs-projects/genome-bottle) cohort. \n",
    "\n",
    "Data sources:\n",
    "- PacBio HiFi sequencing: [URL](ftp://ftp-trace.ncbi.nlm.nih.gov/ReferenceSamples/giab/data/AshkenazimTrio/HG002_NA24385_son/PacBio_CCS_15kb_20kb_chemistry2/GRCh38/HG002.SequelII.merged_15kb_20kb.pbmm2.GRCh38.haplotag.10x.bam)\n",
    "- Gene annotation: [URL](https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_41/gencode.v41.annotation.gtf.gz)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gzip\n",
    "import lakeview as lv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'gzip' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 9\u001b[0m\n\u001b[1;32m      6\u001b[0m GENCODE_GTF_PATH \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m../../tests/data/gencode.v40.annotation.gtf.gz\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m      7\u001b[0m PACBIO_BAM_PATH \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m../../tests/data/HG002_IGH_PacBio_CCS.bam\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m----> 9\u001b[0m \u001b[39mwith\u001b[39;00m gzip\u001b[39m.\u001b[39mopen(GENCODE_GTF_PATH, \u001b[39m\"\u001b[39m\u001b[39mrt\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mas\u001b[39;00m f:\n\u001b[1;32m     10\u001b[0m     gencode_painter \u001b[39m=\u001b[39m lv\u001b[39m.\u001b[39mGeneAnnotation\u001b[39m.\u001b[39mfrom_gencode(\n\u001b[1;32m     11\u001b[0m         f, \u001b[39m\"\u001b[39m\u001b[39mgtf\u001b[39m\u001b[39m\"\u001b[39m, region\u001b[39m=\u001b[39m(CHROMOSOME, (START, END))\n\u001b[1;32m     12\u001b[0m     )\n\u001b[1;32m     13\u001b[0m pacbio_painter \u001b[39m=\u001b[39m lv\u001b[39m.\u001b[39mSequenceAlignment\u001b[39m.\u001b[39mfrom_file(\n\u001b[1;32m     14\u001b[0m     PACBIO_BAM_PATH, region\u001b[39m=\u001b[39m(CHROMOSOME, (START, END))\n\u001b[1;32m     15\u001b[0m )\n",
      "\u001b[0;31mNameError\u001b[0m: name 'gzip' is not defined"
     ]
    }
   ],
   "source": [
    "CHROMOSOME = \"chr14\"\n",
    "VIEW_START = 105679000\n",
    "VIEW_END = 105776000\n",
    "START = VIEW_START - int(50e3)\n",
    "END = VIEW_END + int(50e3)\n",
    "GENCODE_GFF_PATH = \"../../tests/data/gencode.v43.annotation.gff3.gz\"\n",
    "PACBIO_BAM_PATH = \"../../tests/data/HG002_IGH_PacBio_CCS.bam\"\n",
    "\n",
    "with gzip.open(GENCODE_GFF_PATH, \"rt\") as f:\n",
    "    gencode_painter = lv.GeneAnnotation.from_gencode(\n",
    "        f, region=(CHROMOSOME, (START, END))\n",
    "    )\n",
    "pacbio_painter = lv.SequenceAlignment.from_file(\n",
    "    PACBIO_BAM_PATH, region=(CHROMOSOME, (START, END))\n",
    ")\n",
    "gv = lv.GenomeViewer(3, height_ratios=(1, 8, 2))\n",
    "pacbio_painter.draw_pileup(\n",
    "    gv.axes[0],\n",
    "    show_mismatches=False,\n",
    ")\n",
    "pacbio_painter.draw_alignment(\n",
    "    gv.axes[1],\n",
    "    show_mismatches=False,\n",
    "    sort_by=\"length\",\n",
    "    link_by=\"name\",\n",
    "    max_rows=50,\n",
    ")\n",
    "gencode_painter.draw_transcripts(gv.axes[2], max_rows=5, sort_by=\"length\")\n",
    "\n",
    "gv.set_xlim((VIEW_START, VIEW_END))\n",
    "gv.set_xlabel(CHROMOSOME)\n",
    "gv.set_title(\"PacBio HiFi long-read sequencing\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GenomeViewer(figure=<Figure size 1000x1000 with 3 Axes>)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.16"
  },
  "vscode": {
   "interpreter": {
    "hash": "9ac03a0a6051494cc606d484d27d20fce22fb7b4d169f583271e11d5ba46a56e"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}