{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9tcjtJ8cvaPv",
   "metadata": {
    "id": "9tcjtJ8cvaPv"
   },
   "source": [
    "# Query to get intergenic regions of a TARA sample in the OcéanIA Platform"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "yFdcX6L9vmkE",
   "metadata": {
    "id": "yFdcX6L9vmkE"
   },
   "source": [
    "### 1. Install oceania-query-fasta package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "55fdb172",
   "metadata": {
    "id": "55fdb172"
   },
   "outputs": [],
   "source": [
    "%pip install oceania-query-fasta\n",
    "%pip install openpyxl # required to load supplementary info into pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5bdf46f4-fbba-4df4-9450-d4e4ab1dc415",
   "metadata": {},
   "source": [
    "### 2. Load supplementary information for samples and data of Ocean Microbial Reference Gene Catalog v2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "42df4bb5-ac1c-4137-bfae-0e40596f9cc4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas\n",
    "\n",
    "SUPP_INFO_LINK = \"https://zenodo.org/record/3539258/files/Salazar_et_al_2019_Suppl_Info.xlsx?download=1\"\n",
    "\n",
    "table_W1 = pandas.read_excel(SUPP_INFO_LINK, sheet_name=\"Table_W1\")\n",
    "\n",
    "# Select first sample_id at the surface water layer\n",
    "selected_sample = table_W1[table_W1.Layer==\"SRF\"].head(1)\n",
    "print(selected_sample)\n",
    "\n",
    "sample_id = selected_sample[\"PANGAEA sample id\"].item()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25c31393-cfed-419b-b02e-b0b26ae01971",
   "metadata": {},
   "source": [
    "### 3. Get metadata for the first 10 intergenic regions of size greater than 100 for the selected sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f9effea1-ea3b-4cc5-a289-db95795c6eda",
   "metadata": {},
   "outputs": [],
   "source": [
    "from oceania import list_intergenic_regions\n",
    "\n",
    "intergenic_regions_metadata = list_intergenic_regions(sample_id, min_length=100, page=1, page_size=10)\n",
    "\n",
    "print(intergenic_regions_metadata)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ea0f4b3",
   "metadata": {},
   "source": [
    "### 4. Prepare request params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4132badf",
   "metadata": {},
   "outputs": [],
   "source": [
    "request_regions = intergenic_regions_metadata[['sequence', 'start', 'stop']].copy()\n",
    "request_params = []\n",
    "for row in request_regions.itertuples():\n",
    "    request_params.append(\n",
    "        (row[1], int(row[2]), int(row[3]))\n",
    "    )\n",
    "\n",
    "print(request_params)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0159d5e7",
   "metadata": {},
   "source": [
    "### 5. Perform call to the OcéanIA services"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6344f9c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from oceania import get_sequences_from_fasta\n",
    "\n",
    "request_result = get_sequences_from_fasta(\n",
    "    sample_id,\n",
    "    request_params\n",
    ")\n",
    "\n",
    "# request_result is loaded as a pandas.DataFrame\n",
    "print(request_result)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Copia de query_dependecy.ipynb",
   "provenance": [
    {
     "file_id": "https://github.com/Inria-Chile/oceania-lib-demo/blob/main/notebooks/query_dependecy.ipynb",
     "timestamp": 1623342428289
    }
   ]
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}