diff --git a/docs/ingest/gene-ensembl-release-110.ipynb b/docs/ingest/gene-ensembl-release-110.ipynb
new file mode 100644
index 0000000..ce16857
--- /dev/null
+++ b/docs/ingest/gene-ensembl-release-110.ipynb
@@ -0,0 +1,1648 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# `Gene`: ensembl, release-110"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- https://www.ensembl.org/info/data/mysql.html\n",
+    "- https://www.ensembl.org/info/docs/api/core/core_schema.html"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install mysqlclient: https://pypi.org/project/mysqlclient/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ New records found in the public sources.yaml, updated /Users/sunnysun/.lamin/bionty/versions/sources_local.yaml!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from sqlalchemy import create_engine\n",
+    "import mysql.connector as sql  # needed\n",
+    "import bionty as bt\n",
+    "\n",
+    "version = \"release-110\"\n",
+    "species = bt.Species(version=version).lookup()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_url(species: bt.Species):\n",
+    "    return f\"mysql+mysqldb://anonymous:@ensembldb.ensembl.org/{species.core_db}\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_core = \"\"\"\n",
+    "SELECT gene.stable_id, xref.display_label, gene.biotype, gene.description, external_synonym.synonym\n",
+    "FROM gene\n",
+    "LEFT JOIN xref ON gene.display_xref_id = xref.xref_id\n",
+    "LEFT JOIN external_synonym ON gene.display_xref_id = external_synonym.xref_id\n",
+    "\"\"\"\n",
+    "\n",
+    "query_external = \"\"\"\n",
+    "SELECT gene.stable_id, object_xref.xref_id, xref.dbprimary_acc, external_db.db_name\n",
+    "FROM gene\n",
+    "LEFT JOIN object_xref ON gene.gene_id = object_xref.ensembl_id\n",
+    "LEFT JOIN xref ON object_xref.xref_id = xref.xref_id\n",
+    "LEFT JOIN external_db ON xref.external_db_id = external_db.external_db_id\n",
+    "WHERE object_xref.ensembl_object_type = 'Gene' AND external_db.db_name IN ('EntrezGene')\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_genes_df(species: bt.Species, version=\"release-110\"):\n",
+    "    engine = create_engine(url=get_url(species=species))\n",
+    "\n",
+    "    # Query for the basic gene annotations:\n",
+    "    results_core = pd.read_sql(query_core, con=engine)\n",
+    "    print(f\"result_core.shape: {results_core.shape}\")\n",
+    "    print(f\"result_core.head():\\n\")\n",
+    "    display(results_core.head())\n",
+    "\n",
+    "    # aggregate metadata based on ensembl stable_id\n",
+    "    results_core_group = results_core.groupby(\"stable_id\").agg(\n",
+    "        {\n",
+    "            \"display_label\": \"first\",\n",
+    "            \"biotype\": \"first\",\n",
+    "            \"description\": \"first\",\n",
+    "            \"synonym\": lambda x: \"|\".join([i for i in set(x) if i is not None]),\n",
+    "        }\n",
+    "    )\n",
+    "    print(f\"results_core_group.head():\\n\")\n",
+    "    display(results_core_group.head())\n",
+    "\n",
+    "    # Query for external ids:\n",
+    "    results_external = pd.read_sql(query_external, con=engine)\n",
+    "    results_external = results_external[\n",
+    "        results_external.stable_id.str.startswith(\"ENS\")\n",
+    "    ]\n",
+    "    print(f\"results_external.shape: {results_external.shape}\")\n",
+    "    print(f\"results_external.head():\\n\")\n",
+    "    display(results_external.head())\n",
+    "\n",
+    "    # ncbi_gene_id\n",
+    "    entrez = (\n",
+    "        results_external[results_external[\"db_name\"] == \"EntrezGene\"]\n",
+    "        .drop_duplicates([\"stable_id\", \"dbprimary_acc\"])\n",
+    "        .drop(columns=[\"xref_id\", \"db_name\"])\n",
+    "    )\n",
+    "    entrez.rename(columns={\"dbprimary_acc\": \"ncbi_gene_id\"}, inplace=True)\n",
+    "    entrez = entrez.set_index(\"stable_id\")\n",
+    "    dup = entrez[entrez.index.duplicated(keep=False)]\n",
+    "    print(f\"duplicated ensembl_gene_ids with ncbi_gene_ids: {dup.shape[0]}\\n\")\n",
+    "    display(dup.head())\n",
+    "\n",
+    "    # merge with ncbi_gene_id\n",
+    "    df = results_core_group.merge(\n",
+    "        entrez, left_index=True, right_index=True, how=\"outer\"\n",
+    "    )\n",
+    "    df = df.reset_index()\n",
+    "    df.rename(\n",
+    "        columns={\n",
+    "            \"stable_id\": \"ensembl_gene_id\",\n",
+    "            \"display_label\": \"symbol\",\n",
+    "            \"synonym\": \"synonyms\",\n",
+    "        },\n",
+    "        inplace=True,\n",
+    "    )\n",
+    "    df = df[\n",
+    "        [\n",
+    "            \"ensembl_gene_id\",\n",
+    "            \"symbol\",\n",
+    "            \"ncbi_gene_id\",\n",
+    "            \"biotype\",\n",
+    "            \"description\",\n",
+    "            \"synonyms\",\n",
+    "        ]\n",
+    "    ]\n",
+    "    df = df[~df[\"ensembl_gene_id\"].isnull()]\n",
+    "    df = df.sort_values(\"ensembl_gene_id\").reset_index(drop=True)\n",
+    "    print(f\"Final df.shape: {df.shape}\")\n",
+    "    print(f\"df.head():\\n\")\n",
+    "    display(df.head())\n",
+    "\n",
+    "    # save to parquet\n",
+    "    filename = f\"df_{species.name}__ensembl__{version}__Gene.parquet\"\n",
+    "    df.to_parquet(filename)\n",
+    "    print(f\"Saved as {filename}\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Human"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "result_core.shape: (113336, 5)\n",
+      "result_core.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSG00000210049</td>\n",
+       "      <td>MT-TF</td>\n",
+       "      <td>Mt_tRNA</td>\n",
+       "      <td>mitochondrially encoded tRNA-Phe (UUU/C) [Sour...</td>\n",
+       "      <td>MTTF</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSG00000210049</td>\n",
+       "      <td>MT-TF</td>\n",
+       "      <td>Mt_tRNA</td>\n",
+       "      <td>mitochondrially encoded tRNA-Phe (UUU/C) [Sour...</td>\n",
+       "      <td>TRNF</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSG00000211459</td>\n",
+       "      <td>MT-RNR1</td>\n",
+       "      <td>Mt_rRNA</td>\n",
+       "      <td>mitochondrially encoded 12S rRNA [Source:HGNC ...</td>\n",
+       "      <td>12S</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSG00000211459</td>\n",
+       "      <td>MT-RNR1</td>\n",
+       "      <td>Mt_rRNA</td>\n",
+       "      <td>mitochondrially encoded 12S rRNA [Source:HGNC ...</td>\n",
+       "      <td>MOTS-C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSG00000211459</td>\n",
+       "      <td>MT-RNR1</td>\n",
+       "      <td>Mt_rRNA</td>\n",
+       "      <td>mitochondrially encoded 12S rRNA [Source:HGNC ...</td>\n",
+       "      <td>MTRNR1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         stable_id display_label  biotype  \\\n",
+       "0  ENSG00000210049         MT-TF  Mt_tRNA   \n",
+       "1  ENSG00000210049         MT-TF  Mt_tRNA   \n",
+       "2  ENSG00000211459       MT-RNR1  Mt_rRNA   \n",
+       "3  ENSG00000211459       MT-RNR1  Mt_rRNA   \n",
+       "4  ENSG00000211459       MT-RNR1  Mt_rRNA   \n",
+       "\n",
+       "                                         description synonym  \n",
+       "0  mitochondrially encoded tRNA-Phe (UUU/C) [Sour...    MTTF  \n",
+       "1  mitochondrially encoded tRNA-Phe (UUU/C) [Sour...    TRNF  \n",
+       "2  mitochondrially encoded 12S rRNA [Source:HGNC ...     12S  \n",
+       "3  mitochondrially encoded 12S rRNA [Source:HGNC ...  MOTS-C  \n",
+       "4  mitochondrially encoded 12S rRNA [Source:HGNC ...  MTRNR1  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_core_group.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000000003</th>\n",
+       "      <td>TSPAN6</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>tetraspanin 6 [Source:HGNC Symbol;Acc:HGNC:11858]</td>\n",
+       "      <td>TM4SF6|T245|TSPAN-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000000005</th>\n",
+       "      <td>TNMD</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>tenomodulin [Source:HGNC Symbol;Acc:HGNC:17757]</td>\n",
+       "      <td>TEM|MYODULIN|CHM1L|TENDIN|BRICD4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000000419</th>\n",
+       "      <td>DPM1</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>dolichyl-phosphate mannosyltransferase subunit...</td>\n",
+       "      <td>CDGIE|MPDS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000000457</th>\n",
+       "      <td>SCYL3</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>SCY1 like pseudokinase 3 [Source:HGNC Symbol;A...</td>\n",
+       "      <td>PACE-1|PACE1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000000460</th>\n",
+       "      <td>C1orf112</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>chromosome 1 open reading frame 112 [Source:HG...</td>\n",
+       "      <td>FLJ10706|APOLO1|FLIP</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                display_label         biotype  \\\n",
+       "stable_id                                       \n",
+       "ENSG00000000003        TSPAN6  protein_coding   \n",
+       "ENSG00000000005          TNMD  protein_coding   \n",
+       "ENSG00000000419          DPM1  protein_coding   \n",
+       "ENSG00000000457         SCYL3  protein_coding   \n",
+       "ENSG00000000460      C1orf112  protein_coding   \n",
+       "\n",
+       "                                                       description  \\\n",
+       "stable_id                                                            \n",
+       "ENSG00000000003  tetraspanin 6 [Source:HGNC Symbol;Acc:HGNC:11858]   \n",
+       "ENSG00000000005    tenomodulin [Source:HGNC Symbol;Acc:HGNC:17757]   \n",
+       "ENSG00000000419  dolichyl-phosphate mannosyltransferase subunit...   \n",
+       "ENSG00000000457  SCY1 like pseudokinase 3 [Source:HGNC Symbol;A...   \n",
+       "ENSG00000000460  chromosome 1 open reading frame 112 [Source:HG...   \n",
+       "\n",
+       "                                          synonym  \n",
+       "stable_id                                          \n",
+       "ENSG00000000003               TM4SF6|T245|TSPAN-6  \n",
+       "ENSG00000000005  TEM|MYODULIN|CHM1L|TENDIN|BRICD4  \n",
+       "ENSG00000000419                        CDGIE|MPDS  \n",
+       "ENSG00000000457                      PACE-1|PACE1  \n",
+       "ENSG00000000460              FLJ10706|APOLO1|FLIP  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_external.shape: (36004, 4)\n",
+      "results_external.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>xref_id</th>\n",
+       "      <th>dbprimary_acc</th>\n",
+       "      <th>db_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSG00000198888</td>\n",
+       "      <td>554032</td>\n",
+       "      <td>4535</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSG00000198763</td>\n",
+       "      <td>554045</td>\n",
+       "      <td>4536</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSG00000198804</td>\n",
+       "      <td>553814</td>\n",
+       "      <td>4512</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSG00000210151</td>\n",
+       "      <td>1138145</td>\n",
+       "      <td>113219467</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSG00000198712</td>\n",
+       "      <td>553829</td>\n",
+       "      <td>4513</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         stable_id  xref_id dbprimary_acc     db_name\n",
+       "0  ENSG00000198888   554032          4535  EntrezGene\n",
+       "1  ENSG00000198763   554045          4536  EntrezGene\n",
+       "2  ENSG00000198804   553814          4512  EntrezGene\n",
+       "3  ENSG00000210151  1138145     113219467  EntrezGene\n",
+       "4  ENSG00000198712   553829          4513  EntrezGene"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "duplicated ensembl_gene_ids with ncbi_gene_ids: 6158\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000278294</th>\n",
+       "      <td>124907156</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000278294</th>\n",
+       "      <td>124907485</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000278294</th>\n",
+       "      <td>124908250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000274917</th>\n",
+       "      <td>100008587</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSG00000274917</th>\n",
+       "      <td>124907114</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                ncbi_gene_id\n",
+       "stable_id                   \n",
+       "ENSG00000278294    124907156\n",
+       "ENSG00000278294    124907485\n",
+       "ENSG00000278294    124908250\n",
+       "ENSG00000274917    100008587\n",
+       "ENSG00000274917    124907114"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Final df.shape: (77043, 6)\n",
+      "df.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ensembl_gene_id</th>\n",
+       "      <th>symbol</th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonyms</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSG00000000003</td>\n",
+       "      <td>TSPAN6</td>\n",
+       "      <td>7105</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>tetraspanin 6 [Source:HGNC Symbol;Acc:HGNC:11858]</td>\n",
+       "      <td>TM4SF6|T245|TSPAN-6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSG00000000005</td>\n",
+       "      <td>TNMD</td>\n",
+       "      <td>64102</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>tenomodulin [Source:HGNC Symbol;Acc:HGNC:17757]</td>\n",
+       "      <td>TEM|MYODULIN|CHM1L|TENDIN|BRICD4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSG00000000419</td>\n",
+       "      <td>DPM1</td>\n",
+       "      <td>8813</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>dolichyl-phosphate mannosyltransferase subunit...</td>\n",
+       "      <td>CDGIE|MPDS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSG00000000457</td>\n",
+       "      <td>SCYL3</td>\n",
+       "      <td>57147</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>SCY1 like pseudokinase 3 [Source:HGNC Symbol;A...</td>\n",
+       "      <td>PACE-1|PACE1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSG00000000460</td>\n",
+       "      <td>C1orf112</td>\n",
+       "      <td>55732</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>chromosome 1 open reading frame 112 [Source:HG...</td>\n",
+       "      <td>FLJ10706|APOLO1|FLIP</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   ensembl_gene_id    symbol ncbi_gene_id         biotype  \\\n",
+       "0  ENSG00000000003    TSPAN6         7105  protein_coding   \n",
+       "1  ENSG00000000005      TNMD        64102  protein_coding   \n",
+       "2  ENSG00000000419      DPM1         8813  protein_coding   \n",
+       "3  ENSG00000000457     SCYL3        57147  protein_coding   \n",
+       "4  ENSG00000000460  C1orf112        55732  protein_coding   \n",
+       "\n",
+       "                                         description  \\\n",
+       "0  tetraspanin 6 [Source:HGNC Symbol;Acc:HGNC:11858]   \n",
+       "1    tenomodulin [Source:HGNC Symbol;Acc:HGNC:17757]   \n",
+       "2  dolichyl-phosphate mannosyltransferase subunit...   \n",
+       "3  SCY1 like pseudokinase 3 [Source:HGNC Symbol;A...   \n",
+       "4  chromosome 1 open reading frame 112 [Source:HG...   \n",
+       "\n",
+       "                           synonyms  \n",
+       "0               TM4SF6|T245|TSPAN-6  \n",
+       "1  TEM|MYODULIN|CHM1L|TENDIN|BRICD4  \n",
+       "2                        CDGIE|MPDS  \n",
+       "3                      PACE-1|PACE1  \n",
+       "4              FLJ10706|APOLO1|FLIP  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved as df_human__ensembl__release-110__Gene.parquet\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_genes_df(species=species.human)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Mouse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "result_core.shape: (84751, 5)\n",
+      "result_core.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSMUSG00000064336</td>\n",
+       "      <td>mt-Tf</td>\n",
+       "      <td>Mt_tRNA</td>\n",
+       "      <td>mitochondrially encoded tRNA phenylalanine [So...</td>\n",
+       "      <td>tRNA</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSMUSG00000064336</td>\n",
+       "      <td>mt-Tf</td>\n",
+       "      <td>Mt_tRNA</td>\n",
+       "      <td>mitochondrially encoded tRNA phenylalanine [So...</td>\n",
+       "      <td>tRNA-Phe</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSMUSG00000064336</td>\n",
+       "      <td>mt-Tf</td>\n",
+       "      <td>Mt_tRNA</td>\n",
+       "      <td>mitochondrially encoded tRNA phenylalanine [So...</td>\n",
+       "      <td>TrnF tRNA</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSMUSG00000064337</td>\n",
+       "      <td>mt-Rnr1</td>\n",
+       "      <td>Mt_rRNA</td>\n",
+       "      <td>mitochondrially encoded 12S rRNA [Source:MGI S...</td>\n",
+       "      <td>12S ribosomal RNA</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSMUSG00000064337</td>\n",
+       "      <td>mt-Rnr1</td>\n",
+       "      <td>Mt_rRNA</td>\n",
+       "      <td>mitochondrially encoded 12S rRNA [Source:MGI S...</td>\n",
+       "      <td>12S rRNA</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            stable_id display_label  biotype  \\\n",
+       "0  ENSMUSG00000064336         mt-Tf  Mt_tRNA   \n",
+       "1  ENSMUSG00000064336         mt-Tf  Mt_tRNA   \n",
+       "2  ENSMUSG00000064336         mt-Tf  Mt_tRNA   \n",
+       "3  ENSMUSG00000064337       mt-Rnr1  Mt_rRNA   \n",
+       "4  ENSMUSG00000064337       mt-Rnr1  Mt_rRNA   \n",
+       "\n",
+       "                                         description            synonym  \n",
+       "0  mitochondrially encoded tRNA phenylalanine [So...               tRNA  \n",
+       "1  mitochondrially encoded tRNA phenylalanine [So...           tRNA-Phe  \n",
+       "2  mitochondrially encoded tRNA phenylalanine [So...          TrnF tRNA  \n",
+       "3  mitochondrially encoded 12S rRNA [Source:MGI S...  12S ribosomal RNA  \n",
+       "4  mitochondrially encoded 12S rRNA [Source:MGI S...           12S rRNA  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_core_group.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000000001</th>\n",
+       "      <td>Gnai3</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>guanine nucleotide binding protein (G protein)...</td>\n",
+       "      <td>Galphai3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000000003</th>\n",
+       "      <td>Pbsn</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>probasin [Source:MGI Symbol;Acc:MGI:1860484]</td>\n",
+       "      <td>PB</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000000028</th>\n",
+       "      <td>Cdc45</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>cell division cycle 45 [Source:MGI Symbol;Acc:...</td>\n",
+       "      <td>Cdc45l</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000000031</th>\n",
+       "      <td>H19</td>\n",
+       "      <td>lncRNA</td>\n",
+       "      <td>H19, imprinted maternally expressed transcript...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000000037</th>\n",
+       "      <td>Scml2</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Scm polycomb group protein like 2 [Source:MGI ...</td>\n",
+       "      <td>4932420G07Rik</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   display_label         biotype  \\\n",
+       "stable_id                                          \n",
+       "ENSMUSG00000000001         Gnai3  protein_coding   \n",
+       "ENSMUSG00000000003          Pbsn  protein_coding   \n",
+       "ENSMUSG00000000028         Cdc45  protein_coding   \n",
+       "ENSMUSG00000000031           H19          lncRNA   \n",
+       "ENSMUSG00000000037         Scml2  protein_coding   \n",
+       "\n",
+       "                                                          description  \\\n",
+       "stable_id                                                               \n",
+       "ENSMUSG00000000001  guanine nucleotide binding protein (G protein)...   \n",
+       "ENSMUSG00000000003       probasin [Source:MGI Symbol;Acc:MGI:1860484]   \n",
+       "ENSMUSG00000000028  cell division cycle 45 [Source:MGI Symbol;Acc:...   \n",
+       "ENSMUSG00000000031  H19, imprinted maternally expressed transcript...   \n",
+       "ENSMUSG00000000037  Scm polycomb group protein like 2 [Source:MGI ...   \n",
+       "\n",
+       "                          synonym  \n",
+       "stable_id                          \n",
+       "ENSMUSG00000000001       Galphai3  \n",
+       "ENSMUSG00000000003             PB  \n",
+       "ENSMUSG00000000028         Cdc45l  \n",
+       "ENSMUSG00000000031                 \n",
+       "ENSMUSG00000000037  4932420G07Rik  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_external.shape: (27747, 4)\n",
+      "results_external.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>xref_id</th>\n",
+       "      <th>dbprimary_acc</th>\n",
+       "      <th>db_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSMUSG00000064341</td>\n",
+       "      <td>344016</td>\n",
+       "      <td>17716</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSMUSG00000064345</td>\n",
+       "      <td>344027</td>\n",
+       "      <td>17717</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSMUSG00000064351</td>\n",
+       "      <td>343950</td>\n",
+       "      <td>17708</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSMUSG00000064354</td>\n",
+       "      <td>343957</td>\n",
+       "      <td>17709</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSMUSG00000064356</td>\n",
+       "      <td>343940</td>\n",
+       "      <td>17706</td>\n",
+       "      <td>EntrezGene</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            stable_id  xref_id dbprimary_acc     db_name\n",
+       "0  ENSMUSG00000064341   344016         17716  EntrezGene\n",
+       "1  ENSMUSG00000064345   344027         17717  EntrezGene\n",
+       "2  ENSMUSG00000064351   343950         17708  EntrezGene\n",
+       "3  ENSMUSG00000064354   343957         17709  EntrezGene\n",
+       "4  ENSMUSG00000064356   343940         17706  EntrezGene"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "duplicated ensembl_gene_ids with ncbi_gene_ids: 554\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000094383</th>\n",
+       "      <td>108168683</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000094383</th>\n",
+       "      <td>108168684</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000094383</th>\n",
+       "      <td>108169098</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000094383</th>\n",
+       "      <td>108169101</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENSMUSG00000095634</th>\n",
+       "      <td>100039810</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   ncbi_gene_id\n",
+       "stable_id                      \n",
+       "ENSMUSG00000094383    108168683\n",
+       "ENSMUSG00000094383    108168684\n",
+       "ENSMUSG00000094383    108169098\n",
+       "ENSMUSG00000094383    108169101\n",
+       "ENSMUSG00000095634    100039810"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Final df.shape: (57283, 6)\n",
+      "df.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ensembl_gene_id</th>\n",
+       "      <th>symbol</th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonyms</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ENSMUSG00000000001</td>\n",
+       "      <td>Gnai3</td>\n",
+       "      <td>14679</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>guanine nucleotide binding protein (G protein)...</td>\n",
+       "      <td>Galphai3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ENSMUSG00000000003</td>\n",
+       "      <td>Pbsn</td>\n",
+       "      <td>54192</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>probasin [Source:MGI Symbol;Acc:MGI:1860484]</td>\n",
+       "      <td>PB</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ENSMUSG00000000028</td>\n",
+       "      <td>Cdc45</td>\n",
+       "      <td>12544</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>cell division cycle 45 [Source:MGI Symbol;Acc:...</td>\n",
+       "      <td>Cdc45l</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ENSMUSG00000000031</td>\n",
+       "      <td>H19</td>\n",
+       "      <td>14955</td>\n",
+       "      <td>lncRNA</td>\n",
+       "      <td>H19, imprinted maternally expressed transcript...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ENSMUSG00000000037</td>\n",
+       "      <td>Scml2</td>\n",
+       "      <td>107815</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Scm polycomb group protein like 2 [Source:MGI ...</td>\n",
+       "      <td>4932420G07Rik</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      ensembl_gene_id symbol ncbi_gene_id         biotype  \\\n",
+       "0  ENSMUSG00000000001  Gnai3        14679  protein_coding   \n",
+       "1  ENSMUSG00000000003   Pbsn        54192  protein_coding   \n",
+       "2  ENSMUSG00000000028  Cdc45        12544  protein_coding   \n",
+       "3  ENSMUSG00000000031    H19        14955          lncRNA   \n",
+       "4  ENSMUSG00000000037  Scml2       107815  protein_coding   \n",
+       "\n",
+       "                                         description       synonyms  \n",
+       "0  guanine nucleotide binding protein (G protein)...       Galphai3  \n",
+       "1       probasin [Source:MGI Symbol;Acc:MGI:1860484]             PB  \n",
+       "2  cell division cycle 45 [Source:MGI Symbol;Acc:...         Cdc45l  \n",
+       "3  H19, imprinted maternally expressed transcript...                 \n",
+       "4  Scm polycomb group protein like 2 [Source:MGI ...  4932420G07Rik  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved as df_mouse__ensembl__release-110__Gene.parquet\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_genes_df(species=species.mouse)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## saccharomyces_cerevisiae"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "result_core.shape: (8552, 5)\n",
+      "result_core.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>YBR024W</td>\n",
+       "      <td>SCO2</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Protein anchored to mitochondrial inner membra...</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>YDL245C</td>\n",
+       "      <td>HXT15</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Putative transmembrane polyol transporter; sup...</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>YBR232C</td>\n",
+       "      <td>None</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Dubious open reading frame; unlikely to encode...</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>YDR320W-B</td>\n",
+       "      <td>None</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Dubious open reading frame; unlikely to encode...</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>YBR021W</td>\n",
+       "      <td>FUR4</td>\n",
+       "      <td>protein_coding</td>\n",
+       "      <td>Plasma membrane localized uracil permease; exp...</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   stable_id display_label         biotype  \\\n",
+       "0    YBR024W          SCO2  protein_coding   \n",
+       "1    YDL245C         HXT15  protein_coding   \n",
+       "2    YBR232C          None  protein_coding   \n",
+       "3  YDR320W-B          None  protein_coding   \n",
+       "4    YBR021W          FUR4  protein_coding   \n",
+       "\n",
+       "                                         description synonym  \n",
+       "0  Protein anchored to mitochondrial inner membra...    None  \n",
+       "1  Putative transmembrane polyol transporter; sup...    None  \n",
+       "2  Dubious open reading frame; unlikely to encode...    None  \n",
+       "3  Dubious open reading frame; unlikely to encode...    None  \n",
+       "4  Plasma membrane localized uracil permease; exp...    None  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_core_group.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>display_label</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonym</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ETS1-1</th>\n",
+       "      <td>None</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located immediately upstream...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETS1-2</th>\n",
+       "      <td>None</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located immediately upstream...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETS2-1</th>\n",
+       "      <td>None</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located adjacent to and down...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETS2-2</th>\n",
+       "      <td>None</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located adjacent to RDN25; t...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HRA1</th>\n",
+       "      <td>None</td>\n",
+       "      <td>ncRNA</td>\n",
+       "      <td>Non-protein-coding RNA; substrate of RNase P, ...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          display_label biotype  \\\n",
+       "stable_id                         \n",
+       "ETS1-1             None    rRNA   \n",
+       "ETS1-2             None    rRNA   \n",
+       "ETS2-1             None    rRNA   \n",
+       "ETS2-2             None    rRNA   \n",
+       "HRA1               None   ncRNA   \n",
+       "\n",
+       "                                                 description synonym  \n",
+       "stable_id                                                             \n",
+       "ETS1-1     Non-coding region located immediately upstream...          \n",
+       "ETS1-2     Non-coding region located immediately upstream...          \n",
+       "ETS2-1     Non-coding region located adjacent to and down...          \n",
+       "ETS2-2     Non-coding region located adjacent to RDN25; t...          \n",
+       "HRA1       Non-protein-coding RNA; substrate of RNase P, ...          "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results_external.shape: (0, 4)\n",
+      "results_external.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>stable_id</th>\n",
+       "      <th>xref_id</th>\n",
+       "      <th>dbprimary_acc</th>\n",
+       "      <th>db_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [stable_id, xref_id, dbprimary_acc, db_name]\n",
+       "Index: []"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "duplicated ensembl_gene_ids with ncbi_gene_ids: 0\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>stable_id</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [ncbi_gene_id]\n",
+       "Index: []"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Final df.shape: (7127, 6)\n",
+      "df.head():\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ensembl_gene_id</th>\n",
+       "      <th>symbol</th>\n",
+       "      <th>ncbi_gene_id</th>\n",
+       "      <th>biotype</th>\n",
+       "      <th>description</th>\n",
+       "      <th>synonyms</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ETS1-1</td>\n",
+       "      <td>None</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located immediately upstream...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ETS1-2</td>\n",
+       "      <td>None</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located immediately upstream...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ETS2-1</td>\n",
+       "      <td>None</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located adjacent to and down...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ETS2-2</td>\n",
+       "      <td>None</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>rRNA</td>\n",
+       "      <td>Non-coding region located adjacent to RDN25; t...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>HRA1</td>\n",
+       "      <td>None</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>ncRNA</td>\n",
+       "      <td>Non-protein-coding RNA; substrate of RNase P, ...</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  ensembl_gene_id symbol ncbi_gene_id biotype  \\\n",
+       "0          ETS1-1   None          NaN    rRNA   \n",
+       "1          ETS1-2   None          NaN    rRNA   \n",
+       "2          ETS2-1   None          NaN    rRNA   \n",
+       "3          ETS2-2   None          NaN    rRNA   \n",
+       "4            HRA1   None          NaN   ncRNA   \n",
+       "\n",
+       "                                         description synonyms  \n",
+       "0  Non-coding region located immediately upstream...           \n",
+       "1  Non-coding region located immediately upstream...           \n",
+       "2  Non-coding region located adjacent to and down...           \n",
+       "3  Non-coding region located adjacent to RDN25; t...           \n",
+       "4  Non-protein-coding RNA; substrate of RNase P, ...           "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved as df_saccharomyces cerevisiae__ensembl__release-110__Gene.parquet\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_genes_df(species=species.saccharomyces_cerevisiae)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.13 ('py39')",
+   "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": "3.9.16"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "ae1fefc8646a06dd2e75004cd934adda7c5727b046986a772e3b44b0ffba9754"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/docs/ingest/index.md b/docs/ingest/index.md
index a8a6648..7f037b2 100644
--- a/docs/ingest/index.md
+++ b/docs/ingest/index.md
@@ -4,6 +4,7 @@
 :maxdepth: 1
 
 cell_line-clo-2022-03
+gene-ensembl-release-110
 gene-ensembl-release-109
 cell-marker-2.0
 protein-uniprot-2023-03