From 554f1a08410f154721ed0a4ae015868d0218ec54 Mon Sep 17 00:00:00 2001 From: Anders Riutta Date: Fri, 27 May 2022 18:22:30 -0700 Subject: [PATCH] Created using Colaboratory --- notebooks/bte_with_pfocr_cooccurrence.ipynb | 2369 +++++++++++++------ 1 file changed, 1636 insertions(+), 733 deletions(-) diff --git a/notebooks/bte_with_pfocr_cooccurrence.ipynb b/notebooks/bte_with_pfocr_cooccurrence.ipynb index 72a87ce..8f40ac6 100644 --- a/notebooks/bte_with_pfocr_cooccurrence.ipynb +++ b/notebooks/bte_with_pfocr_cooccurrence.ipynb @@ -5,7 +5,7 @@ "colab": { "name": "bte_with_pfocr_cooccurrence.ipynb", "provenance": [], - "authorship_tag": "ABX9TyO6hfzuqfwBUdlOr8CUXLfk", + "authorship_tag": "ABX9TyMGBEO4WsI+qAnctC5k3yPk", "include_colab_link": true }, "kernelspec": { @@ -29,46 +29,64 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 49, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UZZqPBS0UppM", - "outputId": "4dfaac8c-6842-429c-d3b5-9c3b8fbea79c" + "outputId": "9996ad71-f8fb-4c1f-bc40-430ede6b5de3" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ + "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (1.21.6)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.7/dist-packages (1.3.5)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (2.23.0)\n", "Requirement already satisfied: requests_cache in /usr/local/lib/python3.7/dist-packages (0.9.4)\n", + "Requirement already satisfied: SetSimilaritySearch in /usr/local/lib/python3.7/dist-packages (0.1.7)\n", "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas) (2.8.2)\n", "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas) (2022.1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.7.3->pandas) (1.15.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests) (2021.10.8)\n", - "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests) (2.10)\n", - "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests) (3.0.4)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests) (2022.5.18.1)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests) (1.25.11)\n", - "Requirement already satisfied: attrs<22.0,>=21.2 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (21.4.0)\n", - "Requirement already satisfied: cattrs<2.0,>=1.8 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (1.10.0)\n", + "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests) (3.0.4)\n", + "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests) (2.10)\n", "Requirement already satisfied: appdirs<2.0.0,>=1.4.4 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (1.4.4)\n", + "Requirement already satisfied: attrs<22.0,>=21.2 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (21.4.0)\n", "Requirement already satisfied: url-normalize<2.0,>=1.4 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (1.4.3)\n", + "Requirement already satisfied: cattrs<2.0,>=1.8 in /usr/local/lib/python3.7/dist-packages (from requests_cache) (1.10.0)\n", "Requirement already satisfied: typing_extensions in /usr/local/lib/python3.7/dist-packages (from cattrs<2.0,>=1.8->requests_cache) (4.2.0)\n" ] } ], "source": [ - "!pip install numpy pandas requests requests_cache" + "!pip install numpy pandas requests requests_cache SetSimilaritySearch" ] }, + { + "cell_type": "code", + "source": [ + "from copy import copy, deepcopy\n", + "import json" + ], + "metadata": { + "id": "uG7JfetZjcXH" + }, + "execution_count": 100, + "outputs": [] + }, { "cell_type": "markdown", "source": [ - "# BTE with PFOCR Coocurrence" + "# BTE with PFOCR Coocurrence\n", + "\n", + "I modified a query from the 3/17 Question of the Month to find relationships like this:\n", + "\n", + "`1 of 3 selected genes` -> `any gene` -> `Valproic Acid`" ], "metadata": { "id": "j9DiSC9NU_Fa" @@ -86,9 +104,18 @@ "metadata": { "id": "rzoUUSDeVz0a" }, - "execution_count": 2, + "execution_count": 51, "outputs": [] }, + { + "cell_type": "markdown", + "source": [ + "## Get BTE Results" + ], + "metadata": { + "id": "TxW41muraAFL" + } + }, { "cell_type": "code", "source": [ @@ -142,9 +169,9 @@ "base_uri": "https://localhost:8080/" }, "id": "N71NYHWeVCj9", - "outputId": "ff69d979-3a3b-4bc2-8f95-bd6caafa7376" + "outputId": "841a8dfb-1aa4-4f60-ba43-88989b390541" }, - "execution_count": 3, + "execution_count": 52, "outputs": [ { "output_type": "stream", @@ -158,20 +185,20 @@ { "cell_type": "code", "source": [ - "gene_nodes = []\n", - "for query_node_id, v in query[\"message\"][\"query_graph\"][\"nodes\"].items():\n", + "gene_q_node_ids = []\n", + "for q_node_id, v in query[\"message\"][\"query_graph\"][\"nodes\"].items():\n", " if \"biolink:Gene\" in v[\"categories\"]:\n", - " gene_nodes.append(query_node_id)\n", - "print(gene_nodes)" + " gene_q_node_ids.append(q_node_id)\n", + "print(gene_q_node_ids)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "KwyR8hcDZFUo", - "outputId": "68382737-f8f3-47c2-8d6e-dfe94d0ee002" + "outputId": "6b734567-d04a-4f63-d066-e408143e983d" }, - "execution_count": 4, + "execution_count": 53, "outputs": [ { "output_type": "stream", @@ -185,843 +212,1719 @@ { "cell_type": "code", "source": [ - "bte_json = bte_r.json()\n", - "bte_results = bte_json[\"message\"][\"results\"]\n", - "all_genes = set()\n", - "prefixes = set()\n", - "ncbi_genes = set()\n", + "bte_message = bte_r.json()[\"message\"]\n", + "bte_results = bte_message[\"results\"]\n", "genes_to_bte_results = dict()\n", "for bte_result in bte_results:\n", " bte_result_genes = []\n", - " for gene_node in gene_nodes:\n", - " for entry in bte_result[\"node_bindings\"][gene_node]:\n", + " for gene_q_node_id in gene_q_node_ids:\n", + " for entry in bte_result[\"node_bindings\"][gene_q_node_id]:\n", " id = entry[\"id\"]\n", - " all_genes.add(id)\n", - " prefixes.add(entry[\"id\"].split(\":\")[0])\n", " target_prefix = \"NCBIGene:\"\n", " if id.startswith(target_prefix):\n", - " ncbi_genes.add(entry[\"id\"][len(target_prefix):])\n", " bte_result_genes.append(\"NCBIGene:\" + entry[\"id\"][len(target_prefix):])\n", " genes_key = tuple(sorted(bte_result_genes))\n", " if not genes_key in genes_to_bte_results:\n", " genes_to_bte_results[genes_key] = []\n", - " genes_to_bte_results[genes_key].append(bte_result)\n", - "prefixes" + " genes_to_bte_results[genes_key].append(bte_result)" + ], + "metadata": { + "id": "Wjqcf5E4Yk_h" + }, + "execution_count": 54, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "## Get PFOCR Data\n", + "\n", + "Download the entire JSON file we gave to BTE." + ], + "metadata": { + "id": "1GQojZqc0QDf" + } + }, + { + "cell_type": "code", + "source": [ + "pfocr_url = \"https://www.dropbox.com/s/1f14t5zaseocyg6/bte_chemicals_diseases_genes.ndjson?dl=1\"\n", + "pfocr_request = requests.get(pfocr_url)\n", + "print(f\"status_code: {pfocr_request.status_code}\")\n", + "if pfocr_request.status_code != 200:\n", + " print(pfocr_request.text)\n", + "\n", + "genes_to_figids = {}\n", + "figid_to_genes = {}\n", + "figid_to_pfocr_result = {}\n", + "for line in pfocr_request.text.splitlines():\n", + " pfocr_result = json.loads(line)\n", + " figid = pfocr_result[\"_id\"]\n", + " genes = set(\n", + " [\"NCBIGene:\" + g for g in pfocr_result[\"associatedWith\"][\"mentions\"][\"genes\"][\"ncbigene\"]]\n", + " )\n", + " figid_to_pfocr_result[figid] = pfocr_result\n", + " figid_to_genes[figid] = genes\n", + "\n", + " genes_key = tuple(sorted(genes))\n", + " if not genes_key in genes_to_figids:\n", + " genes_to_figids[genes_key] = []\n", + " genes_to_figids[genes_key].append(figid)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, - "id": "Wjqcf5E4Yk_h", - "outputId": "db6e7568-4b98-4fa2-9057-2e6906bd772e" + "id": "OyJJUHbepKp2", + "outputId": "7434741f-5f0d-4396-9e83-fa8a2555f34e" }, - "execution_count": 5, + "execution_count": 55, "outputs": [ { - "output_type": "execute_result", - "data": { - "text/plain": [ - "{'NCBIGene'}" - ] - }, - "metadata": {}, - "execution_count": 5 + "output_type": "stream", + "name": "stdout", + "text": [ + "status_code: 200\n" + ] } ] }, { - "cell_type": "code", + "cell_type": "markdown", "source": [ - "query_param_limit = 4000\n", - "pfocr_results = []\n", - "q_term = \"\"\n", - "for ncbi_gene in ncbi_genes:\n", - " if q_term != \"\":\n", - " concatenator = \" OR \"\n", - " else:\n", - " concatenator = \"\"\n", - "\n", - " next_q = concatenator + \"associatedWith.mentions.genes.ncbigene:\" + ncbi_gene\n", - "\n", - " if len(q_term + next_q) < query_param_limit:\n", - " q_term += next_q\n", - " else:\n", - " payload = {\"q\": q_term}\n", - " pfocr_r = requests.get(\"https://biothings.ncats.io/pfocr/query\", params=payload)\n", - " print(f\"status_code: {pfocr_r.status_code}\")\n", - " if pfocr_r.status_code != 200:\n", - " print(pfocr_r.text)\n", - " pfocr_results.append(pfocr_r.json())\n", - " q_term = \"associatedWith.mentions.genes.ncbigene:\" + ncbi_gene\n", - "\n", - "if q_term:\n", - " print(f\"q_term: {q_term}\")\n", - " payload = {\"q\": q_term}\n", - " pfocr_r = requests.get(\"https://biothings.ncats.io/pfocr/query\", params=payload)\n", - " print(f\"status_code: {pfocr_r.status_code}\")\n", - " if pfocr_r.status_code != 200:\n", - " print(pfocr_r.text)\n", - " pfocr_results.append(pfocr_r.json())\n", - " q_term = \"\"\n", + "## Connect BTE Results & PFOCR" + ], + "metadata": { + "id": "uCW1x4PxnjYJ" + } + }, + { + "cell_type": "markdown", + "source": [ + "### Compare Algo Performance\n", "\n", - "print(len(pfocr_results))" + "The following three algorithms all match up the BTE gene sets with the PFOCR sets, but they have different performances:\n", + "- Brute Force: 47s\n", + "- Check All BTE Results Genes Set: 5s\n", + "- SetSimilaritySearch: 2s" + ], + "metadata": { + "id": "hTrLMM_QxONz" + } + }, + { + "cell_type": "markdown", + "source": [ + "#### Brute Force" + ], + "metadata": { + "id": "ypA0HIzSxfnH" + } + }, + { + "cell_type": "code", + "source": [ + "all_figure_genes_keys = genes_to_figids.keys()\n", + "bf_overlaps_2_plus = set()\n", + "for bte_result_genes_key in genes_to_bte_results.keys():\n", + " bte_result_genes = set(bte_result_genes_key)\n", + " for figure_genes_keys in all_figure_genes_keys:\n", + " figure_genes = set(figure_genes_keys)\n", + " if len(bte_result_genes.intersection(figure_genes)) >= 2:\n", + " bf_overlaps_2_plus.add((bte_result_genes_key, figure_genes_keys))\n", + "print(len(bf_overlaps_2_plus))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, - "id": "R96yZ6CfWc7f", - "outputId": "e1e8f769-09e7-48e4-e4d6-ee64019b5e58" + "id": "InJU5egur5PI", + "outputId": "ff2f3640-aab2-4ece-fb3d-85bd0c073af8" }, - "execution_count": 6, + "execution_count": 56, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "status_code: 200\n", - "status_code: 200\n", - "status_code: 200\n", - "q_term: associatedWith.mentions.genes.ncbigene:4585 OR associatedWith.mentions.genes.ncbigene:23657 OR associatedWith.mentions.genes.ncbigene:3558 OR associatedWith.mentions.genes.ncbigene:2167 OR associatedWith.mentions.genes.ncbigene:36 OR associatedWith.mentions.genes.ncbigene:11118 OR associatedWith.mentions.genes.ncbigene:2169 OR associatedWith.mentions.genes.ncbigene:5950 OR associatedWith.mentions.genes.ncbigene:10038 OR associatedWith.mentions.genes.ncbigene:54556 OR associatedWith.mentions.genes.ncbigene:7450 OR associatedWith.mentions.genes.ncbigene:5111 OR associatedWith.mentions.genes.ncbigene:11083 OR associatedWith.mentions.genes.ncbigene:5927 OR associatedWith.mentions.genes.ncbigene:1026 OR associatedWith.mentions.genes.ncbigene:4582 OR associatedWith.mentions.genes.ncbigene:1543 OR associatedWith.mentions.genes.ncbigene:79633 OR associatedWith.mentions.genes.ncbigene:231 OR associatedWith.mentions.genes.ncbigene:2660 OR associatedWith.mentions.genes.ncbigene:57713 OR associatedWith.mentions.genes.ncbigene:2954 OR associatedWith.mentions.genes.ncbigene:9854 OR associatedWith.mentions.genes.ncbigene:23522 OR associatedWith.mentions.genes.ncbigene:3855 OR associatedWith.mentions.genes.ncbigene:80232 OR associatedWith.mentions.genes.ncbigene:25898 OR associatedWith.mentions.genes.ncbigene:92399 OR associatedWith.mentions.genes.ncbigene:10486 OR associatedWith.mentions.genes.ncbigene:3566 OR associatedWith.mentions.genes.ncbigene:4005 OR associatedWith.mentions.genes.ncbigene:4289 OR associatedWith.mentions.genes.ncbigene:3622 OR associatedWith.mentions.genes.ncbigene:64781 OR associatedWith.mentions.genes.ncbigene:7076 OR associatedWith.mentions.genes.ncbigene:11162 OR associatedWith.mentions.genes.ncbigene:8508 OR associatedWith.mentions.genes.ncbigene:3033 OR associatedWith.mentions.genes.ncbigene:1759 OR associatedWith.mentions.genes.ncbigene:2064 OR associatedWith.mentions.genes.ncbigene:3162 OR associatedWith.mentions.genes.ncbigene:211 OR associatedWith.mentions.genes.ncbigene:7846 OR associatedWith.mentions.genes.ncbigene:58472 OR associatedWith.mentions.genes.ncbigene:23314 OR associatedWith.mentions.genes.ncbigene:2026 OR associatedWith.mentions.genes.ncbigene:80205 OR associatedWith.mentions.genes.ncbigene:79772 OR associatedWith.mentions.genes.ncbigene:335 OR associatedWith.mentions.genes.ncbigene:3866 OR associatedWith.mentions.genes.ncbigene:4023 OR associatedWith.mentions.genes.ncbigene:163050 OR associatedWith.mentions.genes.ncbigene:2735 OR associatedWith.mentions.genes.ncbigene:56052 OR associatedWith.mentions.genes.ncbigene:388610 OR associatedWith.mentions.genes.ncbigene:1728 OR associatedWith.mentions.genes.ncbigene:2744 OR associatedWith.mentions.genes.ncbigene:1975 OR associatedWith.mentions.genes.ncbigene:51310 OR associatedWith.mentions.genes.ncbigene:1371 OR associatedWith.mentions.genes.ncbigene:59 OR associatedWith.mentions.genes.ncbigene:10181 OR associatedWith.mentions.genes.ncbigene:51696 OR associatedWith.mentions.genes.ncbigene:57721 OR associatedWith.mentions.genes.ncbigene:221935 OR associatedWith.mentions.genes.ncbigene:7316 OR associatedWith.mentions.genes.ncbigene:93010 OR associatedWith.mentions.genes.ncbigene:64147 OR associatedWith.mentions.genes.ncbigene:326625 OR associatedWith.mentions.genes.ncbigene:489 OR associatedWith.mentions.genes.ncbigene:79718 OR associatedWith.mentions.genes.ncbigene:3135 OR associatedWith.mentions.genes.ncbigene:100507679 OR associatedWith.mentions.genes.ncbigene:3146 OR associatedWith.mentions.genes.ncbigene:6453 OR associatedWith.mentions.genes.ncbigene:4343 OR associatedWith.mentions.genes.ncbigene:2639 OR associatedWith.mentions.genes.ncbigene:23242 OR associatedWith.mentions.genes.ncbigene:2683 OR associatedWith.mentions.genes.ncbigene:2116 OR associatedWith.mentions.genes.ncbigene:3861 OR associatedWith.mentions.genes.ncbigene:8573 OR associatedWith.mentions.genes.ncbigene:34 OR associatedWith.mentions.genes.ncbigene:7481\n", - "status_code: 200\n", - "4\n" + "164\n" ] } ] }, + { + "cell_type": "markdown", + "source": [ + "#### Check All BTE Results Genes Set\n", + "Check whether the figure gene set overlaps with `size >=2` the set made up of all BTE results genes. Note this performance may be worse if the BTE result count is larger." + ], + "metadata": { + "id": "bXbZKX-9xj2P" + } + }, { "cell_type": "code", "source": [ - "hits = []\n", - "for pfocr_result in pfocr_results:\n", - " hits += pfocr_result[\"hits\"]\n", - "print(len(hits))" + "all_bte_result_genes_keys = genes_to_bte_results.keys()\n", + "all_bte_result_genes = set([]).union(\n", + " *[set(bte_result_genes_key) for bte_result_genes_key in all_bte_result_genes_keys]\n", + ")\n", + "bf_overlaps_2_plus = set()\n", + "\n", + "for figure_genes_keys in genes_to_figids.keys():\n", + " figure_genes = set(figure_genes_keys)\n", + " if len(figure_genes.intersection(all_bte_result_genes)) >= 2:\n", + " for bte_result_genes_key in all_bte_result_genes_keys:\n", + " bte_result_genes = set(bte_result_genes_key)\n", + " if len(bte_result_genes.intersection(figure_genes)) >= 2:\n", + " bf_overlaps_2_plus.add((bte_result_genes_key, figure_genes_keys))\n", + "\n", + "print(len(bf_overlaps_2_plus))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, - "id": "q2WCmhpNQOI-", - "outputId": "1b4c8333-daf5-44f3-e6df-c9811e5258f9" + "id": "IORU-9sQtAKt", + "outputId": "82809f77-a623-444f-f37b-ca2131249db8" }, - "execution_count": 7, + "execution_count": 57, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "40\n" + "164\n" ] } ] }, + { + "cell_type": "markdown", + "source": [ + "#### SetSimilaritySearch\n", + "\n", + "This algorithm is sometimes too permissive, making the overlap check needed, but even so, it's faster and gets the same results once we apply the overlap check." + ], + "metadata": { + "id": "jXFbvMrTx8sS" + } + }, { "cell_type": "code", "source": [ - "pfocr_id_to_genes = dict()\n", - "pfocr_id_to_pfocr_result = dict()\n", - "for hit in hits:\n", - " pfocr_id = hit[\"_id\"]\n", - " pfocr_id_to_genes[pfocr_id] = set(\n", - " \"NCBIGene:\" + g for g in hit[\"associatedWith\"][\"mentions\"][\"genes\"][\"ncbigene\"]\n", - " )\n", - " pfocr_id_to_pfocr_result[pfocr_id] = {\n", - " \"figureUrl\": hit[\"associatedWith\"][\"figureUrl\"],\n", - " \"pmc\": hit[\"associatedWith\"][\"pmc\"],\n", - " \"score\": hit[\"_score\"],\n", - " }" + "from SetSimilaritySearch import SearchIndex\n", + "\n", + "pfocr_gene_sets = list(genes_to_figids.keys())\n", + "index = SearchIndex(pfocr_gene_sets, similarity_func_name=\"containment\", \n", + " similarity_threshold=0.8)\n", + "\n", + "sss_overlaps_2_plus = set()\n", + "for bte_result_genes_key in genes_to_bte_results.keys():\n", + " bte_result_genes = set(bte_result_genes_key)\n", + " results = index.query(bte_result_genes)\n", + " for result in results:\n", + " figure_genes = pfocr_gene_sets[result[0]]\n", + " if len(bte_result_genes.intersection(figure_genes)) >= 2:\n", + " sss_overlaps_2_plus.add((bte_result_genes_key, tuple(sorted(figure_genes))))\n", + "print(len(sss_overlaps_2_plus))" ], "metadata": { - "id": "Dz7mPvLxTPC8" + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "gWWRq_rdq2vC", + "outputId": "0c97fb02-5c60-45aa-add1-c20145c21daa" }, - "execution_count": 8, - "outputs": [] + "execution_count": 58, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "164\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Choose and Apply SetSimilaritySearch\n", + "\n", + "SetSimilaritySearch was fastest, so let's choose it and use it to augment the BTE results." + ], + "metadata": { + "id": "2EzVeKVcn_2L" + } }, { "cell_type": "code", "source": [ - "print(len(pfocr_id_to_genes.keys()))\n", - "len(genes_to_bte_results.keys())" + "from SetSimilaritySearch import SearchIndex\n", + "\n", + "pfocr_gene_sets = list(genes_to_figids.keys())\n", + "index = SearchIndex(pfocr_gene_sets, similarity_func_name=\"containment\", \n", + " similarity_threshold=0.8)\n", + "\n", + "overlaps_2_plus_count = 0\n", + "for bte_result_genes_key, genes_bte_results in genes_to_bte_results.items():\n", + " bte_result_genes = set(bte_result_genes_key)\n", + " results = index.query(bte_result_genes)\n", + " #if results:\n", + " # print(\"------\")\n", + " # print(f'bte_result_genes: {bte_result_genes}')\n", + " for result in results:\n", + " figure_genes = pfocr_gene_sets[result[0]]\n", + " score = result[1]\n", + " figids = genes_to_figids[tuple(sorted(figure_genes))]\n", + " #print(f'{figids} ({score}) - {figure_genes}')\n", + " common = bte_result_genes.intersection(figure_genes)\n", + " #print(f'intersection: {common}')\n", + " if len(common) >= 2:\n", + " for figid in figids:\n", + " overlaps_2_plus_count += 1\n", + " pfocr_result = figid_to_pfocr_result[figid]\n", + " #print(\"--------\")\n", + " #print(f'{figid} - {figure_genes}')\n", + " for bte_result in genes_bte_results:\n", + " #print(f'bte_result: {sorted(bte_result_genes)}')\n", + " #print(f'common: {bte_result_genes.intersection(figure_genes)}')\n", + " nodes = set()\n", + " for q_node_id, values in bte_result[\"node_bindings\"].items():\n", + " for value in values:\n", + " id = value[\"id\"]\n", + " if id in figure_genes:\n", + " nodes.add(q_node_id)\n", + " if not \"pfocr\" in bte_result:\n", + " bte_result[\"pfocr\"] = []\n", + " pfocr_entry = copy(pfocr_result)\n", + " pfocr_entry[\"nodes\"] = sorted(nodes)\n", + " pfocr_entry[\"score\"] = score\n", + " bte_result[\"pfocr\"].append(pfocr_entry)\n", + "print(len(overlaps_2_plus_count))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, - "id": "6dWDZ2Igb2g9", - "outputId": "196f9fae-efbb-461e-c154-9eba630173e1" + "id": "aZX7IzakKCnH", + "outputId": "dabcdf7a-f7d1-4f7a-821a-b21d19ce5a13" }, - "execution_count": 9, + "execution_count": 59, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "36\n" + "172\n" ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "\n", + "\n", + "kg_nodes = bte_message[\"knowledge_graph\"][\"nodes\"]\n", + "\n", + "bte_rows = []\n", + "for bte_result in bte_results:\n", + " bte_row_template = {}\n", + " for q_node_id, value in bte_result[\"node_bindings\"].items():\n", + " node_labels = []\n", + " for v in value:\n", + " id = v[\"id\"]\n", + " name = kg_nodes[id][\"name\"]\n", + " #node_labels.append(f'{name} ({id})')\n", + " node_labels.append(name)\n", + " bte_row_template[q_node_id] = \",\".join(node_labels)\n", + " # just taking the first one for now\n", + " bte_row_template[q_node_id + \"_identifier\"] = value[0][\"id\"]\n", + "\n", + " bte_row_template[\"score\"] = bte_result[\"score\"]\n", + " \n", + " if \"pfocr\" in bte_result:\n", + " for pfocr_result in bte_result[\"pfocr\"]:\n", + " bte_row = deepcopy(bte_row_template)\n", + " bte_row[\"figure_title\"] = pfocr_result[\"associatedWith\"][\"title\"]\n", + " bte_row[\"figid\"] = pfocr_result[\"_id\"]\n", + " bte_row[\"figure_url\"] = pfocr_result[\"associatedWith\"][\"figureUrl\"]\n", + " bte_row[\"pfocr_score\"] = pfocr_result[\"score\"]\n", + " bte_rows.append(bte_row)\n", + " else:\n", + " bte_rows.append(bte_row_template)\n", + " \n", + "bte_df = pd.DataFrame(bte_rows)\n", + "bte_df" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 904 }, + "id": "XdofZ-R62QM9", + "outputId": "d70a6c5a-b9c2-4958-a14d-aa38a0aec294" + }, + "execution_count": 118, + "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ - "356" + " n2 n2_identifier n1 n1_identifier n0 \\\n", + "0 Valproic acid PUBCHEM.COMPOUND:3121 HMOX1 NCBIGene:3162 ALAS1 \n", + "1 Valproic acid PUBCHEM.COMPOUND:3121 HMOX1 NCBIGene:3162 ALAS1 \n", + "2 Valproic acid PUBCHEM.COMPOUND:3121 HMOX1 NCBIGene:3162 ALAS1 \n", + "3 Valproic acid PUBCHEM.COMPOUND:3121 ATP5MG NCBIGene:10632 TRUB2 \n", + "4 Valproic acid PUBCHEM.COMPOUND:3121 ATF2 NCBIGene:1386 KRT7 \n", + ".. ... ... ... ... ... \n", + "454 Valproic acid PUBCHEM.COMPOUND:3121 SLC7A11 NCBIGene:23657 ALAS1 \n", + "455 Valproic acid PUBCHEM.COMPOUND:3121 HPRT1 NCBIGene:3251 ALAS1 \n", + "456 Valproic acid PUBCHEM.COMPOUND:3121 CFTR NCBIGene:1080 KRT7 \n", + "457 Valproic acid PUBCHEM.COMPOUND:3121 LAMP2 NCBIGene:3920 TRUB2 \n", + "458 Valproic acid PUBCHEM.COMPOUND:3121 FABP2 NCBIGene:2169 ALAS1 \n", + "\n", + " n0_identifier score figure_title \\\n", + "0 NCBIGene:211 0 Activated Oncogenic Pathway Modifies Iron Netw... \n", + "1 NCBIGene:211 0 The heme biosynthetic pathway and aspects of i... \n", + "2 NCBIGene:211 0 Pathogenesis and Clinical Features of the Acut... \n", + "3 NCBIGene:26995 0 NaN \n", + "4 NCBIGene:3855 0 Transcriptional landscape of mouse-aged ovarie... \n", + ".. ... ... ... \n", + "454 NCBIGene:211 0 NaN \n", + "455 NCBIGene:211 0 Metabolic pathway differences between LLO118 a... \n", + "456 NCBIGene:3855 0 Network of pancreatic cancer-target genes \n", + "457 NCBIGene:26995 0 NaN \n", + "458 NCBIGene:211 0 NaN \n", + "\n", + " figid \\\n", + "0 PMC5293201__pcbi.1005352.g001.jpg \n", + "1 PMC4279155__metabolites-04-00977-g001.jpg \n", + "2 PMC6754303__nihms-1526961-f0002.jpg \n", + "3 NaN \n", + "4 PMC6281605__41420_2018_121_Fig2_HTML.jpg \n", + ".. ... \n", + "454 NaN \n", + "455 PMC7500861__nihms-1628382-f0005.jpg \n", + "456 PMC6826333__or-42-06-2561-g01.jpg \n", + "457 NaN \n", + "458 NaN \n", + "\n", + " figure_url pfocr_score \n", + "0 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5... 1.0 \n", + "1 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4... 1.0 \n", + "2 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6... 1.0 \n", + "3 NaN NaN \n", + "4 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6... 1.0 \n", + ".. ... ... \n", + "454 NaN NaN \n", + "455 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7... 1.0 \n", + "456 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6... 1.0 \n", + "457 NaN NaN \n", + "458 NaN NaN \n", + "\n", + "[459 rows x 11 columns]" + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
n2n2_identifiern1n1_identifiern0n0_identifierscorefigure_titlefigidfigure_urlpfocr_score
0Valproic acidPUBCHEM.COMPOUND:3121HMOX1NCBIGene:3162ALAS1NCBIGene:2110Activated Oncogenic Pathway Modifies Iron Netw...PMC5293201__pcbi.1005352.g001.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5...1.0
1Valproic acidPUBCHEM.COMPOUND:3121HMOX1NCBIGene:3162ALAS1NCBIGene:2110The heme biosynthetic pathway and aspects of i...PMC4279155__metabolites-04-00977-g001.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC4...1.0
2Valproic acidPUBCHEM.COMPOUND:3121HMOX1NCBIGene:3162ALAS1NCBIGene:2110Pathogenesis and Clinical Features of the Acut...PMC6754303__nihms-1526961-f0002.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6...1.0
3Valproic acidPUBCHEM.COMPOUND:3121ATP5MGNCBIGene:10632TRUB2NCBIGene:269950NaNNaNNaNNaN
4Valproic acidPUBCHEM.COMPOUND:3121ATF2NCBIGene:1386KRT7NCBIGene:38550Transcriptional landscape of mouse-aged ovarie...PMC6281605__41420_2018_121_Fig2_HTML.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6...1.0
....................................
454Valproic acidPUBCHEM.COMPOUND:3121SLC7A11NCBIGene:23657ALAS1NCBIGene:2110NaNNaNNaNNaN
455Valproic acidPUBCHEM.COMPOUND:3121HPRT1NCBIGene:3251ALAS1NCBIGene:2110Metabolic pathway differences between LLO118 a...PMC7500861__nihms-1628382-f0005.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7...1.0
456Valproic acidPUBCHEM.COMPOUND:3121CFTRNCBIGene:1080KRT7NCBIGene:38550Network of pancreatic cancer-target genesPMC6826333__or-42-06-2561-g01.jpghttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6...1.0
457Valproic acidPUBCHEM.COMPOUND:3121LAMP2NCBIGene:3920TRUB2NCBIGene:269950NaNNaNNaNNaN
458Valproic acidPUBCHEM.COMPOUND:3121FABP2NCBIGene:2169ALAS1NCBIGene:2110NaNNaNNaNNaN
\n", + "

459 rows × 11 columns

\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " ] }, "metadata": {}, - "execution_count": 9 + "execution_count": 118 } ] }, + { + "cell_type": "markdown", + "source": [ + "The following table is also [available as a Google Sheet](https://docs.google.com/spreadsheets/d/1yHBTxs6SghJGk-wQP7JbmpZ5Wbq6OY6Yz7PEtwd4j_w/edit?usp=sharing)." + ], + "metadata": { + "id": "FYO4IO4HDGxm" + } + }, { "cell_type": "code", "source": [ - "from copy import copy\n", - "\n", - "\n", - "cooccurring_bte_results = []\n", - "for g0_tuple, genes_bte_results in genes_to_bte_results.items():\n", - " g0 = set(g0_tuple)\n", - " for pfocr_id, g1 in pfocr_id_to_genes.items():\n", - " if len(g0.intersection(g1)) >= 2:\n", - " for bte_result in genes_bte_results:\n", - " matches = list()\n", - " nodes = set()\n", - " for query_node_id, values in bte_result[\"node_bindings\"].items():\n", - " for value in values:\n", - " id = value[\"id\"]\n", - " if id in g0:\n", - " nodes.add(query_node_id)\n", - " bte_result[\"pfocr\"] = copy(pfocr_id_to_pfocr_result[pfocr_id])\n", - " bte_result[\"pfocr\"][\"nodes\"] = sorted(nodes)\n", - " cooccurring_bte_results += genes_bte_results\n", - "cooccurring_bte_results" + "bte_df.rename(columns={\"figure_url\": \"figure_count\"}).groupby([\"n0\", \"n1\", \"n2\"])[[\"figure_count\"]].count().sort_values(\"figure_count\", ascending=False)" ], "metadata": { "colab": { - "base_uri": "https://localhost:8080/" + "base_uri": "https://localhost:8080/", + "height": 455 }, - "id": "jp_798WAfkNb", - "outputId": "016b0159-e65c-4996-83b1-0e9cc5df6a82" + "id": "aWy5v2oEAXfH", + "outputId": "71fc053d-4ca4-4ea5-9fe3-9b44d1c73fcb" }, - "execution_count": 10, + "execution_count": 120, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ - "[{'edge_bindings': {'e01': [{'id': '5fc6cc476f4bcb068460c5d299db52dd'}],\n", - " 'e02': [{'id': 'fc671d4b62d2d983372271323c3e8be3'},\n", - " {'id': '7b6da63564f96e9b4d0aef2581eb3ba3'},\n", - " {'id': '3e93479f91fd45c376d4851eea747174'},\n", - " {'id': 'e495f8080658dd1cd0acbec8c4cfeaf7'},\n", - " {'id': '551bd928ba58c60f465375306b81bbac'},\n", - " {'id': '6f6dd5467485ea133e64cb76b405c7d2'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:5599'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '0eb02f5d33311f1ab445417b47fd6e11'},\n", - " {'id': '0ccc29e5e4605fdc6131e3f091905b66'},\n", - " {'id': 'ed99dfcff0914197197743a6674bf275'},\n", - " {'id': '099133a2b625d0e9768bca884698670a'}],\n", - " 'e02': [{'id': '11777d2063e7b250c311ffe794add320'},\n", - " {'id': '101db421fc6adc0af509da28f3837530'},\n", - " {'id': '15877cabdbb7615197ef367854093c97'},\n", - " {'id': 'bd1e5ef859f20039e1940e5a1ff9fb93'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:5111'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '6bcc6075e3514a3e8965b053157e32ec'}],\n", - " 'e02': [{'id': '39842cc8afc55e85ab02f137108a4b74'},\n", - " {'id': '0290b3b665d8c2c31d8aea63eb185911'},\n", - " {'id': 'e7383e2f1ce64986524b201232b29c6e'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:673'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'feeabe0fb40a838a7f185dc7c0478796'}],\n", - " 'e02': [{'id': '660565a9ee239b937a85512c7151fbbd'},\n", - " {'id': '4e35e06bd7aa1228831ce6bcb5b7bb1f'},\n", - " {'id': '92c694a498385a357539c5c1567aea01'},\n", - " {'id': '0732045fc555e33243205ca22f2e72cb'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2099'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '25db307db624f439266beb0688e3c316'}],\n", - " 'e02': [{'id': 'df09d46810e1cc85a49b4b97f49061aa'},\n", - " {'id': '2938e12d32d70381a2cd5bedb0fbe7e2'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:7316'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '5ecc3d9468a155111a726935dc84affa'}],\n", - " 'e02': [{'id': '217d9d463a01430e588c95f88479908c'},\n", - " {'id': '8204433e37b339c1bb031eff5959885c'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3558'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'a140620edd5c7b3711cf30cf4a837aad'}],\n", - " 'e02': [{'id': '1fc75fd38a4c4424d6a216a2ba4379a7'},\n", - " {'id': '87e1ee492992fc7d1700b8c337f351ec'},\n", - " {'id': 'f3d1141ff2a7581d7118dfdf7e1ec59b'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4087'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'a11e3bf2af13b7bed8ded339a526825f'},\n", - " {'id': 'de1e5dd74badbdcff8de39942f37abeb'}],\n", - " 'e02': [{'id': '87405ad6d79c19ee5e599793cb82484f'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:6256'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '68a1a10534883e57d97516f7ddef8207'}],\n", - " 'e02': [{'id': '499babce0c4006d4f551c873a2c29aa3'},\n", - " {'id': '685c9953fb82a2b4b299a9b73642cc19'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:6662'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'bc876f5ac8bc6bbedae99b1ebecae705'},\n", - " {'id': 'eabd6fa7ecfd35e7270e68fdeeb6ef54'}],\n", - " 'e02': [{'id': 'e768690b5b51b76b670d0b4a482d7c7b'},\n", - " {'id': '544d79de72dd070f6938164a02bbfac0'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3486'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '56048aa997e9d06702b86304c5b456fa'},\n", - " {'id': 'a5fdaf0ecdd9467229097a53161e9e7c'},\n", - " {'id': 'a4a3574e7741ad9e951692568dbd96a6'},\n", - " {'id': 'ced5b6b4fcf5367acb0735a7039f3665'}],\n", - " 'e02': [{'id': 'e363a7af44e8a98a861d7d24156c4d54'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:1045'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '06302d71a2f97ad472d7b468b4430fa9'},\n", - " {'id': '48c3d2248fcbeb697775f39fa8ba1762'}],\n", - " 'e02': [{'id': 'd5a7ed983bd146d7e8970f2f7dd85596'},\n", - " {'id': '2c57d6cb7e370d1261c5d882912e6528'},\n", - " {'id': 'eb4a99ca9069323707278258c6d02f2f'},\n", - " {'id': '17bad7030cc7fa20b45bf6af7e5f519e'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:7124'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '3078a76c2163620fd10306e8bb9f01af'},\n", - " {'id': 'd2b63c53b463a50f0cb9a43eaa36d366'},\n", - " {'id': '8fd55619f8c1ab7637e0109780449d73'}],\n", - " 'e02': [{'id': '25935edc891bf0293767b932eb30550e'},\n", - " {'id': 'e29487b74958d151d054fc7e6669a8c3'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:6855'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'be4af43d42397717bae5a5bcf7a552e8'}],\n", - " 'e02': [{'id': '0661a08b72324a04e63f300c291fceee'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:5894'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '6a1b60fc245053ec3f73f1e1e92e5d9c'}],\n", - " 'e02': [{'id': 'd65c6a20f924f05e2ec07634b875073c'},\n", - " {'id': '83346618336d6bd30ce3d59f8a84f79f'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:9429'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '4a700c7fa1d807ecd2ca25098cd18d3e'}],\n", - " 'e02': [{'id': '85f64c538ca5fd089cd55f6a6b50e1e2'},\n", - " {'id': 'dc94ea78889822fb5d145e70139f20ad'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4092'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '6c9c87af092cf05cd15b3226d803594f'}],\n", - " 'e02': [{'id': 'f69625eea718a596dc1171c0f3650bc7'},\n", - " {'id': '48963c532b62a484f04a6ae58b9ebe89'},\n", - " {'id': 'b684e89e90dc57b3fc348d6092d13cc8'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:2697'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'e1df9fdb7fd371650ddc3a9ae709a088'},\n", - " {'id': '4d5b5f82d20030cf3855a6cb25d9bfa6'},\n", - " {'id': '949a96c4d2431e22debb39d5c234988d'}],\n", - " 'e02': [{'id': 'd18a0d49a0bb723f3e621cea3ecc4a65'},\n", - " {'id': '9a1dc3ee9f3d4951f2ccc873b8bf69a7'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3146'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'e1df9fdb7fd371650ddc3a9ae709a088'},\n", - " {'id': '4d5b5f82d20030cf3855a6cb25d9bfa6'},\n", - " {'id': '949a96c4d2431e22debb39d5c234988d'}],\n", - " 'e02': [{'id': 'd18a0d49a0bb723f3e621cea3ecc4a65'},\n", - " {'id': '9a1dc3ee9f3d4951f2ccc873b8bf69a7'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3146'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '8280fa21ab5b72683c4fed651ef96c60'},\n", - " {'id': '1662be17dc00a4444a17d0515f646795'}],\n", - " 'e02': [{'id': 'f27c34d62201e9de7cf3c95d704cc6a2'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:328'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'f8d57e177a5dc45b2178f4be43a3446a'}],\n", - " 'e02': [{'id': 'd90b28fb9e0d88feaa442d934c95649b'},\n", - " {'id': '188013336adbb86539751aaf75308b95'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:7431'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'a3a81354eb6fb240754c0ab14a25d04e'}],\n", - " 'e02': [{'id': 'a4daafe372bc5b6bd6e9afb62c0085fe'},\n", - " {'id': 'f6fb660f9a02aea8412a9490d204f6a8'},\n", - " {'id': '270caf09c7a925c2665c7676f11e9ff3'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:1956'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '9769a7afe6d77806d6985cfd54d59a0b'}],\n", - " 'e02': [{'id': '1befcf6484bcb0efea5b769fec845f17'},\n", - " {'id': 'd52e887b38c865df7f6d4d5aefe830b8'},\n", - " {'id': '6fb19e9d8eadb267939c051b3a0f0d69'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:8743'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '8b5fdb4036068dff866aa33200abba23'}],\n", - " 'e02': [{'id': '3e185b312016f75f41a895c1261b6fb4'},\n", - " {'id': '413efc61260e7e1f2bf03d2ff1240567'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2305'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '2cb1a70c82f47c2716147637f4c55558'},\n", - " {'id': '624891cb0581176e479de3fd2cd31652'},\n", - " {'id': 'd2f574461650acc2cf2fd46a5fffdece'},\n", - " {'id': '67bbdac723eafcbf048f7379d52d4202'},\n", - " {'id': '013f9f51b185738047b63a8264bdf450'}],\n", - " 'e02': [{'id': '86ba433389166b6b809ee6adbfab8ba7'},\n", - " {'id': '2bba55bf4e9945ec66f2dffd0ff36f70'},\n", - " {'id': '07ca6e026506910d3370aeb9a542078a'},\n", - " {'id': '52b7ed5e0747ed9c05f8a5afcd244626'},\n", - " {'id': '1f20801757066bf35568fb58d5c5646b'},\n", - " {'id': 'c2bed4bbf5888e4285e3df62dbef00dc'},\n", - " {'id': '1c308732ab654c3a77a6755aacfc1bdc'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:7157'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'adbc1653a71b11cbfc551e5002a0570a'},\n", - " {'id': 'ccb7653a3f425b51f67902df385286db'}],\n", - " 'e02': [{'id': '86ba433389166b6b809ee6adbfab8ba7'},\n", - " {'id': '2bba55bf4e9945ec66f2dffd0ff36f70'},\n", - " {'id': '07ca6e026506910d3370aeb9a542078a'},\n", - " {'id': '52b7ed5e0747ed9c05f8a5afcd244626'},\n", - " {'id': '1f20801757066bf35568fb58d5c5646b'},\n", - " {'id': 'c2bed4bbf5888e4285e3df62dbef00dc'},\n", - " {'id': '1c308732ab654c3a77a6755aacfc1bdc'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:7157'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '6c522fd60b2b7c514201a5aa000b9da0'}],\n", - " 'e02': [{'id': '51eb1a5d46c068537a0f67ba8fbbb60d'},\n", - " {'id': 'ba2db69df8aaa215aa84618dc03ed21f'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3383'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '92cac1aba2f06c6a82f162bae56e35ea'}],\n", - " 'e02': [{'id': 'bd9a78c53d7fd2c25bbca5b729d8f974'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:3691'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'ed578e8e6a07225263e79511629d6c7d'}],\n", - " 'e02': [{'id': '8b4f3dee0d2cc02c8703295099cfb4bd'},\n", - " {'id': '27fcf54bc839ecb565948a6054617d75'},\n", - " {'id': '42a4099cb90f6b2d5353771d10ea60e4'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:836'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'ed578e8e6a07225263e79511629d6c7d'}],\n", - " 'e02': [{'id': '8b4f3dee0d2cc02c8703295099cfb4bd'},\n", - " {'id': '27fcf54bc839ecb565948a6054617d75'},\n", - " {'id': '42a4099cb90f6b2d5353771d10ea60e4'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:836'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '555303a67b34407f0dfc1856ec08816f'}],\n", - " 'e02': [{'id': 'd7d6ad84b315e59db7e50063116c35a4'},\n", - " {'id': '517ff511f9c96f9292cdffe39fe05c04'},\n", - " {'id': '57cc64216fbb800e1b19906d89331f77'},\n", - " {'id': '49584f461c5fb74df2c5e979d3fd6561'},\n", - " {'id': '0b2525f5e640cb71f2e9b57d240e2c28'},\n", - " {'id': '38d79c5a78391fe82e6144c031231dd8'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4089'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '04dc3f4cc996929fb804d06596526240'}],\n", - " 'e02': [{'id': 'e723b318973f3c20445e225651e57144'},\n", - " {'id': '602739118779b2859a0cc7889b0235ac'},\n", - " {'id': '8bd35fd0ae1088c91137fa706cf6f5d1'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2064'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '0b91b0f430d6c91ac8d589c7f9cfc43e'}],\n", - " 'e02': [{'id': '2194c7ac2953d455857bf8043094b766'},\n", - " {'id': '207e1d40d7993282b0f845adf79573d9'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:182'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '948389adb6ba42c7575a144097d1fed4'}],\n", - " 'e02': [{'id': 'f98c31718b93cb3d387e9757370797c3'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:947'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'd66f14ba9a5d366b7adb4ca408fa0359'}],\n", - " 'e02': [{'id': 'eccd05b46cda0d944e5e5848601b82f5'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:335'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '54554818d72007b7eb0b33528905ba75'}],\n", - " 'e02': [{'id': '8b710eadc4a71a41c4701d11f179231a'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2660'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'fb4799c8274cc6c362e213ed97050ed0'},\n", - " {'id': '2a61e2fc7a37149ab8682a103fa8bd0f'},\n", - " {'id': '521a7976a55116075a68a98c777293d4'}],\n", - " 'e02': [{'id': 'e9360469e0cfe21a6b88dec49557bb41'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4582'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '68f2ab6dc776f4454429e06d96a8fd24'},\n", - " {'id': 'c0542ef2875bcfda54524a5459dfde2e'},\n", - " {'id': '4fa4d8bff823e55174381d36bf22113c'}],\n", - " 'e02': [{'id': '072a058bab827b0ec5805c1f05cc00db'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3880'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'fc2c80dbdecabd95d4de23e116d7604a'}],\n", - " 'e02': [{'id': '67942d5ff32910c90f5c85400855ae53'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2735'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '300d2358ffdf4c73ae063c9abf82f05e'}],\n", - " 'e02': [{'id': '8e6378e79968e5912499d8c2d932443a'},\n", - " {'id': '0fb050a31375d60e210f2c430449d98f'},\n", - " {'id': '64cfadab0fb8f361918d1966d9ec6f1e'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:59'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '57ad8ff997f564859a5879dd7561aea0'},\n", - " {'id': 'e2d9e66967a218812f4dc2d353a83b24'}],\n", - " 'e02': [{'id': 'd33388b7a4ad138d045e5cbbf4f248bf'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:174'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'a8ed99bfb433990227428a47c29678b5'},\n", - " {'id': '7015ab42f5ba8352dfed1bdc576aefb9'}],\n", - " 'e02': [{'id': 'a72e170807d1ff9d6a428a5f0c1ca2f8'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:2026'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'aebafb30d231255f520e2aeda024e51e'},\n", - " {'id': '3067428f97dbc099bcd77ecd34eb4d32'},\n", - " {'id': '124612c9409417ef94c745d737e744b0'}],\n", - " 'e02': [{'id': '8590534a640a3af0a5efeac0a1e82737'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:1113'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '73a68c1bdf2a4e6f51661c257be6ee12'}],\n", - " 'e02': [{'id': '90b70f6bb73bf4c75c7602e849c7792c'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:3398'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '3f649c8d2050c3d7fd7add4d69346028'}],\n", - " 'e02': [{'id': 'b632f4fcc32ec754ff83b4f4c4d505c2'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:211'}],\n", - " 'n1': [{'id': 'NCBIGene:6277'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5354998/bin/nihms843846f10.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC5354998',\n", - " 'score': 52.49851},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '23d9d84c056d6593b69452e6e6d287ce'}],\n", - " 'e02': [{'id': '8184f46bc16ca1e10b21a535c04aafa3'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4585'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': '184a4e2a71eae23de7dae4b31842c5c1'},\n", - " {'id': '85dca12f22f42cfdb36b71782a0576cf'},\n", - " {'id': 'bdd2eefd59c462c039f1d394be3b2178'}],\n", - " 'e02': [{'id': '20f71adcf6bf00eccf752f93b4665ec8'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:3856'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4677515/bin/fig-1.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC4677515',\n", - " 'score': 51.81472},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'fed559325e36451981f441f6d92efe93'},\n", - " {'id': '771b9d63d6c60f51b615333dbfee2b3d'}],\n", - " 'e02': [{'id': '6d3903a11324e697d3269e2ec9126eba'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:4684'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0},\n", - " {'edge_bindings': {'e01': [{'id': 'c78799b7425800886190398df9d89838'},\n", - " {'id': 'b48bc969430ea6993e22b029488a47c2'}],\n", - " 'e02': [{'id': 'fda666f9517e96f7bf963481387ad15b'}]},\n", - " 'node_bindings': {'n0': [{'id': 'NCBIGene:3855'}],\n", - " 'n1': [{'id': 'NCBIGene:1080'}],\n", - " 'n2': [{'id': 'PUBCHEM.COMPOUND:3121'}]},\n", - " 'pfocr': {'figureUrl': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826333/bin/or-42-06-2561-g01.jpg',\n", - " 'nodes': ['n0', 'n1'],\n", - " 'pmc': 'PMC6826333',\n", - " 'score': 104.711754},\n", - " 'score': 0}]" + " figure_count\n", + "n0 n1 n2 \n", + "ALAS1 ALAD Valproic acid 34\n", + " UROS Valproic acid 28\n", + " CPOX Valproic acid 17\n", + "KRT7 KRT19 Valproic acid 3\n", + " KRT8 Valproic acid 3\n", + "... ...\n", + "ALAS1 TFPI2 Valproic acid 0\n", + " TBP Valproic acid 0\n", + " TBL1XR1 Valproic acid 0\n", + " SUZ12 Valproic acid 0\n", + "TRUB2 ZNF165 Valproic acid 0\n", + "\n", + "[356 rows x 1 columns]" + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
figure_count
n0n1n2
ALAS1ALADValproic acid34
UROSValproic acid28
CPOXValproic acid17
KRT7KRT19Valproic acid3
KRT8Valproic acid3
............
ALAS1TFPI2Valproic acid0
TBPValproic acid0
TBL1XR1Valproic acid0
SUZ12Valproic acid0
TRUB2ZNF165Valproic acid0
\n", + "

356 rows × 1 columns

\n", + "
\n", + " \n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n", + " " ] }, "metadata": {}, - "execution_count": 10 + "execution_count": 120 } ] }, + { + "cell_type": "markdown", + "source": [ + "## Display some figures" + ], + "metadata": { + "id": "H4oQCpp-oUZU" + } + }, { "cell_type": "code", "source": [ - "print(f\"{len(cooccurring_bte_results)} BTE results (out of {len(bte_results)} total) have pfocr figures\")" + "from IPython.display import Image\n", + "from IPython.core.display import HTML \n", + "\n", + "\n", + "for i, df in bte_df[(bte_df[\"n0_identifier\"] == \"NCBIGene:211\") & (bte_df[\"n1_identifier\"] == \"NCBIGene:210\")][[\"figure_url\", \"figure_title\"]].iterrows():\n", + " figure_title = df[\"figure_title\"]\n", + " figure_url = df[\"figure_url\"]\n", + " display(Image(url=figure_url))\n", + " print(figure_title)\n", + " print(\"\")\n", + " print(\"\")\n", + " print(\"\")\n" ], "metadata": { "colab": { - "base_uri": "https://localhost:8080/" + "base_uri": "https://localhost:8080/", + "height": 1000 }, - "id": "N1RxoljKoelD", - "outputId": "6107c3ea-38e5-4070-fe44-8e92310d769b" + "id": "1iqomqP3t1C5", + "outputId": "8882419c-7213-4b54-eba3-becd28733c28" }, - "execution_count": 11, + "execution_count": 140, "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, { "output_type": "stream", "name": "stdout", "text": [ - "49 BTE results (out of 356 total) have pfocr figures\n" + "Evolution of the Tetrapyrrole Biosynthetic Pathway in Secondary Algae: Conservation, Redundancy and Replacement\n", + "\n", + "\n", + "\n" ] - } - ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Evolution of the Tetrapyrrole Biosynthetic Pathway in Secondary Algae: Conservation, Redundancy and Replacement\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthesis\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Increase of microRNA-210, Decrease of Raptor Gene Expression and Alteration of Mammalian Target of Rapamycin Regulated Proteins following Mithramycin Treatment of Human Erythroid Cells\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthesis pathway (left) and the principle of HAL mediated PpIX production enhancement with dimethylsulphoxide (DMSO) or deferoxamine mesylate salt (DFO) (right)\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Schematic of porphyrin-synthetic pathway to illustrate potential control points for increased PpIX accumulation\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthesis\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Haem synthetic pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthesis pathway (in red) connects with glucose (in green) and glutamine (in blue) metabolic pathways\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Tetrapyrrole biosynthetic pathways in prokaryotes\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Metabolic pathway differences between LLO118 and LLO56 and identification of mGPD2 as a candidate gene\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Enzymes and intermediate products of the heme synthesis pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme Biosynthetic Pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Haem synthesis pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme synthesis pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Iron metabolic pathways in the processes of sponge plasticity\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "A: The heme biosynthetic pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Evolution of haem biosynthetic and degradative pathways\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Sequence Evidence for the Presence of Two Tetrapyrrole Pathways in Euglena gracilis\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Four identified pathways responsible for P\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The metabolic pathway of FECH and heme\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthetic pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthetic pathway and experimental porphyria models\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthetic pathway, porphyrias and nutrients\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Scheme of the heme biosynthesis pathway and membrane transporters\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Leishmania heme auxotrophy\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Chemical heme biosynthesis pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme biosynthesis pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The Heme Biosynthetic Pathway of the Obligate Wolbachia Endosymbiont of Brugia malayi as a Potential Anti-filarial Drug Target\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Iron Necessity: The Secret of Wolbachia's Success?\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme-dependent feedback inhibition of ALAS in the heme biosynthetic pathway\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The metabolic roles of the endosymbiotic organelles of Toxoplasma and Plasmodium spp.\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Metabolic pathway of aerial and submerged mycelia in the liquid surface culture of Cordyceps militaris\n", + "\n", + "\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Heme metabolism\n", + "\n", + "\n", + "\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "" + ], + "metadata": { + "id": "XaQvH-tQ1Zt0" + }, + "execution_count": null, + "outputs": [] } ] } \ No newline at end of file