diff --git a/notebooks/Tutorial.ipynb b/notebooks/Tutorial.ipynb index 1f397a7..3d27b06 100644 --- a/notebooks/Tutorial.ipynb +++ b/notebooks/Tutorial.ipynb @@ -13,8 +13,23 @@ "cell_type": "code", "execution_count": 1, "id": "d5507142", - "metadata": {}, + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:09:20.179225Z", + "start_time": "2021-12-06T09:07:56.474635Z" + } + }, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Collecting all CT data: 100%|████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.29it/s]\n", + "Parsing and importing clinical trials data: 100%|███████████████████████████████| 1600/1600 [00:00<00:00, 69571.70it/s]\n", + "Parsing and importing drug data: 100%|█████████████████████████████████████████| 10000/10000 [00:04<00:00, 2280.53it/s]\n", + "Parsing and importing drug data: 100%|███████████████████████████████████████████| 3580/3580 [00:01<00:00, 2682.83it/s]\n" + ] + }, { "data": { "text/html": [ @@ -36,95 +51,89 @@ " \n", " \n", " \n", - " id\n", - " pmod_type\n", - " target_bel\n", - " target_symbol\n", - " target_type\n", - " relation_type\n", - " interactor_bel\n", - " interactor_name\n", - " interactor_type\n", + " target_species\n", " pmid\n", " pmc\n", - " target_species\n", + " interactor_type\n", + " interactor_name\n", + " interactor_bel\n", + " relation_type\n", + " target_bel\n", + " target_type\n", + " target_symbol\n", + " pmod_type\n", " \n", " \n", " \n", " \n", " 0\n", - " 1\n", - " pho\n", - " p(HGNC:\"MAPT\",loc(MESHA:\"Cerebrospinal Fluid\")...\n", - " MAPT\n", + " 9606\n", + " 28768545\n", + " PMC5541421\n", " protein\n", - " increases\n", - " p(HGNC:\"TREM2\",var(\"p.Arg47His\"))\n", " TREM2\n", + " p(HGNC:\"TREM2\",var(\"p.Arg47His\"))\n", + " increases\n", + " p(HGNC:\"MAPT\",loc(MESHA:\"Cerebrospinal Fluid\")...\n", " protein\n", - " 28768545\n", - " PMC5541421\n", - " 9606\n", + " MAPT\n", + " pho\n", " \n", " \n", " 1\n", - " 4\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,S,357))\n", - " MAPT\n", + " 10116\n", + " 24270208\n", + " None\n", " protein\n", + " Dkk1\n", + " p(MGI:\"Dkk1\")\n", " increases\n", - " act(p(HGNC:\"GSK3B\"),ma(kin))\n", - " None\n", - " activity\n", - " 17389597\n", - " None\n", - " 9606\n", + " p(RGD:\"Mapt\",pmod(Ph,S,199))\n", + " protein\n", + " Mapt\n", + " pho\n", " \n", " \n", " 2\n", - " 5\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,S,357))\n", - " MAPT\n", - " protein\n", - " increases\n", - " act(p(HGNC:\"GSK3B\"),ma(kin))\n", + " 0\n", + " 14642273\n", " None\n", " activity\n", - " 17360711\n", " None\n", - " 9606\n", + " act(p(MGI:\"Cdk5\"),ma(kin))\n", + " directly_increases\n", + " p(MGI:\"Mapt\",pmod(Ph,S,239))\n", + " protein\n", + " Mapt\n", + " pho\n", " \n", " \n", " 3\n", - " 6\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", - " MAPT\n", - " protein\n", - " increases\n", - " a(MESHC:\"calyculin A\")\n", - " calyculin A\n", - " abundance\n", - " 21297267\n", - " None\n", " 9606\n", + " 17389597\n", + " None\n", + " activity\n", + " None\n", + " act(p(HGNC:\"GSK3B\"),ma(kin))\n", + " increases\n", + " p(HGNC:\"MAPT\",pmod(Ph,S,357))\n", + " protein\n", + " MAPT\n", + " pho\n", " \n", " \n", " 4\n", - " 7\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", - " MAPT\n", - " protein\n", - " increases\n", - " act(p(HGNC:\"CDK5\"),ma(kin))\n", + " 9606\n", + " 17360711\n", " None\n", " activity\n", - " 12387894\n", " None\n", - " 9606\n", + " act(p(HGNC:\"GSK3B\"),ma(kin))\n", + " increases\n", + " p(HGNC:\"MAPT\",pmod(Ph,S,357))\n", + " protein\n", + " MAPT\n", + " pho\n", " \n", " \n", " ...\n", @@ -139,142 +148,136 @@ " ...\n", " ...\n", " ...\n", - " ...\n", " \n", " \n", - " 962\n", - " 1147\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,T))\n", - " MAPT\n", - " protein\n", - " increases\n", - " act(p(HGNC:\"CDK5\"),ma(kin))\n", - " None\n", - " activity\n", + " 1147\n", + " 9606\n", " 23362255\n", " PMC3597833\n", - " 9606\n", - " \n", - " \n", - " 963\n", - " 1148\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,T))\n", - " MAPT\n", " protein\n", - " decreases\n", - " p(HGNC:\"PIN1\")\n", " PIN1\n", + " p(HGNC:\"PIN1\")\n", + " decreases\n", + " p(HGNC:\"MAPT\",pmod(Ph,T))\n", " protein\n", - " 23362255\n", - " PMC3597833\n", - " 9606\n", + " MAPT\n", + " pho\n", " \n", " \n", - " 964\n", - " 1149\n", - " pho\n", - " p(HGNC:\"MAPT\",pmod(Ph,T))\n", - " MAPT\n", - " protein\n", - " decreases\n", - " act(p(HGNC:\"PPP2CA\"),ma(phos))\n", - " None\n", - " activity\n", + " 1148\n", + " 9606\n", " 23362255\n", " PMC3597833\n", - " 9606\n", + " activity\n", + " None\n", + " act(p(HGNC:\"PPP2CA\"),ma(phos))\n", + " decreases\n", + " p(HGNC:\"MAPT\",pmod(Ph,T))\n", + " protein\n", + " MAPT\n", + " pho\n", " \n", " \n", - " 965\n", - " 1150\n", - " pho\n", - " p(HGNC:\"MAPT\",loc(CONSO:\"microtubule-binding r...\n", - " MAPT\n", + " 1149\n", + " 9606\n", + " 29661268\n", + " PMC6033068\n", " protein\n", - " decreases\n", - " p(HGNC:\"MAPT\",loc(CONSO:\"KXGS motif\"),pmod(Ac,...\n", " MAPT\n", + " p(HGNC:\"MAPT\",loc(CONSO:\"KXGS motif\"),pmod(Ac,...\n", + " decreases\n", + " p(HGNC:\"MAPT\",loc(CONSO:\"microtubule-binding r...\n", " protein\n", - " 29661268\n", - " PMC6033068\n", - " 9606\n", + " MAPT\n", + " pho\n", " \n", " \n", - " 966\n", - " 1151\n", - " pho\n", + " 1150\n", + " 9606\n", + " 30935091\n", + " PMC6480207\n", + " protein\n", + " HDAC6\n", + " p(HGNC:\"HDAC6\")\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", + " protein\n", " MAPT\n", + " pho\n", + " \n", + " \n", + " 1151\n", + " 10090\n", + " 22419736\n", + " None\n", " protein\n", + " Ak1\n", + " p(MGI:\"Ak1\")\n", " increases\n", - " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", + " p(MGI:\"Mapt\",pmod(Ph,T,235))\n", " protein\n", - " 30935091\n", - " PMC6480207\n", - " 9606\n", + " Mapt\n", + " pho\n", " \n", " \n", "\n", - "

967 rows × 12 columns

\n", + "

1152 rows × 11 columns

\n", "" ], "text/plain": [ - " id pmod_type target_bel \\\n", - "0 1 pho p(HGNC:\"MAPT\",loc(MESHA:\"Cerebrospinal Fluid\")... \n", - "1 4 pho p(HGNC:\"MAPT\",pmod(Ph,S,357)) \n", - "2 5 pho p(HGNC:\"MAPT\",pmod(Ph,S,357)) \n", - "3 6 pho p(HGNC:\"MAPT\",pmod(Ph,S,199)) \n", - "4 7 pho p(HGNC:\"MAPT\",pmod(Ph,S,199)) \n", - ".. ... ... ... \n", - "962 1147 pho p(HGNC:\"MAPT\",pmod(Ph,T)) \n", - "963 1148 pho p(HGNC:\"MAPT\",pmod(Ph,T)) \n", - "964 1149 pho p(HGNC:\"MAPT\",pmod(Ph,T)) \n", - "965 1150 pho p(HGNC:\"MAPT\",loc(CONSO:\"microtubule-binding r... \n", - "966 1151 pho p(HGNC:\"MAPT\",pmod(Ph,S,369)) \n", + " target_species pmid pmc interactor_type interactor_name \\\n", + "0 9606 28768545 PMC5541421 protein TREM2 \n", + "1 10116 24270208 None protein Dkk1 \n", + "2 0 14642273 None activity None \n", + "3 9606 17389597 None activity None \n", + "4 9606 17360711 None activity None \n", + "... ... ... ... ... ... \n", + "1147 9606 23362255 PMC3597833 protein PIN1 \n", + "1148 9606 23362255 PMC3597833 activity None \n", + "1149 9606 29661268 PMC6033068 protein MAPT \n", + "1150 9606 30935091 PMC6480207 protein HDAC6 \n", + "1151 10090 22419736 None protein Ak1 \n", "\n", - " target_symbol target_type relation_type \\\n", - "0 MAPT protein increases \n", - "1 MAPT protein increases \n", - "2 MAPT protein increases \n", - "3 MAPT protein increases \n", - "4 MAPT protein increases \n", - ".. ... ... ... \n", - "962 MAPT protein increases \n", - "963 MAPT protein decreases \n", - "964 MAPT protein decreases \n", - "965 MAPT protein decreases \n", - "966 MAPT protein increases \n", + " interactor_bel relation_type \\\n", + "0 p(HGNC:\"TREM2\",var(\"p.Arg47His\")) increases \n", + "1 p(MGI:\"Dkk1\") increases \n", + "2 act(p(MGI:\"Cdk5\"),ma(kin)) directly_increases \n", + "3 act(p(HGNC:\"GSK3B\"),ma(kin)) increases \n", + "4 act(p(HGNC:\"GSK3B\"),ma(kin)) increases \n", + "... ... ... \n", + "1147 p(HGNC:\"PIN1\") decreases \n", + "1148 act(p(HGNC:\"PPP2CA\"),ma(phos)) decreases \n", + "1149 p(HGNC:\"MAPT\",loc(CONSO:\"KXGS motif\"),pmod(Ac,... decreases \n", + "1150 p(HGNC:\"HDAC6\") increases \n", + "1151 p(MGI:\"Ak1\") increases \n", "\n", - " interactor_bel interactor_name \\\n", - "0 p(HGNC:\"TREM2\",var(\"p.Arg47His\")) TREM2 \n", - "1 act(p(HGNC:\"GSK3B\"),ma(kin)) None \n", - "2 act(p(HGNC:\"GSK3B\"),ma(kin)) None \n", - "3 a(MESHC:\"calyculin A\") calyculin A \n", - "4 act(p(HGNC:\"CDK5\"),ma(kin)) None \n", - ".. ... ... \n", - "962 act(p(HGNC:\"CDK5\"),ma(kin)) None \n", - "963 p(HGNC:\"PIN1\") PIN1 \n", - "964 act(p(HGNC:\"PPP2CA\"),ma(phos)) None \n", - "965 p(HGNC:\"MAPT\",loc(CONSO:\"KXGS motif\"),pmod(Ac,... MAPT \n", - "966 p(HGNC:\"HDAC6\") HDAC6 \n", + " target_bel target_type \\\n", + "0 p(HGNC:\"MAPT\",loc(MESHA:\"Cerebrospinal Fluid\")... protein \n", + "1 p(RGD:\"Mapt\",pmod(Ph,S,199)) protein \n", + "2 p(MGI:\"Mapt\",pmod(Ph,S,239)) protein \n", + "3 p(HGNC:\"MAPT\",pmod(Ph,S,357)) protein \n", + "4 p(HGNC:\"MAPT\",pmod(Ph,S,357)) protein \n", + "... ... ... \n", + "1147 p(HGNC:\"MAPT\",pmod(Ph,T)) protein \n", + "1148 p(HGNC:\"MAPT\",pmod(Ph,T)) protein \n", + "1149 p(HGNC:\"MAPT\",loc(CONSO:\"microtubule-binding r... protein \n", + "1150 p(HGNC:\"MAPT\",pmod(Ph,S,369)) protein \n", + "1151 p(MGI:\"Mapt\",pmod(Ph,T,235)) protein \n", "\n", - " interactor_type pmid pmc target_species \n", - "0 protein 28768545 PMC5541421 9606 \n", - "1 activity 17389597 None 9606 \n", - "2 activity 17360711 None 9606 \n", - "3 abundance 21297267 None 9606 \n", - "4 activity 12387894 None 9606 \n", - ".. ... ... ... ... \n", - "962 activity 23362255 PMC3597833 9606 \n", - "963 protein 23362255 PMC3597833 9606 \n", - "964 activity 23362255 PMC3597833 9606 \n", - "965 protein 29661268 PMC6033068 9606 \n", - "966 protein 30935091 PMC6480207 9606 \n", + " target_symbol pmod_type \n", + "0 MAPT pho \n", + "1 Mapt pho \n", + "2 Mapt pho \n", + "3 MAPT pho \n", + "4 MAPT pho \n", + "... ... ... \n", + "1147 MAPT pho \n", + "1148 MAPT pho \n", + "1149 MAPT pho \n", + "1150 MAPT pho \n", + "1151 Mapt pho \n", "\n", - "[967 rows x 12 columns]" + "[1152 rows x 11 columns]" ] }, "execution_count": 1, @@ -286,6 +289,8 @@ "#!pip install drugintfinder\n", "from drugintfinder.finder import InteractorFinder\n", "\n", + "import pandas as pd\n", + "\n", "# Initialize with base information\n", "finder = InteractorFinder(symbol=\"MAPT\", pmods=[\"pho\"], edge=\"causal\")\n", "\n", @@ -307,7 +312,12 @@ "cell_type": "code", "execution_count": 2, "id": "176a87ce", - "metadata": {}, + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:14:31.420305Z", + "start_time": "2021-12-06T09:14:10.856319Z" + } + }, "outputs": [ { "data": { @@ -330,149 +340,143 @@ " \n", " \n", " \n", - " id\n", " drug\n", - " drugbank_id\n", - " chembl_id\n", - " pubchem_id\n", - " interactor_type\n", + " capsule_interactor_type\n", + " capsule_interactor_bel\n", " interactor_bel\n", + " interactor_type\n", " interactor_name\n", - " capsule_interactor_bel\n", - " capsule_interactor_type\n", - " ...\n", + " relation_type\n", " target_bel\n", " target_symbol\n", " target_type\n", - " relation_type\n", - " pmod_type\n", " pmid\n", " pmc\n", + " rel_pub_year\n", " rel_rid\n", " drug_rel_rid\n", " drug_rel_actions\n", + " drugbank_id\n", + " chembl_id\n", + " pubchem_id\n", + " pmod_type\n", " \n", " \n", " \n", " \n", " 0\n", - " 1\n", " N'-(Pyrrolidino[2,1-B]Isoindolin-4-On-8-Yl)-N-...\n", - " DB04186\n", - " CHEMBL141247\n", - " 445840.0\n", - " protein\n", + " NaN\n", + " NaN\n", " p(HGNC:\"CDK2\")\n", + " protein\n", " CDK2\n", - " None\n", - " None\n", - " ...\n", + " directly_increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", " MAPT\n", " protein\n", - " directly_increases\n", - " pho\n", " 8282104\n", " None\n", + " 1994\n", " #570:10\n", " #1898:10624\n", " None\n", + " DB04186\n", + " CHEMBL141247\n", + " 445840.0\n", + " pho\n", " \n", " \n", " 1\n", - " 2\n", " 1-(3,5-DICHLOROPHENYL)-5-METHYL-1H-1,2,4-TRIAZ...\n", - " DB07852\n", - " None\n", - " 2763754.0\n", - " protein\n", + " NaN\n", + " NaN\n", " p(HGNC:\"CDK2\")\n", + " protein\n", " CDK2\n", - " None\n", - " None\n", - " ...\n", + " directly_increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", " MAPT\n", " protein\n", - " directly_increases\n", - " pho\n", " 8282104\n", " None\n", + " 1994\n", " #570:10\n", " #1898:10917\n", " None\n", + " DB07852\n", + " None\n", + " 2763754.0\n", + " pho\n", " \n", " \n", " 2\n", - " 3\n", " N(6)-dimethylallyladenine\n", - " DB08768\n", - " CHEMBL476189\n", - " 92180.0\n", - " protein\n", + " NaN\n", + " NaN\n", " p(HGNC:\"CDK2\")\n", + " protein\n", " CDK2\n", - " None\n", - " None\n", - " ...\n", + " directly_increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", " MAPT\n", " protein\n", - " directly_increases\n", - " pho\n", " 8282104\n", " None\n", + " 1994\n", " #570:10\n", " #1898:11306\n", " None\n", + " DB08768\n", + " CHEMBL476189\n", + " 92180.0\n", + " pho\n", " \n", " \n", " 3\n", - " 4\n", " (5E)-2-Amino-5-(2-pyridinylmethylene)-1,3-thia...\n", - " DB07529\n", - " None\n", - " 46937079.0\n", - " protein\n", + " NaN\n", + " NaN\n", " p(HGNC:\"CDK2\")\n", + " protein\n", " CDK2\n", - " None\n", - " None\n", - " ...\n", + " directly_increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", " MAPT\n", " protein\n", - " directly_increases\n", - " pho\n", " 8282104\n", " None\n", + " 1994\n", " #570:10\n", " #1898:11332\n", " None\n", + " DB07529\n", + " None\n", + " 46937079.0\n", + " pho\n", " \n", " \n", " 4\n", - " 5\n", " 4-{5-[(Z)-(2-IMINO-4-OXO-1,3-THIAZOLIDIN-5-YLI...\n", - " DB07534\n", - " CHEMBL233149\n", - " 5729339.0\n", - " protein\n", + " NaN\n", + " NaN\n", " p(HGNC:\"CDK2\")\n", + " protein\n", " CDK2\n", - " None\n", - " None\n", - " ...\n", + " directly_increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,199))\n", " MAPT\n", " protein\n", - " directly_increases\n", - " pho\n", " 8282104\n", " None\n", + " 1994\n", " #570:10\n", " #1899:10523\n", " None\n", + " DB07534\n", + " CHEMBL233149\n", + " 5729339.0\n", + " pho\n", " \n", " \n", " ...\n", @@ -496,213 +500,207 @@ " ...\n", " ...\n", " ...\n", - " ...\n", " \n", " \n", - " 57951\n", - " 57952\n", + " 54760\n", " Bufexamac\n", - " DB13346\n", - " CHEMBL94394\n", - " 2466.0\n", " protein\n", " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", " p(HGNC:\"HDAC6\")\n", " protein\n", - " ...\n", + " HDAC6\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", " MAPT\n", " protein\n", - " increases\n", - " pho\n", " 30935091\n", " PMC6480207\n", + " 2019\n", " #557:788\n", " #1900:11395\n", " inhibitor\n", + " DB13346\n", + " CHEMBL94394\n", + " 2466.0\n", + " pho\n", " \n", " \n", - " 57952\n", - " 57953\n", + " 54761\n", " Debio-1347\n", - " None\n", - " None\n", - " None\n", " protein\n", " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", " p(HGNC:\"HDAC6\")\n", " protein\n", - " ...\n", + " HDAC6\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", " MAPT\n", " protein\n", - " increases\n", - " pho\n", " 30935091\n", " PMC6480207\n", + " 2019\n", " #557:788\n", " #1911:11461\n", " inhibitor\n", + " None\n", + " None\n", + " NaN\n", + " pho\n", " \n", " \n", - " 57953\n", - " 57954\n", + " 54762\n", " indirubin-3'-monoxime\n", - " None\n", - " None\n", - " None\n", " protein\n", " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", " p(HGNC:\"HDAC6\")\n", " protein\n", - " ...\n", + " HDAC6\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", " MAPT\n", " protein\n", - " increases\n", - " pho\n", " 30935091\n", " PMC6480207\n", + " 2019\n", " #557:788\n", " #1912:11461\n", " inhibitor\n", + " None\n", + " None\n", + " NaN\n", + " pho\n", " \n", " \n", - " 57954\n", - " 57955\n", + " 54763\n", " quercetin\n", - " None\n", - " None\n", - " None\n", " protein\n", " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", " p(HGNC:\"HDAC6\")\n", " protein\n", - " ...\n", + " HDAC6\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", " MAPT\n", " protein\n", - " increases\n", - " pho\n", " 30935091\n", " PMC6480207\n", + " 2019\n", " #557:788\n", " #1913:11461\n", " inhibitor\n", + " None\n", + " None\n", + " NaN\n", + " pho\n", " \n", " \n", - " 57955\n", - " 57956\n", + " 54764\n", " GW441756\n", - " None\n", - " None\n", - " None\n", " protein\n", " p(HGNC:\"HDAC6\")\n", - " HDAC6\n", " p(HGNC:\"HDAC6\")\n", " protein\n", - " ...\n", + " HDAC6\n", + " increases\n", " p(HGNC:\"MAPT\",pmod(Ph,S,369))\n", " MAPT\n", " protein\n", - " increases\n", - " pho\n", " 30935091\n", " PMC6480207\n", + " 2019\n", " #557:788\n", " #1898:11465\n", " inhibitor\n", + " None\n", + " None\n", + " NaN\n", + " pho\n", " \n", " \n", "\n", - "

57956 rows × 21 columns

\n", + "

57956 rows × 20 columns

\n", "" ], "text/plain": [ - " id drug drugbank_id \\\n", - "0 1 N'-(Pyrrolidino[2,1-B]Isoindolin-4-On-8-Yl)-N-... DB04186 \n", - "1 2 1-(3,5-DICHLOROPHENYL)-5-METHYL-1H-1,2,4-TRIAZ... DB07852 \n", - "2 3 N(6)-dimethylallyladenine DB08768 \n", - "3 4 (5E)-2-Amino-5-(2-pyridinylmethylene)-1,3-thia... DB07529 \n", - "4 5 4-{5-[(Z)-(2-IMINO-4-OXO-1,3-THIAZOLIDIN-5-YLI... DB07534 \n", - "... ... ... ... \n", - "57951 57952 Bufexamac DB13346 \n", - "57952 57953 Debio-1347 None \n", - "57953 57954 indirubin-3'-monoxime None \n", - "57954 57955 quercetin None \n", - "57955 57956 GW441756 None \n", + " drug \\\n", + "0 N'-(Pyrrolidino[2,1-B]Isoindolin-4-On-8-Yl)-N-... \n", + "1 1-(3,5-DICHLOROPHENYL)-5-METHYL-1H-1,2,4-TRIAZ... \n", + "2 N(6)-dimethylallyladenine \n", + "3 (5E)-2-Amino-5-(2-pyridinylmethylene)-1,3-thia... \n", + "4 4-{5-[(Z)-(2-IMINO-4-OXO-1,3-THIAZOLIDIN-5-YLI... \n", + "... ... \n", + "54760 Bufexamac \n", + "54761 Debio-1347 \n", + "54762 indirubin-3'-monoxime \n", + "54763 quercetin \n", + "54764 GW441756 \n", "\n", - " chembl_id pubchem_id interactor_type interactor_bel \\\n", - "0 CHEMBL141247 445840.0 protein p(HGNC:\"CDK2\") \n", - "1 None 2763754.0 protein p(HGNC:\"CDK2\") \n", - "2 CHEMBL476189 92180.0 protein p(HGNC:\"CDK2\") \n", - "3 None 46937079.0 protein p(HGNC:\"CDK2\") \n", - "4 CHEMBL233149 5729339.0 protein p(HGNC:\"CDK2\") \n", - "... ... ... ... ... \n", - "57951 CHEMBL94394 2466.0 protein p(HGNC:\"HDAC6\") \n", - "57952 None None protein p(HGNC:\"HDAC6\") \n", - "57953 None None protein p(HGNC:\"HDAC6\") \n", - "57954 None None protein p(HGNC:\"HDAC6\") \n", - "57955 None None protein p(HGNC:\"HDAC6\") \n", + " capsule_interactor_type capsule_interactor_bel interactor_bel \\\n", + "0 NaN NaN p(HGNC:\"CDK2\") \n", + "1 NaN NaN p(HGNC:\"CDK2\") \n", + "2 NaN NaN p(HGNC:\"CDK2\") \n", + "3 NaN NaN p(HGNC:\"CDK2\") \n", + "4 NaN NaN p(HGNC:\"CDK2\") \n", + "... ... ... ... \n", + "54760 protein p(HGNC:\"HDAC6\") p(HGNC:\"HDAC6\") \n", + "54761 protein p(HGNC:\"HDAC6\") p(HGNC:\"HDAC6\") \n", + "54762 protein p(HGNC:\"HDAC6\") p(HGNC:\"HDAC6\") \n", + "54763 protein p(HGNC:\"HDAC6\") p(HGNC:\"HDAC6\") \n", + "54764 protein p(HGNC:\"HDAC6\") p(HGNC:\"HDAC6\") \n", "\n", - " interactor_name capsule_interactor_bel capsule_interactor_type ... \\\n", - "0 CDK2 None None ... \n", - "1 CDK2 None None ... \n", - "2 CDK2 None None ... \n", - "3 CDK2 None None ... \n", - "4 CDK2 None None ... \n", - "... ... ... ... ... \n", - "57951 HDAC6 p(HGNC:\"HDAC6\") protein ... \n", - "57952 HDAC6 p(HGNC:\"HDAC6\") protein ... \n", - "57953 HDAC6 p(HGNC:\"HDAC6\") protein ... \n", - "57954 HDAC6 p(HGNC:\"HDAC6\") protein ... \n", - "57955 HDAC6 p(HGNC:\"HDAC6\") protein ... \n", + " interactor_type interactor_name relation_type \\\n", + "0 protein CDK2 directly_increases \n", + "1 protein CDK2 directly_increases \n", + "2 protein CDK2 directly_increases \n", + "3 protein CDK2 directly_increases \n", + "4 protein CDK2 directly_increases \n", + "... ... ... ... \n", + "54760 protein HDAC6 increases \n", + "54761 protein HDAC6 increases \n", + "54762 protein HDAC6 increases \n", + "54763 protein HDAC6 increases \n", + "54764 protein HDAC6 increases \n", "\n", - " target_bel target_symbol target_type \\\n", - "0 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein \n", - "1 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein \n", - "2 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein \n", - "3 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein \n", - "4 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein \n", - "... ... ... ... \n", - "57951 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein \n", - "57952 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein \n", - "57953 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein \n", - "57954 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein \n", - "57955 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein \n", + " target_bel target_symbol target_type pmid \\\n", + "0 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein 8282104 \n", + "1 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein 8282104 \n", + "2 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein 8282104 \n", + "3 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein 8282104 \n", + "4 p(HGNC:\"MAPT\",pmod(Ph,S,199)) MAPT protein 8282104 \n", + "... ... ... ... ... \n", + "54760 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein 30935091 \n", + "54761 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein 30935091 \n", + "54762 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein 30935091 \n", + "54763 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein 30935091 \n", + "54764 p(HGNC:\"MAPT\",pmod(Ph,S,369)) MAPT protein 30935091 \n", "\n", - " relation_type pmod_type pmid pmc rel_rid \\\n", - "0 directly_increases pho 8282104 None #570:10 \n", - "1 directly_increases pho 8282104 None #570:10 \n", - "2 directly_increases pho 8282104 None #570:10 \n", - "3 directly_increases pho 8282104 None #570:10 \n", - "4 directly_increases pho 8282104 None #570:10 \n", - "... ... ... ... ... ... \n", - "57951 increases pho 30935091 PMC6480207 #557:788 \n", - "57952 increases pho 30935091 PMC6480207 #557:788 \n", - "57953 increases pho 30935091 PMC6480207 #557:788 \n", - "57954 increases pho 30935091 PMC6480207 #557:788 \n", - "57955 increases pho 30935091 PMC6480207 #557:788 \n", + " pmc rel_pub_year rel_rid drug_rel_rid drug_rel_actions \\\n", + "0 None 1994 #570:10 #1898:10624 None \n", + "1 None 1994 #570:10 #1898:10917 None \n", + "2 None 1994 #570:10 #1898:11306 None \n", + "3 None 1994 #570:10 #1898:11332 None \n", + "4 None 1994 #570:10 #1899:10523 None \n", + "... ... ... ... ... ... \n", + "54760 PMC6480207 2019 #557:788 #1900:11395 inhibitor \n", + "54761 PMC6480207 2019 #557:788 #1911:11461 inhibitor \n", + "54762 PMC6480207 2019 #557:788 #1912:11461 inhibitor \n", + "54763 PMC6480207 2019 #557:788 #1913:11461 inhibitor \n", + "54764 PMC6480207 2019 #557:788 #1898:11465 inhibitor \n", "\n", - " drug_rel_rid drug_rel_actions \n", - "0 #1898:10624 None \n", - "1 #1898:10917 None \n", - "2 #1898:11306 None \n", - "3 #1898:11332 None \n", - "4 #1899:10523 None \n", - "... ... ... \n", - "57951 #1900:11395 inhibitor \n", - "57952 #1911:11461 inhibitor \n", - "57953 #1912:11461 inhibitor \n", - "57954 #1913:11461 inhibitor \n", - "57955 #1898:11465 inhibitor \n", + " drugbank_id chembl_id pubchem_id pmod_type \n", + "0 DB04186 CHEMBL141247 445840.0 pho \n", + "1 DB07852 None 2763754.0 pho \n", + "2 DB08768 CHEMBL476189 92180.0 pho \n", + "3 DB07529 None 46937079.0 pho \n", + "4 DB07534 CHEMBL233149 5729339.0 pho \n", + "... ... ... ... ... \n", + "54760 DB13346 CHEMBL94394 2466.0 pho \n", + "54761 None None NaN pho \n", + "54762 None None NaN pho \n", + "54763 None None NaN pho \n", + "54764 None None NaN pho \n", "\n", - "[57956 rows x 21 columns]" + "[57956 rows x 20 columns]" ] }, "execution_count": 2, @@ -732,13 +730,19 @@ "cell_type": "code", "execution_count": 3, "id": "ffcc5bd7", - "metadata": {}, + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:19:05.740057Z", + "start_time": "2021-12-06T09:14:57.167220Z" + } + }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "Counting edges: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 80/80 [00:00<00:00, 881.72it/s]\n" + "Counting BioAssays for targets: 100%|██████████████████████████████████████████████████| 80/80 [01:18<00:00, 1.02it/s]\n", + "Counting edges: 100%|██████████████████████████████████████████████████████████████████| 80/80 [02:48<00:00, 2.11s/it]\n" ] }, { @@ -775,58 +779,58 @@ " \n", " \n", " 0\n", - " 4-((3r,4s,5r)-4-Amino-3,5-Dihydroxy-Hex-1-Ynyl...\n", - " CDK2\n", + " [4-({4-[(5-cyclopropyl-1H-pyrazol-3-yl)amino]q...\n", + " SRC\n", " N/A\n", - " 1518\n", - " 15\n", + " 1380\n", + " 50\n", " No\n", " No\n", - " N/A\n", + " 1\n", " \n", " \n", " 1\n", - " Indirubin-3'-monoxime\n", - " CDK5\n", + " 3-fluoro-N-1H-indol-5-yl-5-morpholin-4-ylbenza...\n", + " MAPK14\n", " N/A\n", - " 588\n", - " 41\n", + " 1508\n", + " 7\n", " No\n", " No\n", - " N/A\n", + " 1\n", " \n", " \n", " 2\n", - " GW441756\n", - " SYK\n", + " Epinephrine\n", + " TNF\n", " N/A\n", - " 527\n", - " 57\n", - " No\n", + " 128\n", + " 222\n", " No\n", - " N/A\n", + " Yes\n", + " 8\n", " \n", " \n", " 3\n", - " Halicin\n", - " MAPK10\n", - " N/A\n", - " 579\n", - " 0\n", - " No\n", - " No\n", - " N/A\n", + " Cevimeline\n", + " CHRM1\n", + " Yes\n", + " 1130\n", + " 9\n", + " Yes\n", + " Yes\n", + " 2\n", " \n", " \n", " 4\n", - " Phenobarbital\n", - " CHRNA7\n", + " Binimetinib\n", + " IL1B\n", " N/A\n", - " 398\n", - " 151\n", + " 5\n", + " 202\n", " No\n", " No\n", - " N/A\n", + " 5\n", " \n", " \n", " ...\n", @@ -841,58 +845,58 @@ " \n", " \n", " 853\n", - " 1-[4-(PYRIDIN-4-YLOXY)PHENYL]-3-[3-(TRIFLUOROM...\n", - " ABL1\n", + " Minocycline\n", + " MAPK12\n", " N/A\n", - " 1929\n", - " 10\n", - " No\n", + " 653\n", + " 6\n", " No\n", - " N/A\n", + " Yes\n", + " 23\n", " \n", " \n", " 854\n", - " Homatropine methylbromide\n", - " CHRM1\n", + " Aluminium phosphate\n", + " APP\n", " N/A\n", - " 1115\n", - " 9\n", + " 1135\n", + " 208\n", " No\n", " No\n", - " N/A\n", + " 4\n", " \n", " \n", " 855\n", - " (2E,3S)-3-hydroxy-5'-[(4-hydroxypiperidin-1-yl...\n", - " CDK2\n", + " Acetylsalicylic acid\n", + " MAPK1\n", " N/A\n", - " 1518\n", - " 15\n", + " 983\n", + " 30\n", " No\n", - " No\n", - " N/A\n", + " Yes\n", + " 28\n", " \n", " \n", " 856\n", - " XL228\n", - " ABL2\n", + " {4-[(2S)-2-Acetamido-3-({(1S)-1-[3-carbamoyl-4...\n", + " LCK\n", " N/A\n", - " 255\n", - " 1\n", + " 969\n", + " 8\n", " No\n", " No\n", - " N/A\n", + " 1\n", " \n", " \n", " 857\n", - " Regorafenib\n", - " ABL1\n", + " Vitamin E\n", + " PRKCA\n", " N/A\n", - " 1929\n", - " 10\n", - " No\n", + " 884\n", + " 18\n", " No\n", - " N/A\n", + " Yes\n", + " 10\n", " \n", " \n", "\n", @@ -901,56 +905,56 @@ ], "text/plain": [ " Drug Target Synergizes \\\n", - "0 4-((3r,4s,5r)-4-Amino-3,5-Dihydroxy-Hex-1-Ynyl... CDK2 N/A \n", - "1 Indirubin-3'-monoxime CDK5 N/A \n", - "2 GW441756 SYK N/A \n", - "3 Halicin MAPK10 N/A \n", - "4 Phenobarbital CHRNA7 N/A \n", + "0 [4-({4-[(5-cyclopropyl-1H-pyrazol-3-yl)amino]q... SRC N/A \n", + "1 3-fluoro-N-1H-indol-5-yl-5-morpholin-4-ylbenza... MAPK14 N/A \n", + "2 Epinephrine TNF N/A \n", + "3 Cevimeline CHRM1 Yes \n", + "4 Binimetinib IL1B N/A \n", ".. ... ... ... \n", - "853 1-[4-(PYRIDIN-4-YLOXY)PHENYL]-3-[3-(TRIFLUOROM... ABL1 N/A \n", - "854 Homatropine methylbromide CHRM1 N/A \n", - "855 (2E,3S)-3-hydroxy-5'-[(4-hydroxypiperidin-1-yl... CDK2 N/A \n", - "856 XL228 ABL2 N/A \n", - "857 Regorafenib ABL1 N/A \n", + "853 Minocycline MAPK12 N/A \n", + "854 Aluminium phosphate APP N/A \n", + "855 Acetylsalicylic acid MAPK1 N/A \n", + "856 {4-[(2S)-2-Acetamido-3-({(1S)-1-[3-carbamoyl-4... LCK N/A \n", + "857 Vitamin E PRKCA N/A \n", "\n", " Number of BioAssays for Target Number of Causal Edges for Target \\\n", - "0 1518 15 \n", - "1 588 41 \n", - "2 527 57 \n", - "3 579 0 \n", - "4 398 151 \n", + "0 1380 50 \n", + "1 1508 7 \n", + "2 128 222 \n", + "3 1130 9 \n", + "4 5 202 \n", ".. ... ... \n", - "853 1929 10 \n", - "854 1115 9 \n", - "855 1518 15 \n", - "856 255 1 \n", - "857 1929 10 \n", + "853 653 6 \n", + "854 1135 208 \n", + "855 983 30 \n", + "856 969 8 \n", + "857 884 18 \n", "\n", " Drug Patent Ongoing Generic Version of Drug Available \\\n", "0 No No \n", "1 No No \n", - "2 No No \n", - "3 No No \n", + "2 No Yes \n", + "3 Yes Yes \n", "4 No No \n", ".. ... ... \n", - "853 No No \n", + "853 No Yes \n", "854 No No \n", - "855 No No \n", + "855 No Yes \n", "856 No No \n", - "857 No No \n", + "857 No Yes \n", "\n", " Number of Drug Targets \n", - "0 N/A \n", - "1 N/A \n", - "2 N/A \n", - "3 N/A \n", - "4 N/A \n", + "0 1 \n", + "1 1 \n", + "2 8 \n", + "3 2 \n", + "4 5 \n", ".. ... \n", - "853 N/A \n", - "854 N/A \n", - "855 N/A \n", - "856 N/A \n", - "857 N/A \n", + "853 23 \n", + "854 4 \n", + "855 28 \n", + "856 1 \n", + "857 10 \n", "\n", "[858 rows x 8 columns]" ] @@ -969,6 +973,401 @@ "summary" ] }, + { + "cell_type": "code", + "execution_count": 23, + "id": "e0dab569", + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:34:57.287676Z", + "start_time": "2021-12-06T09:34:57.234674Z" + } + }, + "outputs": [ + { + "data": { + "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", + "
ProteinBioAssays per Drug
70F21106
64STAT3613
63RPS6KB1387
73CSNK1D367
42GSK3A365
62MAPK11235
40MAPK13207
33HDAC6204
54CDK5R1201
76MARK1188
\n", + "
" + ], + "text/plain": [ + " Protein BioAssays per Drug\n", + "70 F2 1106\n", + "64 STAT3 613\n", + "63 RPS6KB1 387\n", + "73 CSNK1D 367\n", + "42 GSK3A 365\n", + "62 MAPK11 235\n", + "40 MAPK13 207\n", + "33 HDAC6 204\n", + "54 CDK5R1 201\n", + "76 MARK1 188" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bioassays_per_drug = []\n", + "\n", + "for interactor in summary.Target.unique():\n", + " drugs = len(summary[summary.Target == interactor].Drug.unique())\n", + " bioassays = summary[summary.Target == interactor][\"Number of BioAssays for Target\"].iloc[0]\n", + " bioassays_per_drug.append({\"Protein\": interactor, \"BioAssays per Drug\": bioassays // drugs})\n", + "\n", + "ratio_df = pd.DataFrame(bioassays_per_drug)\n", + "ratio_df.sort_values(\"BioAssays per Drug\", ascending=False)[:10]" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "1c434d6e", + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:34:03.996914Z", + "start_time": "2021-12-06T09:34:03.981913Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "1135" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "summary[summary.Target == \"APP\"][\"Number of BioAssays for Target\"].iloc[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "63920910", + "metadata": { + "ExecuteTime": { + "end_time": "2021-12-06T09:27:43.996431Z", + "start_time": "2021-12-06T09:27:43.973404Z" + } + }, + "outputs": [ + { + "data": { + "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", + "
DrugTargetSynergizesNumber of BioAssays for TargetNumber of Causal Edges for TargetDrug Patent OngoingGeneric Version of Drug AvailableNumber of Drug TargetsBioAssays per Known Drug Target
8025-[3-(2-METHOXYPHENYL)-1H-PYRROLO[2,3-B]PYRIDI...ABL1N/A197010NoNo11970
7132-{[(6-OXO-1,6-DIHYDROPYRIDIN-3-YL)METHYL]AMIN...ABL1N/A197010NoNo11970
758RadotinibABL1N/A197010NoNo11970
2422-amino-5-[3-(1-ethyl-1H-pyrazol-5-yl)-1H-pyrr...ABL1N/A197010NoNo11970
612PD-166326ABL1N/A197010NoNo11970
..............................
296quercetinCAMK2BN/A18110NoNoN/A0
289Pyridoxal phosphateDDCNo82NoYes560
777PolaprezincIL6N/A799NoNo80
279Foreskin fibroblast (neonatal)IL6No799NoNo110
268quercetinHDAC6N/A2042180NoNoN/A0
\n", + "

858 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Drug Target Synergizes \\\n", + "802 5-[3-(2-METHOXYPHENYL)-1H-PYRROLO[2,3-B]PYRIDI... ABL1 N/A \n", + "713 2-{[(6-OXO-1,6-DIHYDROPYRIDIN-3-YL)METHYL]AMIN... ABL1 N/A \n", + "758 Radotinib ABL1 N/A \n", + "242 2-amino-5-[3-(1-ethyl-1H-pyrazol-5-yl)-1H-pyrr... ABL1 N/A \n", + "612 PD-166326 ABL1 N/A \n", + ".. ... ... ... \n", + "296 quercetin CAMK2B N/A \n", + "289 Pyridoxal phosphate DDC No \n", + "777 Polaprezinc IL6 N/A \n", + "279 Foreskin fibroblast (neonatal) IL6 No \n", + "268 quercetin HDAC6 N/A \n", + "\n", + " Number of BioAssays for Target Number of Causal Edges for Target \\\n", + "802 1970 10 \n", + "713 1970 10 \n", + "758 1970 10 \n", + "242 1970 10 \n", + "612 1970 10 \n", + ".. ... ... \n", + "296 181 10 \n", + "289 8 2 \n", + "777 7 99 \n", + "279 7 99 \n", + "268 2042 180 \n", + "\n", + " Drug Patent Ongoing Generic Version of Drug Available \\\n", + "802 No No \n", + "713 No No \n", + "758 No No \n", + "242 No No \n", + "612 No No \n", + ".. ... ... \n", + "296 No No \n", + "289 No Yes \n", + "777 No No \n", + "279 No No \n", + "268 No No \n", + "\n", + " Number of Drug Targets BioAssays per Known Drug Target \n", + "802 1 1970 \n", + "713 1 1970 \n", + "758 1 1970 \n", + "242 1 1970 \n", + "612 1 1970 \n", + ".. ... ... \n", + "296 N/A 0 \n", + "289 56 0 \n", + "777 8 0 \n", + "279 11 0 \n", + "268 N/A 0 \n", + "\n", + "[858 rows x 9 columns]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summary.sort_values(by=\"BioAssays per Known Drug Target\", ascending=False)" + ] + }, { "cell_type": "markdown", "id": "2d7e196d", @@ -1228,9 +1627,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.2" + "version": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 -} \ No newline at end of file +}