diff Selenzyme_query.ipynb @ 0:ac027c9ace4d draft

planemo upload commit 9e24fae395aeaca30c5bcdef80a21b7decb04042-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Selenzyme_query.ipynb	Mon Apr 29 09:49:36 2019 -0400
@@ -0,0 +1,280 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import os\n",
+    "import sys\n",
+    "import time\n",
+    "import signal\n",
+    "import datetime\n",
+    "import logging\n",
+    "import copy\n",
+    "import requests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smarts = \"O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O>>O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O\"\n",
+    "targets = 2\n",
+    "noMSA = False"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Request with smarts string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_request_data = {'smarts': smarts, \"targets\": targets, \"noMSA\": noMSA}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "url = 'http://selenzyme.synbiochem.co.uk/REST'\n",
+    "url = 'http://localhost:5000/REST'\n",
+    "r = requests.post( os.path.join(url, 'Query') , json=all_request_data )\n",
+    "res = json.loads( r.content.decode('utf-8') )\n",
+    "assert res['data'] is not None\n",
+    "val = json.loads( res['data'] )\n",
+    "assert 'Seq. ID' in val and len(val['Seq. ID'])>0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'app': 'Selenzy',\n",
+       " 'author': 'Synbiochem',\n",
+       " 'data': '{\"Score\":{\"1\":163.7,\"2\":155.9},\"Seq. ID\":{\"1\":\"Q68XV9\",\"2\":\"P85951\"},\"Description\":{\"1\":\"Aspartate aminotransferase\",\"2\":\"Aspartate aminotransferase 2 (Fragments)\"},\"Organism Source\":{\"1\":\"Rickettsia typhi (strain ATCC VR-144 \\\\/ Wilmington) \",\"2\":\"Pseudotsuga menziesii PE=1 SV=1\"},\"Tax. distance\":{\"1\":15,\"2\":23},\"Rxn. ID\":{\"1\":\"MNXR32641\",\"2\":\"MNXR32641\"},\"EC Number\":{\"1\":\"2.6.1.1\",\"2\":\"2.6.1.1\"},\"Uniprot protein evidence\":{\"1\":3,\"2\":1},\"Consv. Score\":{\"1\":79.0,\"2\":79.0},\"Rxn Sim.\":{\"1\":1.0,\"2\":1.0},\"Direction Used\":{\"1\":1,\"2\":1},\"Direction Preferred\":{\"1\":0,\"2\":0},\"% helices\":{\"1\":42.6,\"2\":27.8},\"% sheets\":{\"1\":24.8,\"2\":72.2},\"% turns\":{\"1\":19.6,\"2\":5.6},\"% coils\":{\"1\":17.2,\"2\":83.3},\"Mol. Weight\":{\"1\":44337.23,\"2\":3587.11},\"Isoelec. Point\":{\"1\":8.3119,\"2\":10.4338},\"Polar %\":{\"1\":45.113,\"2\":41.176},\"Query\":{\"1\":\"O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O>>O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O\",\"2\":\"O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O>>O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O\"},\"Hit\":{\"1\":\"O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O>>O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O\",\"2\":\"O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O>>O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O\"}}',\n",
+       " 'version': '1.0'}"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Score': {'1': 136.7, '2': 125.9}, 'Seq. ID': {'1': 'P39643', '2': 'E9L7A5'}, 'Description': {'1': 'Probable aspartate aminotransferase', '2': 'Bifunctional aspartate aminotransferase and glutamate/aspartate-prephenate aminotransferase'}, 'Organism Source': {'1': 'Bacillus subtilis (strain 168) ', '2': 'Petunia hybrida PE=1 SV=1'}, 'Tax. distance': {'1': 18, '2': 29}, 'Rxn. ID': {'1': 'MNXR32641', '2': 'MNXR32641'}, 'EC Number': {'1': '2.6.1.1', '2': '2.6.1.1'}, 'Uniprot protein evidence': {'1': 3, '2': 1}, 'Consv. Score': {'1': 55.0, '2': 55.0}, 'Rxn Sim.': {'1': 1.0, '2': 1.0}, 'Direction Used': {'1': 1, '2': 1}, 'Direction Preferred': {'1': 0, '2': 0}, '% helices': {'1': 51.4, '2': 31.3}, '% sheets': {'1': 16.2, '2': 29.4}, '% turns': {'1': 13.8, '2': 18.6}, '% coils': {'1': 22.7, '2': 24.2}, 'Mol. Weight': {'1': 44702.91, '2': 51743.31}, 'Isoelec. Point': {'1': 5.4491, '2': 8.6228}, 'Polar %': {'1': 42.105, '2': 43.841}, 'Query': {'1': 'O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O>>O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O', '2': 'O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O>>O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O'}, 'Hit': {'1': 'O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O>>O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O', '2': 'O=C([O-])CC(=O)C(=O)[O-].NC(CCC(=O)[O-])C(=O)O>>O=C([O-])CCC(=O)C(=O)[O-].NC(CC(=O)[O-])C(=O)O'}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(val)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Request with reaction DB and reaction ID following indications on http://selenzyme.synbiochem.co.uk/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_request_data = {\"db\": \"mnx\", \"rxnid\": \"MNXR141534\", \"targets\": targets, \"noMSA\": noMSA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "ename": "AssertionError",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-7-b6f4ae0ef527>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpost\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Query'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m,\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mall_request_data\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontent\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'utf-8'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32massert\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'data'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0mval\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'data'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;32massert\u001b[0m \u001b[0;34m'Seq. ID'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mval\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mval\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Seq. ID'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m>\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mAssertionError\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "url = 'http://selenzyme.synbiochem.co.uk/REST'\n",
+    "r = requests.post( os.path.join(url, 'Query') , json=all_request_data )\n",
+    "res = json.loads( r.content.decode('utf-8') )\n",
+    "assert res['data'] is not None\n",
+    "val = json.loads( res['data'] )\n",
+    "assert 'Seq. ID' in val and len(val['Seq. ID'])>0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Same reaction with its sabiork id"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_request_data = {\"db\": \"sabiork\", \"rxnid\": \"12346\", \"targets\": targets, \"noMSA\": noMSA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AssertionError",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-9-b6f4ae0ef527>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpost\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Query'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m,\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mall_request_data\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontent\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'utf-8'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32massert\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'data'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0mval\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'data'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;32massert\u001b[0m \u001b[0;34m'Seq. ID'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mval\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mval\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Seq. ID'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m>\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mAssertionError\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "url = 'http://selenzyme.synbiochem.co.uk/REST'\n",
+    "r = requests.post( os.path.join(url, 'Query') , json=all_request_data )\n",
+    "res = json.loads( r.content.decode('utf-8') )\n",
+    "assert res['data'] is not None\n",
+    "val = json.loads( res['data'] )\n",
+    "assert 'Seq. ID' in val and len(val['Seq. ID'])>0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "same reaction with its EC number"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_request_data = {\"db\": \"ec\", \"rxnid\": \"3.2.1.2\", \"targets\": targets, \"noMSA\": noMSA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "url = 'http://selenzyme.synbiochem.co.uk/REST'\n",
+    "r = requests.post( os.path.join(url, 'Query') , json=all_request_data )\n",
+    "res = json.loads( r.content.decode('utf-8') )\n",
+    "assert res['data'] is not None\n",
+    "val = json.loads( res['data'] )\n",
+    "assert 'Seq. ID' in val and len(val['Seq. ID'])>0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'app': 'Selenzy',\n",
+       " 'author': 'Synbiochem',\n",
+       " 'data': '{\"Score\":{\"1\":134.6,\"2\":121.9},\"Seq. ID\":{\"1\":\"Q9HHC8\",\"2\":\"O23553\"},\"Description\":{\"1\":\"Cyclomaltodextrinase\",\"2\":\"Beta-amylase 3; chloroplastic\"},\"Organism Source\":{\"1\":\"Thermococcus sp. B1001 \",\"2\":\"Arabidopsis thaliana \"},\"Tax. distance\":{\"1\":16,\"2\":29},\"Rxn. ID\":{\"1\":\"MNXR87651\",\"2\":\"MNXR87683\"},\"EC Number\":{\"1\":\"3.2.1\",\"2\":\"3.2.1.2\"},\"Uniprot protein evidence\":{\"1\":4,\"2\":1},\"Consv. Score\":{\"1\":51.0,\"2\":51.0},\"Rxn Sim.\":{\"1\":1.0,\"2\":1.0},\"Direction Used\":{\"1\":-1,\"2\":-1},\"Direction Preferred\":{\"1\":-1,\"2\":-1},\"% helices\":{\"1\":45.7,\"2\":33.8},\"% sheets\":{\"1\":20.7,\"2\":17.9},\"% turns\":{\"1\":18.5,\"2\":24.6},\"% coils\":{\"1\":17.7,\"2\":26.7},\"Mol. Weight\":{\"1\":78842.79,\"2\":61353.16},\"Isoelec. Point\":{\"1\":9.1162,\"2\":7.0599},\"Polar %\":{\"1\":45.455,\"2\":47.993},\"Query\":{\"1\":\"O.[*]OC1C(CO)OC(OC2C(CO)OC(O)C(O)C2O)C(O)C1O>>OCC1OC(OC2C(CO)OC(O)C(O)C2O)C(O)C(O)C1O\",\"2\":\"O.[*]OC1C(CO)OC(OC2C(CO)OC(O)C(O)C2O)C(O)C1O>>OCC1OC(OC2C(CO)OC(O)C(O)C2O)C(O)C(O)C1O\"},\"Hit\":{\"1\":\"O.[*]OC1C(CO)OC(OC2C(CO)OC(OC3C(CO)OC(O)C(O)C3O)C(O)C2O)C(O)C1O>>OCC1OC(OC2C(CO)OC(O)C(O)C2O)C(O)C(O)C1O.OCC1OC(O)C(O)C(O)C1O\",\"2\":\"O.[*]OC1C(CO)OC(OC2C(CO)OC(O)C(O)C2O)C(O)C1O>>OCC1OC(OC2C(CO)OC(O)C(O)C2O)C(O)C(O)C1O.[*]OC1C(CO)OC(OC2C(CO)OC(O)C(O)C2O)C(O)C1O\"}}',\n",
+       " 'version': '1.0'}"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "anaconda-cloud": {},
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}