pubmed-disambig.ipynb

{
 "metadata": {
  "name": "pubmed-disambig"
 }, 
 "name": "pubmed-disambig", 
 "nbformat": 2, 
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown", 
     "source": "#Pubmed disambiguation service\n\nWe were able to ingest a significant amount of faculty publications into VIVO from faculty CVs.  We have this data stored\nin a separate VIVO instance.  We can use this data to ingest new publications for faculty using a web service\nfrom the Harvard profiles systems.  \n\nhttp://profiles.catalyst.harvard.edu/Meetings/ProfilesRNSDisambiguation120120.pdf"
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "import vdm\nimport catalyst\ncatalyst.get_pubs('jteno')", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "stream", 
       "stream": "stderr", 
       "text": "<?xml version=\"1.0\" ?>\n<FindPMIDs>\n\t<Name>\n\t\t<First>Joan</First>\n\t\t<Last>Teno</Last>\n\t</Name>\n\t<EmailList>\n\t\t<email>joan_teno@brown.edu</email>\n\t</EmailList>\n\t<AffiliationList>\n\t\t<Affiliation>%Brown University%</Affiliation>\n\t\t<Affiliation>%@brown.edu%</Affiliation>\n\t</AffiliationList>\n\t<LocalDuplicateNames>1</LocalDuplicateNames>\n\t<RequireFirstName>false</RequireFirstName>\n\t<MatchThreshold>0.98</MatchThreshold>\n\t<PMIDAddList>\n\t\t<PMID>19468089</PMID>\n\t\t<PMID>21991894</PMID>\n\t\t<PMID>22587857</PMID>\n\t\t<PMID>21276698</PMID>\n\t\t<PMID>19327073</PMID>\n\t\t<PMID>19828530</PMID>\n\t\t<PMID>20398123</PMID>\n\t\t<PMID>21045099</PMID>\n\t\t<PMID>23002947</PMID>\n\t\t<PMID>22587857</PMID>\n\t\t<PMID>19426943</PMID>\n\t\t<PMID>21539524</PMID>\n\t\t<PMID>19255336</PMID>\n\t\t<PMID>21797834</PMID>\n\t\t<PMID>22727255</PMID>\n\t\t<PMID>20621437</PMID>\n\t\t<PMID>21143437</PMID>\n\t\t<PMID>22734023</PMID>\n\t\t<PMID>19187881</PMID>\n\t\t<PMID>22782196</PMID>\n\t\t<PMID>20145231</PMID>\n\t\t<PMID>22583382</PMID>\n\t\t<PMID>20532652</PMID>\n\t\t<PMID>20065203</PMID>\n\t</PMIDAddList>\n\t<PMIDExcludeList/>\n</FindPMIDs>\n\nDisambiguation service status code."
      }, 
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "\n    PREFIX xsd:   <http://www.w3.org/2001/XMLSchema#>\n    PREFIX bibo: <http://purl.org/ontology/bibo/>\n    PREFIX foaf: <http://xmlns.com/foaf/0.1/>\n    PREFIX vivo: <http://vivoweb.org/ontology/core#>\n    PREFIX bu: <http://vivo.brown.edu/individual/>\n    PREFIX blocal: <http://vivo.brown.edu/ontology/vivo-brown/>\n\n    SELECT ?f ?first ?middle ?last ?email ?pub ?pmid\n    WHERE\n    {\n          ?f a vivo:FacultyMember .\n          ?f blocal:shortId \"jteno\" .\n          ?f foaf:firstName ?first .\n          ?f foaf:lastName ?last .\n          ?f vivo:primaryEmail ?email .\n          OPTIONAL {?f vivo:middleName ?middle }\n          #?f vivo:personInPosition/vivo:positionInOrganization bu:org-brown-univ-dept58 .\n          ?f vivo:authorInAuthorship/vivo:linkedInformationResource ?pub .\n          ?pub bibo:doi ?doi .\n          ?pub bibo:pmid ?pmid .\n          ?pub vivo:dateTimeValue/vivo:dateTime ?dtv .\n          #FILTER (?dtv >= \"2009-01-01T00:00:00\"^^xsd:dateTime)\n    }\n    \n12854949"
      }, 
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "\n11347780\n8678391\n10069147\n10069146\n15190529\n22690916\n7776500\n10069149\n17341248\n18562157\n16043002\n9214246\n18271346\n9403743\n16108932\n10809474\n11099680\n11844628\n9670868\n15225329\n16199399\n17509813\n22871537\n8694674\n21130211\n12967728\n9245224\n24117283\n9679799\n23434175\n17087706\n19805664\n15673348\n9715857\n8003719\n15086658\n20420548\n23860991\n23347201\n10732940\n15262674\n11652116\n9686709\n15890038\n22213494\n7847645\n7571588\n7773427\n11434148\n11311096\n18215499\n15859855\n15974046\n8486905\n11059436\n16629555\n18294811\n10839009\n11943046\n9777906\n8790698\n2254571\n1997751\n7790978\n9100721\n9100722\n9100723\n8629646\n11532588\n10791277\n19995290\n20303027\n17608886\n10069150\n19211472\n11532587\n10809472\n16181162\n11643112\n12837714\n10474691\n15811976\n1706820\n11798477\n15571532\n17302654\n10809452\n12555059\n16274371\n16877177\n7860278\n21711122\n16499468\n9256845\n22940756\n2071815\n9100728\n12072667\n15471649\n8302322\n16917187\n8842929\n16917188\n15541622\n3392724\n22285282\n10068357\n10156190\n12076216\n18331293\n7860268\n19375273\n12854987\n10577294\n14709580\n9437445\n9496977\n23385273\n16505460\n9256855\n18216601\n15083099\n8123062\n14687333\n10809451\n10809457\n10809456\n10809459\n10809458\n23108341\n15673356\n2266430\n17684107\n17583469\n9215332\n9005760\n20129211\n10069151\n9225705\n8981191\n9736116\n9436083\n16310614\n17919879\n11532584\n10809460\n10809461\n17900854\n10612321\n7963209\n8790228"
      }, 
      {
       "output_type": "stream", 
       "stream": "stderr", 
       "text": " 200"
      }
     ], 
     "prompt_number": 2
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "", 
     "language": "python", 
     "outputs": []
    }
   ]
  }
 ]
}