{"data":{"id":"10.6084/m9.figshare.1257838","type":"dois","attributes":{"doi":"10.6084/m9.figshare.1257838","prefix":"10.6084","suffix":"m9.figshare.1257838","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Groza, Tudor","nameType":"Personal","givenName":"Tudor","familyName":"Groza","affiliation":[],"nameIdentifiers":[]},{"name":"Oellrich, Anika","nameType":"Personal","givenName":"Anika","familyName":"Oellrich","affiliation":[],"nameIdentifiers":[]},{"name":"Collier, Nigel","nameType":"Personal","givenName":"Nigel","familyName":"Collier","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"Silver standard concept annotations from biomedical texts with special relevance to phenotypes"}],"publisher":"figshare","container":{},"publicationYear":2014,"subjects":[{"subject":"Diseases"},{"subject":"Information Systems"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Computer and information sciences","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"60102 Bioinformatics","subjectScheme":"FOR"},{"subject":"Artificial Intelligence and Image Processing"}],"contributors":[],"dates":[{"date":"2014-12-04","dateType":"Created"},{"date":"2014-12-04","dateType":"Updated"},{"date":"2014","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["19749195 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This dataset documents the results achieved by applying four concept recognition systems to text minining phenotypes from unstructured data. It comprises the individual stand-off annotations created by the systems on four corpora. In addition, for each textual corpus, system-based silver standard corpora have been created using both exact matching, as well as sentence-level matching. The four systems are: * NCBO Annotator * MetaMap * cTAKES * BeCAS The four corpora are: * Pubmed: A corpus of 2,163 publication abstracts from Pubmed * CT_Phenotype: A corpus of 906 clinical trials from http://clinicaltrials.gov/ * i2b2: The i2b2 corpus * SHARE: The ShARE/CLEF e-health 2013 Task 1 testing dataset All annotations are stored in stand-off tab based format in files carrying the names corresponding to the files listed in the original corpus. In the case of the Pubmed and CT_Phentoype corpora, the file names represent Pubmed or Clinical Trials IDs, which can be directly retrived from their original publishers. The stand-off annotation format is: startOffset::endOffset [tab] original text span [tab] list of CUIs separated by comma. Silver standard corpora created from the system annotations ommit the original text span and list only the offsets and the CUIs.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHJlc291cmNlIHhtbG5zPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCIgeG1sbnM6eHNpPSJodHRwOi8vd3d3LnczLm9yZy8yMDAxL1hNTFNjaGVtYS1pbnN0YW5jZSIgeHNpOnNjaGVtYUxvY2F0aW9uPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCBodHRwOi8vc2NoZW1hLmRhdGFjaXRlLm9yZy9tZXRhL2tlcm5lbC00LjEvbWV0YWRhdGEueHNkIj4KICA8aWRlbnRpZmllciBpZGVudGlmaWVyVHlwZT0iRE9JIj4xMC42MDg0L005LkZJR1NIQVJFLjEyNTc4Mzg8L2lkZW50aWZpZXI+CiAgPGNyZWF0b3JzPgogICAgPGNyZWF0b3I+CiAgICAgIDxjcmVhdG9yTmFtZT5UdWRvciBHcm96YTwvY3JlYXRvck5hbWU+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lPkFuaWthIE9lbGxyaWNoPC9jcmVhdG9yTmFtZT4KICAgIDwvY3JlYXRvcj4KICAgIDxjcmVhdG9yPgogICAgICA8Y3JlYXRvck5hbWU+TmlnZWwgQ29sbGllcjwvY3JlYXRvck5hbWU+CiAgICA8L2NyZWF0b3I+CiAgPC9jcmVhdG9ycz4KICA8dGl0bGVzPgogICAgPHRpdGxlPlNpbHZlciBzdGFuZGFyZCBjb25jZXB0IGFubm90YXRpb25zIGZyb20gYmlvbWVkaWNhbCB0ZXh0cyB3aXRoIHNwZWNpYWwgcmVsZXZhbmNlIHRvIHBoZW5vdHlwZXM8L3RpdGxlPgogIDwvdGl0bGVzPgogIDxkZXNjcmlwdGlvbnM+CiAgICA8ZGVzY3JpcHRpb24gZGVzY3JpcHRpb25UeXBlPSJBYnN0cmFjdCI+Jmx0O3AmZ3Q7VGhpcyBkYXRhc2V0IGRvY3VtZW50cyB0aGUgcmVzdWx0cyBhY2hpZXZlZCBieSBhcHBseWluZyBmb3VyIGNvbmNlcHQgcmVjb2duaXRpb24gc3lzdGVtc8KgdG8gdGV4dCBtaW5pbmluZyBwaGVub3R5cGVzIGZyb20gdW5zdHJ1Y3R1cmVkIGRhdGEuIEl0IGNvbXByaXNlcyB0aGUgaW5kaXZpZHVhbCBzdGFuZC1vZmYgYW5ub3RhdGlvbnMgY3JlYXRlZCBieSB0aGUgc3lzdGVtcyBvbiBmb3VyIGNvcnBvcmEuIEluIGFkZGl0aW9uLCBmb3IgZWFjaCB0ZXh0dWFsIGNvcnB1cywgc3lzdGVtLWJhc2VkIHNpbHZlciBzdGFuZGFyZCBjb3Jwb3JhIGhhdmUgYmVlbiBjcmVhdGVkIHVzaW5nIGJvdGggZXhhY3QgbWF0Y2hpbmcsIGFzIHdlbGwgYXMgc2VudGVuY2UtbGV2ZWwgbWF0Y2hpbmcuJmx0Oy9wJmd0OwombHQ7cCZndDtUaGUgZm91ciBzeXN0ZW1zIGFyZTombHQ7L3AmZ3Q7CiZsdDtwJmd0OyogTkNCTyBBbm5vdGF0b3ImbHQ7L3AmZ3Q7CiZsdDtwJmd0OyogTWV0YU1hcCZsdDsvcCZndDsKJmx0O3AmZ3Q7KiBjVEFLRVMmbHQ7L3AmZ3Q7CiZsdDtwJmd0OyogQmVDQVMmbHQ7L3AmZ3Q7CiZsdDtwJmd0O1RoZSBmb3VyIGNvcnBvcmEgYXJlOiZsdDsvcCZndDsKJmx0O3AmZ3Q7KiBQdWJtZWQ6IEEgY29ycHVzIG9mIDIsMTYzIHB1YmxpY2F0aW9uIGFic3RyYWN0cyBmcm9tIFB1Ym1lZCZsdDsvcCZndDsKJmx0O3AmZ3Q7KiBDVF9QaGVub3R5cGU6IEEgY29ycHVzIG9mIDkwNiBjbGluaWNhbCB0cmlhbHMgZnJvbSBodHRwOi8vY2xpbmljYWx0cmlhbHMuZ292LyZsdDsvcCZndDsKJmx0O3AmZ3Q7KiBpMmIyOiBUaGUgaTJiMiBjb3JwdXMmbHQ7L3AmZ3Q7CiZsdDtwJmd0OyogU0hBUkU6IFRoZSBTaEFSRS9DTEVGIGUtaGVhbHRoIDIwMTMgVGFzayAxIHRlc3RpbmcgZGF0YXNldCZsdDsvcCZndDsKJmx0O3AmZ3Q7QWxsIGFubm90YXRpb25zIGFyZSBzdG9yZWQgaW4gc3RhbmQtb2ZmIHRhYiBiYXNlZCBmb3JtYXQgaW4gZmlsZXMgY2FycnlpbmcgdGhlIG5hbWVzIGNvcnJlc3BvbmRpbmcgdG8gdGhlIGZpbGVzIGxpc3RlZCBpbiB0aGUgb3JpZ2luYWwgY29ycHVzLiBJbiB0aGUgY2FzZSBvZiB0aGUgUHVibWVkIGFuZCBDVF9QaGVudG95cGUgY29ycG9yYSwgdGhlIGZpbGUgbmFtZXMgcmVwcmVzZW50IFB1Ym1lZCBvciBDbGluaWNhbCBUcmlhbHMgSURzLCB3aGljaCBjYW4gYmUgZGlyZWN0bHkgcmV0cml2ZWQgZnJvbSB0aGVpciBvcmlnaW5hbCBwdWJsaXNoZXJzLiBUaGUgc3RhbmQtb2ZmIGFubm90YXRpb24gZm9ybWF0IGlzOiBzdGFydE9mZnNldDo6ZW5kT2Zmc2V0IFt0YWJdIG9yaWdpbmFsIHRleHQgc3BhbiBbdGFiXSBsaXN0IG9mIENVSXMgc2VwYXJhdGVkIGJ5IGNvbW1hLiBTaWx2ZXIgc3RhbmRhcmQgY29ycG9yYSBjcmVhdGVkIGZyb20gdGhlIHN5c3RlbSBhbm5vdGF0aW9ucyBvbW1pdCB0aGUgb3JpZ2luYWwgdGV4dCBzcGFuIGFuZCBsaXN0IG9ubHkgdGhlIG9mZnNldHMgYW5kIHRoZSBDVUlzLiZsdDsvcCZndDs8L2Rlc2NyaXB0aW9uPgogIDwvZGVzY3JpcHRpb25zPgogIDxzdWJqZWN0cz4KICAgIDxzdWJqZWN0PkRpc2Vhc2VzPC9zdWJqZWN0PgogICAgPHN1YmplY3Q+SW5mb3JtYXRpb24gU3lzdGVtczwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+NjAxMDIgQmlvaW5mb3JtYXRpY3M8L3N1YmplY3Q+CiAgICA8c3ViamVjdD5BcnRpZmljaWFsIEludGVsbGlnZW5jZSBhbmQgSW1hZ2UgUHJvY2Vzc2luZzwvc3ViamVjdD4KICA8L3N1YmplY3RzPgogIDxwdWJsaXNoZXI+Zmlnc2hhcmU8L3B1Ymxpc2hlcj4KICA8cHVibGljYXRpb25ZZWFyPjIwMTQ8L3B1YmxpY2F0aW9uWWVhcj4KICA8ZGF0ZXM+CiAgICA8ZGF0ZSBkYXRlVHlwZT0iQ3JlYXRlZCI+MjAxNC0xMi0wNDwvZGF0ZT4KICAgIDxkYXRlIGRhdGVUeXBlPSJVcGRhdGVkIj4yMDE0LTEyLTA0PC9kYXRlPgogIDwvZGF0ZXM+CiAgPHJlc291cmNlVHlwZSByZXNvdXJjZVR5cGVHZW5lcmFsPSJEYXRhc2V0Ij5EYXRhc2V0PC9yZXNvdXJjZVR5cGU+CiAgPHNpemVzPgogICAgPHNpemU+MTk3NDkxOTUgQnl0ZXM8L3NpemU+CiAgPC9zaXplcz4KICA8cmlnaHRzTGlzdD4KICAgIDxyaWdodHMgcmlnaHRzVVJJPSJodHRwczovL2NyZWF0aXZlY29tbW9ucy5vcmcvbGljZW5zZXMvYnkvNC4wLyI+Q0MgQlkgNC4wPC9yaWdodHM+CiAgPC9yaWdodHNMaXN0Pgo8L3Jlc291cmNlPg==","url":"https://figshare.com/articles/dataset/Silver_standard_concept_annotations_from_biomedical_texts_with_special_relevance_to_phenotypes/1257838","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2014-12-04T00:38:57.000Z","registered":"2014-12-04T00:38:58.000Z","published":"2014","updated":"2020-09-04T20:12:49.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.1257838","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}