Lee Harland
Research Subjects
Lee Harland has a total of 209 co-authors. Here are the top co-authors by number of shared publications:
- Anna Gaulton
EMBL-EBI, Hinxton, United Kingdom
4 shared publications Ian Dix
Knowledge Engineering & Information Science, Discovery Information, AstraZeneca plc, Macclesfield, UK
4 shared publicationsBryn Williams-Jones
3 shared publications- Bryn Williams-Jones
Programmes de bioéthique, Département de médecine sociale et préventive, École de santé publique de l’Université de Montréal ; Institut de recherche en santé publique de l’Université de Montréal, Montréal, Canada
3 shared publications - Carole Goble
The Department of Computer Science, the University of Manchester, Manchester, United Kingdom
3 shared publications Mark Forster
3 shared publications
Latest Publications
- Open Access
Optimising biomedical relationship extraction with BioBERT
Text mining is widely used within the life sciences as an evidence stream for inferring relationships between biological entities. In most cases, conventional string matching is used to identify cooccurrences of given entities within sentences. This limits the utility of text mining results, as they tend to contain significant noise due to weak inclusion criteria. We show that, in the indicative case of protein-protein interactions (PPIs), the majority of sentences containing cooccurrences (∽75%) do not describe any causal relationship. We further demonstrate the feasibility of fine tuning a strong domain-specific language model, BioBERT, to analyse sentences containing cooccurrences and accurately (F1 score: 88.95%) identify functional links between proteins. These strong results come in spite of the deep complexity of the language involved, which limits the accuracy even of expert curators. We establish guidelines for best practices in data creation to this end, including an examination of inter-annotator agreement, of semisupervision, and of rules based alternatives to manual curation, and explore the potential for downstream use of the model to accelerate curation of interactions in the SIGNOR database of causal protein interactions and the IntAct database of experimental evidence for physical protein interactions.
Open AccessOptimising biomedical relationship extraction with BioBERT
Text mining is widely used within the life sciences as an evidence stream for inferring relationships between biological entities. In most cases, conventional string matching is used to identify cooccurrences of given entities within sentences. This limits the utility of text mining results, as they tend to contain significant noise due to weak inclusion criteria. We show that, in the indicative case of protein-protein interactions (PPIs), the majority of sentences containing cooccurrences (∽75%) do not describe any causal relationship. We further demonstrate the feasibility of fine tuning a strong domain-specific language model, BioBERT, to analyse sentences containing cooccurrences and accurately (F1 score: 88.95%) identify functional links between proteins. These strong results come in spite of the deep complexity of the language involved, which limits the accuracy even of expert curators. We establish guidelines for best practices in data creation to this end, including an examination of inter-annotator agreement, of semisupervision, and of rules based alternatives to manual curation, and explore the potential for downstream use of the model to accelerate curation of interactions in the SIGNOR database of causal protein interactions and the IntAct database of experimental evidence for physical protein interactions.
- Open Access
- 1 April 2015
- Published by Elsevier in Drug Discovery Today
- Vol. 20 (4) , 399-405
Drug discovery FAQs: workflows for answering multidomain drug discovery questions
- 1 April 2015
- Published by Elsevier in Drug Discovery Today
- Vol. 20 (4) , 399-405
Open AccessDrug discovery FAQs: workflows for answering multidomain drug discovery questions
- 1 December 2014
- Published by Elsevier in Journal of Web Semantics
- Vol. 29, 12-18
API-centric Linked Data integration: The Open PHACTS Discovery Platform case study
- 1 December 2014
- Published by Elsevier in Journal of Web Semantics
- Vol. 29, 12-18
API-centric Linked Data integration: The Open PHACTS Discovery Platform case study
- 31 January 2014
- Published by Springer Nature in Nature Reviews Drug Discovery
- Vol. 13 (2) , 83-84
Precompetitive activity to address the biological data needs of drug discovery
- 31 January 2014
- Published by Springer Nature in Nature Reviews Drug Discovery
- Vol. 13 (2) , 83-84
Precompetitive activity to address the biological data needs of drug discovery
- Open Access
- 1 September 2013
- Published by Elsevier in Drug Discovery Today
- Vol. 18 (17-18) , 843-852
Scientific competency questions as the basis for semantically enriched open pharmacological space development
- 1 September 2013
- Published by Elsevier in Drug Discovery Today
- Vol. 18 (17-18) , 843-852
Open AccessScientific competency questions as the basis for semantically enriched open pharmacological space development
- Open Access
- 1 November 2012
- Published by Ubiquity Press, Ltd. in Insights the UKSG journal
- Vol. 25 (3) , 288-293
Reuniting data and narrative in scientific articles
- 1 November 2012
- Published by Ubiquity Press, Ltd. in Insights the UKSG journal
- Vol. 25 (3) , 288-293
Open AccessReuniting data and narrative in scientific articles
- Top Cited PapersOpen Access
- 1 November 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17 (21-22) , 1188-1198
Open PHACTS: semantic interoperability for drug discovery
- 1 November 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17 (21-22) , 1188-1198
Top Cited PapersOpen AccessOpen PHACTS: semantic interoperability for drug discovery
- 1 May 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17 (9-10) , 469-474
Systems chemical biology and the Semantic Web: what they mean for the future of drug discovery research
- 1 May 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17 (9-10) , 469-474
Systems chemical biology and the Semantic Web: what they mean for the future of drug discovery research
- 1 February 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17, S3-S15
Visualizing the drug target landscape
- 1 February 2012
- Published by Elsevier in Drug Discovery Today
- Vol. 17, S3-S15
Visualizing the drug target landscape
- Top Cited PapersOpen Access
- 27 January 2012
- Published by Springer Nature in Nature Genetics
- Vol. 44 (2) , 121-126
Toward interoperable bioscience data
To make full use of research data, the bioscience community needs to adopt technologies and reward mechanisms that support interoperability and promote the growth of an open 'data commoning' culture. Here we describe the prerequisites for data commoning and present an established and growing ecosystem of solutions using the shared 'Investigation-Study-Assay' framework to support that vision.
- 27 January 2012
- Published by Springer Nature in Nature Genetics
- Vol. 44 (2) , 121-126
Top Cited PapersOpen AccessToward interoperable bioscience data
To make full use of research data, the bioscience community needs to adopt technologies and reward mechanisms that support interoperability and promote the growth of an open 'data commoning' culture. Here we describe the prerequisites for data commoning and present an established and growing ecosystem of solutions using the shared 'Investigation-Study-Assay' framework to support that vision.