Indirect association and ranking hypotheses for literature based discovery.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Author(s): Henry S;Henry S; McInnes BT; McInnes BT
  • Source:
    BMC bioinformatics [BMC Bioinformatics] 2019 Aug 15; Vol. 20 (1), pp. 425. Date of Electronic Publication: 2019 Aug 15.
  • Publication Type:
    Journal Article
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: BioMed Central Country of Publication: England NLM ID: 100965194 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2105 (Electronic) Linking ISSN: 14712105 NLM ISO Abbreviation: BMC Bioinformatics Subsets: MEDLINE
    • Publication Information:
      Original Publication: [London] : BioMed Central, 2000-
    • Subject Terms:
      Knowledge Discovery* ; Models, Theoretical*; Area Under Curve ; Databases as Topic ; Humans ; ROC Curve ; Semantics ; Statistics, Nonparametric
    • Abstract:
      Background: Literature Based Discovery (LBD) produces more potential hypotheses than can be manually reviewed, making automatically ranking these hypotheses critical. In this paper, we introduce the indirect association measures of Linking Term Association (LTA), Minimum Weight Association (MWA), and Shared B to C Set Association (SBC), and compare them to Linking Set Association (LSA), concept embeddings vector cosine, Linking Term Count (LTC), and direct co-occurrence vector cosine. Our proposed indirect association measures extend traditional association measures to quantify indirect rather than direct associations while preserving valuable statistical properties.
      Results: We perform a comparison between several different hypothesis ranking methods for LBD, and compare them against our proposed indirect association measures. We intrinsically evaluate each method's performance using its ability to estimate semantic relatedness on standard evaluation datasets. We extrinsically evaluate each method's ability to rank hypotheses in LBD using a time-slicing dataset based on co-occurrence information, and another time-slicing dataset based on SemRep extracted-relationships. Precision and recall curves are generated by ranking term pairs and applying a threshold at each rank.
      Conclusions: Results differ depending on the evaluation methods and datasets, but it is unclear if this is a result of biases in the evaluation datasets or if one method is truly better than another. We conclude that LTC and SBC are the best suited methods for hypothesis ranking in LBD, but there is value in having a variety of methods to choose from.
    • References:
      Brief Bioinform. 2017 May 1;18(3):488-497. (PMID: 27113728)
      J Biomed Inform. 2003 Dec;36(6):462-77. (PMID: 14759819)
      BMC Bioinformatics. 2012 Jun 06;13:119. (PMID: 22672646)
      J Biomed Inform. 2015 Apr;54:141-57. (PMID: 25661592)
      J Med Syst. 2016 Aug;40(8):185. (PMID: 27318993)
      KDD. 2017 Aug;2017:1633-1642. (PMID: 29430330)
      PLoS One. 2015 Mar 04;10(3):e0118432. (PMID: 25738806)
      Stud Health Technol Inform. 2001;84(Pt 2):1344-8. (PMID: 11604946)
      Mol Inform. 2015 Feb;34(2-3):160-70. (PMID: 27490038)
      J Biomed Discov Collab. 2010 Sep 21;5:21-49. (PMID: 20859853)
      AMIA Annu Symp Proc. 2010 Nov 13;2010:572-6. (PMID: 21347043)
      J Biomed Inform. 2009 Apr;42(2):219-27. (PMID: 18771753)
      Methods Inf Med. 2016 Aug 5;55(4):340-6. (PMID: 27435341)
      Stud Health Technol Inform. 2004;107(Pt 1):327-31. (PMID: 15360828)
      J Biomed Inform. 2007 Jun;40(3):288-99. (PMID: 16875881)
      Int J Med Inform. 2005 Mar;74(2-4):289-98. (PMID: 15694635)
      BMC Bioinformatics. 2004 Oct 07;5:145. (PMID: 15471547)
      J Biomed Inform. 2018 Jan;77:111-119. (PMID: 29247788)
      J Biomed Inform. 2016 Apr;60:23-37. (PMID: 26732995)
      AMIA Jt Summits Transl Sci Proc. 2019 May 06;2019:582-591. (PMID: 31259013)
      J Biomed Inform. 2015 Apr;54:329-36. (PMID: 25523466)
      Perspect Biol Med. 1986 Autumn;30(1):7-18. (PMID: 3797213)
      Bioinformatics. 2012 Dec 1;28(23):3158-60. (PMID: 23044550)
      J Am Med Inform Assoc. 2010 May-Jun;17(3):229-36. (PMID: 20442139)
      Artif Intell Med. 2019 Jan;93:1-10. (PMID: 30197305)
      J Biomed Inform. 2009 Aug;42(4):633-43. (PMID: 19124086)
      AMIA Annu Symp Proc. 2011;2011:1514-23. (PMID: 22195216)
      J Biomed Inform. 2011 Apr;44(2):251-65. (PMID: 21044697)
      J Data Inf Sci. 2017 Dec;2(4):43-64. (PMID: 29355246)
      J Am Med Inform Assoc. 2015 Sep;22(5):987-92. (PMID: 25971437)
      J Am Med Inform Assoc. 2007 Sep-Oct;14(5):651-61. (PMID: 17600104)
      AMIA Annu Symp Proc. 2009 Nov 14;2009:431-5. (PMID: 20351894)
    • Contributed Indexing:
      Keywords: Indirect association; Literature based discovery; Semantic relatedness; Semantic similarity
    • Publication Date:
      Date Created: 20190817 Date Completed: 20191018 Latest Revision: 20231013
    • Publication Date:
      20240105
    • Accession Number:
      PMC6694578
    • Accession Number:
      10.1186/s12859-019-2989-9
    • Accession Number:
      31416434