Show simple item record

dc.contributor.authorAkujuobi, Uchenna Thankgod
dc.contributor.authorSpranger, Michael
dc.contributor.authorPalanniappan, Sucheendra K
dc.contributor.authorZhang, Xiangliang
dc.date.accessioned2020-08-19T07:45:26Z
dc.date.available2020-08-19T07:45:26Z
dc.date.issued2020
dc.identifier.citationAkujuobi, U., Spranger, M., Palaniappan, S. K., & Zhang, X. (2020). T-PAIR: Temporal Node-pair Embedding for Automatic Biomedical Hypothesis Generation. IEEE Transactions on Knowledge and Data Engineering, 1–1. doi:10.1109/tkde.2020.3017687
dc.identifier.issn2326-3865
dc.identifier.doi10.1109/TKDE.2020.3017687
dc.identifier.urihttp://hdl.handle.net/10754/664664
dc.description.abstractIn this paper, we study an automatic hypothesis generation (HG) problem, which refers to the discovery of meaningful implicit connections between scientific terms, including but not limited to diseases, chemicals, drugs, and genes extracted from databases of biomedical publications. Most prior studies of this problem focused on the use of static information of terms and largely ignored the temporal dynamics of scientific term relations. Even when the dynamics were considered in a few recent studies, they learned the representations for the scientific terms, rather than focusing on the term-pair relations. Since the HG problem is to predict term-pair connections, it is not enough to know with whom the terms are connected; it is more important to know how the connections have been formed (in a dynamic process). We formulate this HG problem as a future connectivity prediction in a dynamic attributed graph. The key is to capture the temporal evolution of node-pair (term-pair) relations. We propose an inductive edge (node-pair) embedding method named T-PAIR, utilizing both the graphical structure and node attribute to encode the temporal node-pair relationship. We demonstrate the efficiency of the proposed model on three real-world datasets constructed from biomedical publications in the transductive and inductive settings.
dc.description.sponsorshipThis work was supported and funded by Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology (KAUST), and National Science Foundation of China (NSFC No. 61828302). We would also like to thank Ayako Yachie from The Systems Biology institute for her help in validating and checking the list of hypotheses generated by our algorithm.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9170911/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9170911
dc.rightsArchived with thanks to IEEE Transactions on Knowledge and Data Engineering
dc.subjectHypothesis generation
dc.subjectDynamic edge embedding
dc.subjectGraph neural networks
dc.subjectBiomedical term relation prediction
dc.titleT-PAIR: Temporal Node-pair Embedding for Automatic Biomedical Hypothesis Generation
dc.typeArticle
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentMachine Intelligence & kNowledge Engineering Lab
dc.identifier.journalIEEE Transactions on Knowledge and Data Engineering
dc.eprint.versionPost-print
dc.contributor.institutionSony Computer Science Laboratories Inc, Sony, Tokyo, Tokyo Japan
dc.contributor.institutionSBI, SBI, Tokyo, Tokyo Japan
kaust.personAkujuobi, Uchenna Thankgod
kaust.personZhang, Xiangliang
refterms.dateFOA2020-12-27T11:03:09Z
kaust.acknowledged.supportUnitComputational Bioscience Research Center (CBRC)


Files in this item

Thumbnail
Name:
T_PAIR__Temporal_Node_pair_Embedding_for_Automatic_Biomedical_Hypothesis_Generation__TKDE_.pdf
Size:
1.038Mb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record