Abstract
Huge volumes of biomedical text data discussing about different biomedical entities are being generated every day. Hidden in those unstructured data are the strong relevance relationships between those entities, which are critical for many interesting applications including building knowledge bases for the biomedical domain and semantic search among biomedical entities. In this paper, we study the problem of discovering strong relevance between heterogeneous typed biomedical entities from massive biomedical text data. We first build an entity correlation graph from data, in which the collection of paths linking two heterogeneous entities offer rich semantic contexts for their relationships, especially those paths following the patterns of top-\(k\) selected meta paths inferred from data. Guided by such meta paths, we design a novel relevance measure to compute the strong relevance between two heterogeneous entities, named \({\mathsf {EntityRel}}\). Our intuition is, two entities of heterogeneous types are strongly relevant if they have strong direct links or they are linked closely to other strongly relevant heterogeneous entities along paths following the selected patterns. We provide experimental results on mining strong relevance between drugs and diseases. More than 20 millions of MEDLINE abstracts and 5 types of biological entities (Drug, Disease, Compound, Target, MeSH) are used to construct the entity correlation graph. A prototype of drug search engine for disease queries is implemented. Extensive comparisons are made against multiple state-of-the-arts in the examples of Drug–Disease relevance discovery.
Similar content being viewed by others
Notes
http://www.ebi.ac.uk/chebi/. Note that drugs belong to compounds. In this paper, we treat them differently as they originate from different sources orthogonally.
http://www.accessdata.fda.gov/scripts/cder/ob/default.cfm. Among all the relevance relationships between different types of biological entities, we show the discovery results of the therapeutic relationships as an example since the results are easy to be evaluated by referring to FDA’s orange book.
The hit disease “acne vulgaris” is its synonym.
References
Aleman-Meza B, Halaschek-Wiener C, Arpinar IB, Sheth AP (2003) Context-aware semantic association ranking. In: Semantic Web and Databases, pp. 33–50
Anyanwu K, Maduko A, Sheth AP (2005) Semrank: ranking complex relationship search results on the semantic web. In: WWW, pp. 117–127
Anyanwu K, Sheth AP (2003) P-queries: enabling querying for semantic associations on the semantic web. In: WWW, pp. 690–699
Coulet A, Garten Y, Dumontier M, Altman R, Musen M, Shah N (2011) Integration and publication of heterogeneous text-mined relationships on the semantic web. J Biomed Semant 2(Suppl 2):S10
Eppstein D (1998) Finding the k shortest paths. SIAM J Comput 28(2):652–673
Guan Z, Wang C, Bu J, Chen C, Yang K, Cai D, He X (2010) Document recommendation in social tagging services. In: WWW, pp. 391–400
Gunther E, Stone D, Gerwien R, Bento P, Heyes M (2003) Prediction of clinical drug efficacy by classification of drug-induced genomic expression profiles in vitro. Proc Natl Acad Sci 100(16):9608
Jeh G, Widom J (2002) Simrank: a measure of structural-context similarity. In: KDD, pp. 538–543
Jeh G, Widom J (2003) Scaling personalized web search. In: WWW, pp. 271–279
Lao N, Cohen WW (2004) Relational retrieval using a combination of path-constrained random walks. Mach Learn 81:53–67
Lao N, Cohen WW (2010) Fast query execution for retrieval models based on path-constrained random walks. In: KDD, pp. 881–888
Manning CD, Raghavan P, Schütze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge
Ramakrishnan C, Mendes P, Wang S, Sheth A (2008) Unsupervised discovery of compound entities for relationship extraction. Knowledge Engineering: Practice and Patterns pp. 146–155
Searls D (2005) Data integration: challenges for drug discovery. Nat Rev Drug Discov 4(1):45–58
Sen S, Vig J, Riedl J (2009) Tagommenders: connecting users to items through tags. In: WWW, pp. 671–680
Sheth AP, Aleman-Meza B, Arpinar IB, Bertram C, Warke YS, Ramakrishnan C, Halaschek C, Anyanwu K, Avant D, Arpinar FS, Kochut K (2005) Semantic association identification and knowledge discovery for national security applications. J Database Manage 16(1):33–53
Shi C, Kong X, Yu PS, Xie S, Wu B (2012) Relevance search in heterogeneous networks. In: EDBT, pp. 180–191
Sun Y, Han J, Yan X, Yu PS, Wu T (2011) Pathsim: meta path-based top-k similarity search in heterogeneous information networks. PVLDB 4(11):992–1003
Yan S, Spangler WS, Chen Y (2011) Cross media entity extraction and linkage for chemical documents. In: AAAI
Yin D, Xue Z, Hong L, Davison B (2010) A probabilistic model for personalized tag prediction. In: KDD, pp. 959–968
Acknowledgments
Research was sponsored in part by the Army Research Lab, under Cooperative Agreement No. W911NF-09-2-0053 (NSCTA), National Science Foundation IIS-1017362, IIS-1320617, IIS-1354329, HDTRA1-10-1-0120, and NIH Big Data to Knowledge (BD2K) (U54).
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible editor: Fei Wang, Gregor Stiglic, Ian Davidson, Zoran Obradovic.
This work was done when the first author was doing an internship at IBM Almaden Research Center.
Rights and permissions
About this article
Cite this article
Ji, M., He, Q., Han, J. et al. Mining strong relevance between heterogeneous entities from unstructured biomedical data. Data Min Knowl Disc 29, 976–998 (2015). https://doi.org/10.1007/s10618-014-0396-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10618-014-0396-4