-
Tytuł:
-
DI2: prior-free and multi-item discretization of biological data and its applications.
-
Autorzy:
-
Alexandre L; IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001, Lisbon, Portugal. .; INESC-ID, Lisbon, Portugal. .; Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal. .
Costa RS; IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001, Lisbon, Portugal.; LAQV-REQUIMTE, DQ, NOVA School of Science and Technology, Universidade NOVA de Lisboa, 2829-516, Caparica, Portugal.
Henriques R; INESC-ID, Lisbon, Portugal.; Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal.
-
Źródło:
-
BMC bioinformatics [BMC Bioinformatics] 2021 Sep 08; Vol. 22 (1), pp. 426. Date of Electronic Publication: 2021 Sep 08.
-
Typ publikacji:
-
Journal Article
-
Język:
-
English
-
Imprint Name(s):
-
Original Publication: [London] : BioMed Central, 2000-
-
MeSH Terms:
-
Algorithms*
Data Mining*
Computational Biology
-
References:
-
Proc Int Conf Intell Syst Mol Biol. 1996;4:109-15. (PMID: 8877510)
J Am Med Inform Assoc. 2013 May 1;20(3):544-53. (PMID: 23059731)
Algorithms Mol Biol. 2014 Dec 16;9(1):27. (PMID: 25649207)
BMC Med Res Methodol. 2012 Feb 29;12:21. (PMID: 22375553)
Med Biol Eng Comput. 1996 Sep;34(5):346-50. (PMID: 8945857)
Nat Methods. 2020 Mar;17(3):261-272. (PMID: 32015543)
Med Inform Internet Med. 2002 Mar;27(1):59-67. (PMID: 12509124)
-
Grant Information:
-
UIDB/50021/2020 Fundação para a Ciência e a Tecnologia; DSAIPA/DS/0042/2018 Fundação para a Ciência e a Tecnologia; DSAIPA/DS/0111/2018 Fundação para a Ciência e a Tecnologia; UIDB/50006/2020 Fundação para a Ciência e a Tecnologia; UIDP/50006/2020 Fundação para a Ciência e a Tecnologia; UIDB/50021/2020 Fundação para a Ciência e a Tecnologia; CEECIND/01399/2017 Fundação para a Ciência e a Tecnologia
-
Contributed Indexing:
-
Keywords: Data mining; Heterogeneous biological data; Multi-item discretization; Prior-free discretization
-
Entry Date(s):
-
Date Created: 20210909 Date Completed: 20210910 Latest Revision: 20210912
-
Update Code:
-
20240105
-
PubMed Central ID:
-
PMC8425008
-
DOI:
-
10.1186/s12859-021-04329-8
-
PMID:
-
34496758
-
Background: A considerable number of data mining approaches for biomedical data analysis, including state-of-the-art associative models, require a form of data discretization. Although diverse discretization approaches have been proposed, they generally work under a strict set of statistical assumptions which are arguably insufficient to handle the diversity and heterogeneity of clinical and molecular variables within a given dataset. In addition, although an increasing number of symbolic approaches in bioinformatics are able to assign multiple items to values occurring near discretization boundaries for superior robustness, there are no reference principles on how to perform multi-item discretizations.
Results: In this study, an unsupervised discretization method, DI2, for variables with arbitrarily skewed distributions is proposed. Statistical tests applied to assess differences in performance confirm that DI2 generally outperforms well-established discretizations methods with statistical significance. Within classification tasks, DI2 displays either competitive or superior levels of predictive accuracy, particularly delineate for classifiers able to accommodate border values.
Conclusions: This work proposes a new unsupervised method for data discretization, DI2, that takes into account the underlying data regularities, the presence of outlier values disrupting expected regularities, as well as the relevance of border values. DI2 is available at https://github.com/JupitersMight/DI2.
(© 2021. The Author(s).)