Literature DB >> 27435341

Link Prediction on a Network of Co-occurring MeSH Terms: Towards Literature-based Discovery.

Andrej Kastrin1, Thomas C Rindflesch, Dimitar Hristovski.   

Abstract

OBJECTIVES: Literature-based discovery (LBD) is a text mining methodology for automatically generating research hypotheses from existing knowledge. We mimic the process of LBD as a classification problem on a graph of MeSH terms. We employ unsupervised and supervised link prediction methods for predicting previously unknown connections between biomedical concepts.
METHODS: We evaluate the effectiveness of link prediction through a series of experiments using a MeSH network that contains the history of link formation between biomedical concepts. We performed link prediction using proximity measures, such as common neighbor (CN), Jaccard coefficient (JC), Adamic / Adar index (AA) and preferential attachment (PA). Our approach relies on the assumption that similar nodes are more likely to establish a link in the future.
RESULTS: Applying an unsupervised approach, the AA measure achieved the best performance in terms of area under the ROC curve (AUC = 0.76), followed by CN, JC, and PA. In a supervised approach, we evaluate whether proximity measures can be combined to define a model of link formation across all four predictors. We applied various classifiers, including decision trees, k-nearest neighbors, logistic regression, multilayer perceptron, naïve Bayes, and random forests. Random forest classifier accomplishes the best performance (AUC = 0.87).
CONCLUSIONS: The link prediction approach proved to be effective for LBD processing. Supervised statistical learning approaches clearly outperform an unsupervised approach to link prediction.

Entities:  

Keywords:  Complex networks; link prediction; literature-based discovery; network analysis

Mesh:

Year:  2016        PMID: 27435341     DOI: 10.3414/ME15-01-0108

Source DB:  PubMed          Journal:  Methods Inf Med        ISSN: 0026-1270            Impact factor:   2.176


  12 in total

1.  Gaps within the Biomedical Literature: Initial Characterization and Assessment of Strategies for Discovery.

Authors:  Yufang Peng; Gary Bonifield; Neil R Smalheiser
Journal:  Front Res Metr Anal       Date:  2017-05-22

2.  Rediscovering Don Swanson: the Past, Present and Future of Literature-Based Discovery.

Authors:  Neil R Smalheiser
Journal:  J Data Inf Sci       Date:  2017-12

3.  Combining Literature Mining and Machine Learning for Predicting Biomedical Discoveries.

Authors:  Balu Bhasuran
Journal:  Methods Mol Biol       Date:  2022

Review 4.  Recent advances in biomedical literature mining.

Authors:  Sendong Zhao; Chang Su; Zhiyong Lu; Fei Wang
Journal:  Brief Bioinform       Date:  2021-05-20       Impact factor: 11.622

5.  Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches.

Authors:  Gamal Crichton; Yufan Guo; Sampo Pyysalo; Anna Korhonen
Journal:  BMC Bioinformatics       Date:  2018-05-21       Impact factor: 3.169

6.  Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning.

Authors:  Andrej Kastrin; Polonca Ferk; Brane Leskošek
Journal:  PLoS One       Date:  2018-05-08       Impact factor: 3.240

7.  Indirect association and ranking hypotheses for literature based discovery.

Authors:  Sam Henry; Bridget T McInnes
Journal:  BMC Bioinformatics       Date:  2019-08-15       Impact factor: 3.169

8.  Inferring new relations between medical entities using literature curated term co-occurrences.

Authors:  Adam Spiro; Jonatan Fernández García; Chen Yanover
Journal:  JAMIA Open       Date:  2019-07-01

9.  A systematic review on literature-based discovery workflow.

Authors:  Menasha Thilakaratne; Katrina Falkner; Thushari Atapattu
Journal:  PeerJ Comput Sci       Date:  2019-11-18

10.  Creation of Individual Scientific Concept-Centered Semantic Maps Based on Automated Text-Mining Analysis of PubMed.

Authors:  Ekaterina Ilgisonis; Andrey Lisitsa; Valerya Kudryavtseva; Elena Ponomarenko
Journal:  Adv Bioinformatics       Date:  2018-07-26
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.