SemPathFinder: Semantic path analysis for discovering publicly unknown knowledge

Min Song, Go Eun Heo, Ying Ding

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The enormous amount of biomedicine's natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. This paper proposes SemPathFinder to discover previously unknown relations in biomedical text. SemPathFinder overcomes the problems of Swanson's ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. Storytelling-based semantic path analysis can be viewed as relation navigation for bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. We apply SemPathFinder for two well-known use cases of Swanson's ABC model, and the experimental results show that SemPathFinder detects all intermediate terms except for one and also infers several interesting new hypotheses.

Original languageEnglish
Pages (from-to)686-703
Number of pages18
JournalJournal of Informetrics
Volume9
Issue number4
DOIs
Publication statusPublished - 2015 Oct 1

Fingerprint

path analysis
Semantics
semantics
Navigation
biomedicine
Genes
drug
language

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Library and Information Sciences

Cite this

@article{bb0e7dffa3834cf9bb69f263cb400477,
title = "SemPathFinder: Semantic path analysis for discovering publicly unknown knowledge",
abstract = "The enormous amount of biomedicine's natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. This paper proposes SemPathFinder to discover previously unknown relations in biomedical text. SemPathFinder overcomes the problems of Swanson's ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. Storytelling-based semantic path analysis can be viewed as relation navigation for bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. We apply SemPathFinder for two well-known use cases of Swanson's ABC model, and the experimental results show that SemPathFinder detects all intermediate terms except for one and also infers several interesting new hypotheses.",
author = "Min Song and Heo, {Go Eun} and Ying Ding",
year = "2015",
month = "10",
day = "1",
doi = "10.1016/j.joi.2015.06.004",
language = "English",
volume = "9",
pages = "686--703",
journal = "Journal of Informetrics",
issn = "1751-1577",
publisher = "Elsevier BV",
number = "4",

}

SemPathFinder : Semantic path analysis for discovering publicly unknown knowledge. / Song, Min; Heo, Go Eun; Ding, Ying.

In: Journal of Informetrics, Vol. 9, No. 4, 01.10.2015, p. 686-703.

Research output: Contribution to journalArticle

TY - JOUR

T1 - SemPathFinder

T2 - Semantic path analysis for discovering publicly unknown knowledge

AU - Song, Min

AU - Heo, Go Eun

AU - Ding, Ying

PY - 2015/10/1

Y1 - 2015/10/1

N2 - The enormous amount of biomedicine's natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. This paper proposes SemPathFinder to discover previously unknown relations in biomedical text. SemPathFinder overcomes the problems of Swanson's ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. Storytelling-based semantic path analysis can be viewed as relation navigation for bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. We apply SemPathFinder for two well-known use cases of Swanson's ABC model, and the experimental results show that SemPathFinder detects all intermediate terms except for one and also infers several interesting new hypotheses.

AB - The enormous amount of biomedicine's natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. This paper proposes SemPathFinder to discover previously unknown relations in biomedical text. SemPathFinder overcomes the problems of Swanson's ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. Storytelling-based semantic path analysis can be viewed as relation navigation for bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. We apply SemPathFinder for two well-known use cases of Swanson's ABC model, and the experimental results show that SemPathFinder detects all intermediate terms except for one and also infers several interesting new hypotheses.

UR - http://www.scopus.com/inward/record.url?scp=84940483846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940483846&partnerID=8YFLogxK

U2 - 10.1016/j.joi.2015.06.004

DO - 10.1016/j.joi.2015.06.004

M3 - Article

AN - SCOPUS:84940483846

VL - 9

SP - 686

EP - 703

JO - Journal of Informetrics

JF - Journal of Informetrics

SN - 1751-1577

IS - 4

ER -