MKEM: A Multi-level Knowledge Emergence Model for mining undiscovered public knowledge

Ali Z. Ijaz, Min Song, Doheon Lee

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Background: Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypotheses and expand knowledge.Methods: We propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships.Results: We applied our system on 5000 abstracts downloaded from PubMed database. We performed the performance evaluation as a gold standard is not yet available. Our system performed with a good precision and recall and we generated 24 hypotheses.Conclusions: Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model. .

Original languageEnglish
Article numberS3
JournalBMC bioinformatics
Volume11
Issue numberSUPPL. 2
DOIs
Publication statusPublished - 2010 Apr 16

Fingerprint

Mining
Unified Medical Language System
Natural Language Processing
Human Body
PubMed
Model
Databases
Ontology
Tagging
Gold
Grammar
Genes
Natural Language
Expand
Performance Evaluation
Proteins
Disjoint
Research
Knowledge
Gene

All Science Journal Classification (ASJC) codes

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

@article{7162167547434cd98fb03559543e02bc,
title = "MKEM: A Multi-level Knowledge Emergence Model for mining undiscovered public knowledge",
abstract = "Background: Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypotheses and expand knowledge.Methods: We propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships.Results: We applied our system on 5000 abstracts downloaded from PubMed database. We performed the performance evaluation as a gold standard is not yet available. Our system performed with a good precision and recall and we generated 24 hypotheses.Conclusions: Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model. .",
author = "Ijaz, {Ali Z.} and Min Song and Doheon Lee",
year = "2010",
month = "4",
day = "16",
doi = "10.1186/1471-2105-11-S2-S3",
language = "English",
volume = "11",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "SUPPL. 2",

}

MKEM : A Multi-level Knowledge Emergence Model for mining undiscovered public knowledge. / Ijaz, Ali Z.; Song, Min; Lee, Doheon.

In: BMC bioinformatics, Vol. 11, No. SUPPL. 2, S3, 16.04.2010.

Research output: Contribution to journalArticle

TY - JOUR

T1 - MKEM

T2 - A Multi-level Knowledge Emergence Model for mining undiscovered public knowledge

AU - Ijaz, Ali Z.

AU - Song, Min

AU - Lee, Doheon

PY - 2010/4/16

Y1 - 2010/4/16

N2 - Background: Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypotheses and expand knowledge.Methods: We propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships.Results: We applied our system on 5000 abstracts downloaded from PubMed database. We performed the performance evaluation as a gold standard is not yet available. Our system performed with a good precision and recall and we generated 24 hypotheses.Conclusions: Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model. .

AB - Background: Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier works, however, required substantial manual intervention to reduce the number of possible connections and are mainly applied to disease-effect relation. With the advancement in biomedical science, it has become imperative to extract and combine information from multiple disjoint researches, studies and articles to infer new hypotheses and expand knowledge.Methods: We propose MKEM, a Multi-level Knowledge Emergence Model, to discover implicit relationships using Natural Language Processing techniques such as Link Grammar and Ontologies such as Unified Medical Language System (UMLS) MetaMap. The contribution of MKEM is as follows: First, we propose a flexible knowledge emergence model to extract implicit relationships across different levels such as molecular level for gene and protein and Phenomic level for disease and treatment. Second, we employ MetaMap for tagging biological concepts. Third, we provide an empirical and systematic approach to discover novel relationships.Results: We applied our system on 5000 abstracts downloaded from PubMed database. We performed the performance evaluation as a gold standard is not yet available. Our system performed with a good precision and recall and we generated 24 hypotheses.Conclusions: Our experiments show that MKEM is a powerful tool to discover hidden relationships residing in extracted entities that were represented by our Substance-Effect-Process-Disease-Body Part (SEPDB) model. .

UR - http://www.scopus.com/inward/record.url?scp=77952943324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952943324&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-11-S2-S3

DO - 10.1186/1471-2105-11-S2-S3

M3 - Article

C2 - 20406501

AN - SCOPUS:77952943324

VL - 11

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - SUPPL. 2

M1 - S3

ER -