Relational Descriptive Analysis of Gene Expression Data

Igor Trajkovski; Filip Zelezny; Nada Lavrac; Jakub Tolar

Relational Descriptive Analysis of Gene Expression Data

Igor Trajkovski, Filip Zelezny, Nada Lavrac, Jakub Tolar

Administration (TMED)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a method that uses gene ontologies, together with the paradigm of relational subgroup discovery, to help find description of groups of genes differentially expressed in specific cancers. The descriptions are represented by means of relational features, extracted from publicly available gene ontology information, and are straightforwardly interpretable by the medical experts. We applied the proposed method to two known data sets: (i) acute lymphoblastic leukemia (ALL) vs. acute myeloid leukemia (AML) and (ii) classification of fourteen types of cancer. Significant number of discovered groups of genes had a description, confirmed by the medical expert, which highlighted the underlying biological process that is responsible for distinguishing one class from the other classes. We view our methodology not just as a prototypical example of applying more sophisticated machine learning algorithms to gene expression analysis, but also as a motivation for developing increasingly more sophisticated functional annotations and ontologies, that can be processed by such learning algorithms.

Original language	English (US)
Title of host publication	STAIRS 2006 - Proceedings of the 3rd Starting AI Researchers' Symposium
Editors	Loris Penserini, Pavlos Peppas, Anna Perini
Publisher	IOS Press BV
Pages	184-195
Number of pages	12
ISBN (Electronic)	1586036459, 9781586036454
State	Published - 2006
Event	3rd European Starting AI Researchers Symposium, STAIRS 2006 - Trento, Italy Duration: May 23 2006 → …

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	142
ISSN (Print)	0922-6389

Conference

Conference	3rd European Starting AI Researchers Symposium, STAIRS 2006
Country/Territory	Italy
City	Trento
Period	5/23/06 → …

Bibliographical note

Funding Information:
The research of I.T. and N.L. is supported by the Slovenian Ministry of Higher Education, Science and Technology. F.Z. is supported by the Czech Academy of Sciences through the project KJB201210501 Logic Based Machine Learning for Analysis of Genomic Data.

Publisher Copyright:
©2006 The authors. All rights reserved.

Keywords

Inductive logic programming
Learning from structured data
Learning in bioinformatics
Meta-learning
Relational learning
Scientific discovery

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Find It

Find It at U of M Libraries

Cite this

Relational Descriptive Analysis of Gene Expression Data. / Trajkovski, Igor; Zelezny, Filip; Lavrac, Nada et al.
STAIRS 2006 - Proceedings of the 3rd Starting AI Researchers' Symposium. ed. / Loris Penserini; Pavlos Peppas; Anna Perini. IOS Press BV, 2006. p. 184-195 (Frontiers in Artificial Intelligence and Applications; Vol. 142).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Trajkovski, I, Zelezny, F, Lavrac, N & Tolar, J 2006, Relational Descriptive Analysis of Gene Expression Data. in L Penserini, P Peppas & A Perini (eds), STAIRS 2006 - Proceedings of the 3rd Starting AI Researchers' Symposium. Frontiers in Artificial Intelligence and Applications, vol. 142, IOS Press BV, pp. 184-195, 3rd European Starting AI Researchers Symposium, STAIRS 2006, Trento, Italy, 5/23/06.

@inproceedings{eac44ed76b0b48c595d82279fa995a71,

title = "Relational Descriptive Analysis of Gene Expression Data",

abstract = "This paper presents a method that uses gene ontologies, together with the paradigm of relational subgroup discovery, to help find description of groups of genes differentially expressed in specific cancers. The descriptions are represented by means of relational features, extracted from publicly available gene ontology information, and are straightforwardly interpretable by the medical experts. We applied the proposed method to two known data sets: (i) acute lymphoblastic leukemia (ALL) vs. acute myeloid leukemia (AML) and (ii) classification of fourteen types of cancer. Significant number of discovered groups of genes had a description, confirmed by the medical expert, which highlighted the underlying biological process that is responsible for distinguishing one class from the other classes. We view our methodology not just as a prototypical example of applying more sophisticated machine learning algorithms to gene expression analysis, but also as a motivation for developing increasingly more sophisticated functional annotations and ontologies, that can be processed by such learning algorithms.",

keywords = "Inductive logic programming, Learning from structured data, Learning in bioinformatics, Meta-learning, Relational learning, Scientific discovery",

author = "Igor Trajkovski and Filip Zelezny and Nada Lavrac and Jakub Tolar",

note = "Funding Information: The research of I.T. and N.L. is supported by the Slovenian Ministry of Higher Education, Science and Technology. F.Z. is supported by the Czech Academy of Sciences through the project KJB201210501 Logic Based Machine Learning for Analysis of Genomic Data. Publisher Copyright: {\textcopyright}2006 The authors. All rights reserved.; 3rd European Starting AI Researchers Symposium, STAIRS 2006 ; Conference date: 23-05-2006",

year = "2006",

language = "English (US)",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press BV",

pages = "184--195",

editor = "Loris Penserini and Pavlos Peppas and Anna Perini",

booktitle = "STAIRS 2006 - Proceedings of the 3rd Starting AI Researchers' Symposium",

address = "Netherlands",

}

TY - GEN

T1 - Relational Descriptive Analysis of Gene Expression Data

AU - Trajkovski, Igor

AU - Zelezny, Filip

AU - Lavrac, Nada

AU - Tolar, Jakub

N1 - Funding Information: The research of I.T. and N.L. is supported by the Slovenian Ministry of Higher Education, Science and Technology. F.Z. is supported by the Czech Academy of Sciences through the project KJB201210501 Logic Based Machine Learning for Analysis of Genomic Data. Publisher Copyright: ©2006 The authors. All rights reserved.

PY - 2006

Y1 - 2006

N2 - This paper presents a method that uses gene ontologies, together with the paradigm of relational subgroup discovery, to help find description of groups of genes differentially expressed in specific cancers. The descriptions are represented by means of relational features, extracted from publicly available gene ontology information, and are straightforwardly interpretable by the medical experts. We applied the proposed method to two known data sets: (i) acute lymphoblastic leukemia (ALL) vs. acute myeloid leukemia (AML) and (ii) classification of fourteen types of cancer. Significant number of discovered groups of genes had a description, confirmed by the medical expert, which highlighted the underlying biological process that is responsible for distinguishing one class from the other classes. We view our methodology not just as a prototypical example of applying more sophisticated machine learning algorithms to gene expression analysis, but also as a motivation for developing increasingly more sophisticated functional annotations and ontologies, that can be processed by such learning algorithms.

AB - This paper presents a method that uses gene ontologies, together with the paradigm of relational subgroup discovery, to help find description of groups of genes differentially expressed in specific cancers. The descriptions are represented by means of relational features, extracted from publicly available gene ontology information, and are straightforwardly interpretable by the medical experts. We applied the proposed method to two known data sets: (i) acute lymphoblastic leukemia (ALL) vs. acute myeloid leukemia (AML) and (ii) classification of fourteen types of cancer. Significant number of discovered groups of genes had a description, confirmed by the medical expert, which highlighted the underlying biological process that is responsible for distinguishing one class from the other classes. We view our methodology not just as a prototypical example of applying more sophisticated machine learning algorithms to gene expression analysis, but also as a motivation for developing increasingly more sophisticated functional annotations and ontologies, that can be processed by such learning algorithms.

KW - Inductive logic programming

KW - Learning from structured data

KW - Learning in bioinformatics

KW - Meta-learning

KW - Relational learning

KW - Scientific discovery

UR - http://www.scopus.com/inward/record.url?scp=81155130427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81155130427&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:81155130427

T3 - Frontiers in Artificial Intelligence and Applications

SP - 184

EP - 195

BT - STAIRS 2006 - Proceedings of the 3rd Starting AI Researchers' Symposium

A2 - Penserini, Loris

A2 - Peppas, Pavlos

A2 - Perini, Anna

PB - IOS Press BV

T2 - 3rd European Starting AI Researchers Symposium, STAIRS 2006

Y2 - 23 May 2006

ER -

Relational Descriptive Analysis of Gene Expression Data

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Find It

Other files and links

Fingerprint

Cite this