A hidden Markov model for gene function prediction from sequential expression data

Xutao Deng, Hesham H Ali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Hidden Markov Models (HMMs) have demonatrated great successes in modeling noisy sequential data sets in the area of speech recognition and protein sequence profiling. Results from association test showed significant Markov dependency in time-series gene expression data, and therefore HMMs would be especially appropriate for modeling gene expressions. In this project, we developed a gene function prediction tool based on profile HMMs. Each function class is associated with a distinct HMM whose parameters are trained using yeast time-series gene expression data. The function annotations of the HMM training set were obtained from Munich Information Centre for Protein Sequences (MIPS) data base. We designed several structural variants of HMMs (single, double-split) and tested each of them on forty function classes each of which includes more than one hundred instances. The highest prediction sensitivity we achieved is 51% by using double-split HMM with 3-fold cross-validation.

Original languageEnglish (US)
Title of host publicationProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004
Pages670-671
Number of pages2
StatePublished - Dec 1 2004
EventProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004 - Stanford, CA, United States
Duration: Aug 16 2004Aug 19 2004

Publication series

NameProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004

Conference

ConferenceProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004
CountryUnited States
CityStanford, CA
Period8/16/048/19/04

Fingerprint

Hidden Markov models
Genes
Gene expression
Time series
Proteins
Information services
Speech recognition
Yeast

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Deng, X., & Ali, H. H. (2004). A hidden Markov model for gene function prediction from sequential expression data. In Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004 (pp. 670-671). (Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004).

A hidden Markov model for gene function prediction from sequential expression data. / Deng, Xutao; Ali, Hesham H.

Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004. 2004. p. 670-671 (Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Deng, X & Ali, HH 2004, A hidden Markov model for gene function prediction from sequential expression data. in Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004. Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004, pp. 670-671, Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004, Stanford, CA, United States, 8/16/04.
Deng X, Ali HH. A hidden Markov model for gene function prediction from sequential expression data. In Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004. 2004. p. 670-671. (Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004).
Deng, Xutao ; Ali, Hesham H. / A hidden Markov model for gene function prediction from sequential expression data. Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004. 2004. pp. 670-671 (Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004).
@inproceedings{5683cd1be49a40b990aa3f88e256bbfb,
title = "A hidden Markov model for gene function prediction from sequential expression data",
abstract = "Hidden Markov Models (HMMs) have demonatrated great successes in modeling noisy sequential data sets in the area of speech recognition and protein sequence profiling. Results from association test showed significant Markov dependency in time-series gene expression data, and therefore HMMs would be especially appropriate for modeling gene expressions. In this project, we developed a gene function prediction tool based on profile HMMs. Each function class is associated with a distinct HMM whose parameters are trained using yeast time-series gene expression data. The function annotations of the HMM training set were obtained from Munich Information Centre for Protein Sequences (MIPS) data base. We designed several structural variants of HMMs (single, double-split) and tested each of them on forty function classes each of which includes more than one hundred instances. The highest prediction sensitivity we achieved is 51{\%} by using double-split HMM with 3-fold cross-validation.",
author = "Xutao Deng and Ali, {Hesham H}",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
isbn = "0769521940",
series = "Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004",
pages = "670--671",
booktitle = "Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004",

}

TY - GEN

T1 - A hidden Markov model for gene function prediction from sequential expression data

AU - Deng, Xutao

AU - Ali, Hesham H

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Hidden Markov Models (HMMs) have demonatrated great successes in modeling noisy sequential data sets in the area of speech recognition and protein sequence profiling. Results from association test showed significant Markov dependency in time-series gene expression data, and therefore HMMs would be especially appropriate for modeling gene expressions. In this project, we developed a gene function prediction tool based on profile HMMs. Each function class is associated with a distinct HMM whose parameters are trained using yeast time-series gene expression data. The function annotations of the HMM training set were obtained from Munich Information Centre for Protein Sequences (MIPS) data base. We designed several structural variants of HMMs (single, double-split) and tested each of them on forty function classes each of which includes more than one hundred instances. The highest prediction sensitivity we achieved is 51% by using double-split HMM with 3-fold cross-validation.

AB - Hidden Markov Models (HMMs) have demonatrated great successes in modeling noisy sequential data sets in the area of speech recognition and protein sequence profiling. Results from association test showed significant Markov dependency in time-series gene expression data, and therefore HMMs would be especially appropriate for modeling gene expressions. In this project, we developed a gene function prediction tool based on profile HMMs. Each function class is associated with a distinct HMM whose parameters are trained using yeast time-series gene expression data. The function annotations of the HMM training set were obtained from Munich Information Centre for Protein Sequences (MIPS) data base. We designed several structural variants of HMMs (single, double-split) and tested each of them on forty function classes each of which includes more than one hundred instances. The highest prediction sensitivity we achieved is 51% by using double-split HMM with 3-fold cross-validation.

UR - http://www.scopus.com/inward/record.url?scp=14044278130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14044278130&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:14044278130

SN - 0769521940

SN - 9780769521947

T3 - Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004

SP - 670

EP - 671

BT - Proceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004

ER -