Constrained Markov networks for automated analysis of G-banded chromosomes

C. Guthrie, Jens Gregor, M. G. Thomason

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Automated analysis of chromosome band patterns using probabilistic Markov networks has been reported in previous work. Band patterns are represented as strings of symbols. Inferred from a set of learning strings, a Markov network is a model of intraband and interband relations in these strings. The inference is entirely data-driven and is accomplished using dynamic programming. This paper presents a new model of chromosome band patterns, the constrained Markov network, which is a special case of its predecessor. Substantial experimental evidence of the superiority of the new model over the old is given in terms of equal results in centromere finding and improved results in classification for the 22 autosomes. Furthermore, a method for simplification of constrained Markov networks is shown to be of considerable importance with respect to computational complexity.

Original languageEnglish (US)
Pages (from-to)105-114
Number of pages10
JournalComputers in Biology and Medicine
Volume23
Issue number2
DOIs
StatePublished - Jan 1 1993
Externally publishedYes

Fingerprint

Chromosomes, Human, 21-22 and Y
Chromosomes
Centromere
Learning
Dynamic programming
Computational complexity

All Science Journal Classification (ASJC) codes

  • Computer Science Applications

Cite this

Constrained Markov networks for automated analysis of G-banded chromosomes. / Guthrie, C.; Gregor, Jens; Thomason, M. G.

In: Computers in Biology and Medicine, Vol. 23, No. 2, 01.01.1993, p. 105-114.

Research output: Contribution to journalArticle

@article{5a26407fcfe8436fa0cb6a89dbb94f75,
title = "Constrained Markov networks for automated analysis of G-banded chromosomes",
abstract = "Automated analysis of chromosome band patterns using probabilistic Markov networks has been reported in previous work. Band patterns are represented as strings of symbols. Inferred from a set of learning strings, a Markov network is a model of intraband and interband relations in these strings. The inference is entirely data-driven and is accomplished using dynamic programming. This paper presents a new model of chromosome band patterns, the constrained Markov network, which is a special case of its predecessor. Substantial experimental evidence of the superiority of the new model over the old is given in terms of equal results in centromere finding and improved results in classification for the 22 autosomes. Furthermore, a method for simplification of constrained Markov networks is shown to be of considerable importance with respect to computational complexity.",
author = "C. Guthrie and Jens Gregor and Thomason, {M. G.}",
year = "1993",
month = "1",
day = "1",
doi = "10.1016/0010-4825(93)90142-N",
language = "English (US)",
volume = "23",
pages = "105--114",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Constrained Markov networks for automated analysis of G-banded chromosomes

AU - Guthrie, C.

AU - Gregor, Jens

AU - Thomason, M. G.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - Automated analysis of chromosome band patterns using probabilistic Markov networks has been reported in previous work. Band patterns are represented as strings of symbols. Inferred from a set of learning strings, a Markov network is a model of intraband and interband relations in these strings. The inference is entirely data-driven and is accomplished using dynamic programming. This paper presents a new model of chromosome band patterns, the constrained Markov network, which is a special case of its predecessor. Substantial experimental evidence of the superiority of the new model over the old is given in terms of equal results in centromere finding and improved results in classification for the 22 autosomes. Furthermore, a method for simplification of constrained Markov networks is shown to be of considerable importance with respect to computational complexity.

AB - Automated analysis of chromosome band patterns using probabilistic Markov networks has been reported in previous work. Band patterns are represented as strings of symbols. Inferred from a set of learning strings, a Markov network is a model of intraband and interband relations in these strings. The inference is entirely data-driven and is accomplished using dynamic programming. This paper presents a new model of chromosome band patterns, the constrained Markov network, which is a special case of its predecessor. Substantial experimental evidence of the superiority of the new model over the old is given in terms of equal results in centromere finding and improved results in classification for the 22 autosomes. Furthermore, a method for simplification of constrained Markov networks is shown to be of considerable importance with respect to computational complexity.

UR - http://www.scopus.com/inward/record.url?scp=0027322246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027322246&partnerID=8YFLogxK

U2 - 10.1016/0010-4825(93)90142-N

DO - 10.1016/0010-4825(93)90142-N

M3 - Article

VL - 23

SP - 105

EP - 114

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 2

ER -