A machine-learning approach to combined evidence validation of genome assemblies

Jeong-Hyeon Choi, Sun Kim, Haixu Tang, Justen Andrews, Don G. Gilbert, John K. Colbourne

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Motivation: While it is common to refer to 'the genome sequence' as if it were a single, complete and contiguous DNA string, it is in fact an assembly of millions of small, partially overlapping DNA fragments. Sophisticated computer algorithms (assemblers and scaffolders) merge these DNA fragments into contigs, and place these contigs into sequence scaffolds using the paired-end sequences derived from large-insert DNA libraries. Each step in this automated process is susceptible to producing errors; hence, the resulting draft assembly represents (in practice) only a likely assembly that requires further validation. Knowing which parts of the draft assembly are likely free of errors is critical if researchers are to draw reliable conclusions from the assembled sequence data. Results: We develop a machine-learning method to detect assembly errors in sequence assemblies. Several in silico measures for assembly validation have been proposed by various researchers. Using three benchmarking Drosophila draft genomes, we evaluate these techniques along with some new measures that we propose, including the good-minus-bad coverage (GMB), the good-to-bad-ratio (RGB), the average Z-score (AZ) and the average absolute Z-score (ASZ). Our results show that the GMB measure performs better than the others in both its sensitivity and its specificity for assembly error detection. Nevertheless, no single method performs sufficiently well to reliably detect genomic regions requiring attention for further experimental verification. To utilize the advantages of all these measures, we develop a novel machine learning approach that combines these individual measures to achieve a higher prediction accuracy (i.e. greater than 90%). Our combined evidence approach avoids the difficult and often ad hoc selection of many parameters the individual measures require, and significantly improves the overall precisions on the benchmarking data sets.

Original languageEnglish (US)
Pages (from-to)744-750
Number of pages7
JournalBioinformatics
Volume24
Issue number6
DOIs
StatePublished - Mar 1 2008
Externally publishedYes

Fingerprint

Learning systems
Benchmarking
Machine Learning
Genome
Genes
DNA
Research Personnel
Z-score
Gene Library
Computer Simulation
Drosophila
Sensitivity and Specificity
Fragment
Coverage
Likely
Evidence
Error Detection
Scaffold
Error detection
Drosophilidae

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

A machine-learning approach to combined evidence validation of genome assemblies. / Choi, Jeong-Hyeon; Kim, Sun; Tang, Haixu; Andrews, Justen; Gilbert, Don G.; Colbourne, John K.

In: Bioinformatics, Vol. 24, No. 6, 01.03.2008, p. 744-750.

Research output: Contribution to journalArticle

Choi, J-H, Kim, S, Tang, H, Andrews, J, Gilbert, DG & Colbourne, JK 2008, 'A machine-learning approach to combined evidence validation of genome assemblies', Bioinformatics, vol. 24, no. 6, pp. 744-750. https://doi.org/10.1093/bioinformatics/btm608
Choi, Jeong-Hyeon ; Kim, Sun ; Tang, Haixu ; Andrews, Justen ; Gilbert, Don G. ; Colbourne, John K. / A machine-learning approach to combined evidence validation of genome assemblies. In: Bioinformatics. 2008 ; Vol. 24, No. 6. pp. 744-750.
@article{a2dad40f5b924f769bec514cde657a38,
title = "A machine-learning approach to combined evidence validation of genome assemblies",
abstract = "Motivation: While it is common to refer to 'the genome sequence' as if it were a single, complete and contiguous DNA string, it is in fact an assembly of millions of small, partially overlapping DNA fragments. Sophisticated computer algorithms (assemblers and scaffolders) merge these DNA fragments into contigs, and place these contigs into sequence scaffolds using the paired-end sequences derived from large-insert DNA libraries. Each step in this automated process is susceptible to producing errors; hence, the resulting draft assembly represents (in practice) only a likely assembly that requires further validation. Knowing which parts of the draft assembly are likely free of errors is critical if researchers are to draw reliable conclusions from the assembled sequence data. Results: We develop a machine-learning method to detect assembly errors in sequence assemblies. Several in silico measures for assembly validation have been proposed by various researchers. Using three benchmarking Drosophila draft genomes, we evaluate these techniques along with some new measures that we propose, including the good-minus-bad coverage (GMB), the good-to-bad-ratio (RGB), the average Z-score (AZ) and the average absolute Z-score (ASZ). Our results show that the GMB measure performs better than the others in both its sensitivity and its specificity for assembly error detection. Nevertheless, no single method performs sufficiently well to reliably detect genomic regions requiring attention for further experimental verification. To utilize the advantages of all these measures, we develop a novel machine learning approach that combines these individual measures to achieve a higher prediction accuracy (i.e. greater than 90{\%}). Our combined evidence approach avoids the difficult and often ad hoc selection of many parameters the individual measures require, and significantly improves the overall precisions on the benchmarking data sets.",
author = "Jeong-Hyeon Choi and Sun Kim and Haixu Tang and Justen Andrews and Gilbert, {Don G.} and Colbourne, {John K.}",
year = "2008",
month = "3",
day = "1",
doi = "10.1093/bioinformatics/btm608",
language = "English (US)",
volume = "24",
pages = "744--750",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - A machine-learning approach to combined evidence validation of genome assemblies

AU - Choi, Jeong-Hyeon

AU - Kim, Sun

AU - Tang, Haixu

AU - Andrews, Justen

AU - Gilbert, Don G.

AU - Colbourne, John K.

PY - 2008/3/1

Y1 - 2008/3/1

N2 - Motivation: While it is common to refer to 'the genome sequence' as if it were a single, complete and contiguous DNA string, it is in fact an assembly of millions of small, partially overlapping DNA fragments. Sophisticated computer algorithms (assemblers and scaffolders) merge these DNA fragments into contigs, and place these contigs into sequence scaffolds using the paired-end sequences derived from large-insert DNA libraries. Each step in this automated process is susceptible to producing errors; hence, the resulting draft assembly represents (in practice) only a likely assembly that requires further validation. Knowing which parts of the draft assembly are likely free of errors is critical if researchers are to draw reliable conclusions from the assembled sequence data. Results: We develop a machine-learning method to detect assembly errors in sequence assemblies. Several in silico measures for assembly validation have been proposed by various researchers. Using three benchmarking Drosophila draft genomes, we evaluate these techniques along with some new measures that we propose, including the good-minus-bad coverage (GMB), the good-to-bad-ratio (RGB), the average Z-score (AZ) and the average absolute Z-score (ASZ). Our results show that the GMB measure performs better than the others in both its sensitivity and its specificity for assembly error detection. Nevertheless, no single method performs sufficiently well to reliably detect genomic regions requiring attention for further experimental verification. To utilize the advantages of all these measures, we develop a novel machine learning approach that combines these individual measures to achieve a higher prediction accuracy (i.e. greater than 90%). Our combined evidence approach avoids the difficult and often ad hoc selection of many parameters the individual measures require, and significantly improves the overall precisions on the benchmarking data sets.

AB - Motivation: While it is common to refer to 'the genome sequence' as if it were a single, complete and contiguous DNA string, it is in fact an assembly of millions of small, partially overlapping DNA fragments. Sophisticated computer algorithms (assemblers and scaffolders) merge these DNA fragments into contigs, and place these contigs into sequence scaffolds using the paired-end sequences derived from large-insert DNA libraries. Each step in this automated process is susceptible to producing errors; hence, the resulting draft assembly represents (in practice) only a likely assembly that requires further validation. Knowing which parts of the draft assembly are likely free of errors is critical if researchers are to draw reliable conclusions from the assembled sequence data. Results: We develop a machine-learning method to detect assembly errors in sequence assemblies. Several in silico measures for assembly validation have been proposed by various researchers. Using three benchmarking Drosophila draft genomes, we evaluate these techniques along with some new measures that we propose, including the good-minus-bad coverage (GMB), the good-to-bad-ratio (RGB), the average Z-score (AZ) and the average absolute Z-score (ASZ). Our results show that the GMB measure performs better than the others in both its sensitivity and its specificity for assembly error detection. Nevertheless, no single method performs sufficiently well to reliably detect genomic regions requiring attention for further experimental verification. To utilize the advantages of all these measures, we develop a novel machine learning approach that combines these individual measures to achieve a higher prediction accuracy (i.e. greater than 90%). Our combined evidence approach avoids the difficult and often ad hoc selection of many parameters the individual measures require, and significantly improves the overall precisions on the benchmarking data sets.

UR - http://www.scopus.com/inward/record.url?scp=40749116115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40749116115&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btm608

DO - 10.1093/bioinformatics/btm608

M3 - Article

VL - 24

SP - 744

EP - 750

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 6

ER -