Mining housekeeping genes with a Naive Bayes classifier

Luna De Ferrari; Stuart Aitken

doi:10.1186/1471-2164-7-277

Mining housekeeping genes with a Naive Bayes classifier

Luna De Ferrari, Stuart Aitken

Deanery of Molecular, Genetic and Population Health Sciences

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

BACKGROUND: Traditionally, housekeeping and tissue specific genes have been classified using direct assay of mRNA presence across different tissues, but these experiments are costly and the results not easy to compare and reproduce.

RESULTS: In this work, a Naive Bayes classifier based only on physical and functional characteristics of genes already available in databases, like exon length and measures of chromatin compactness, has achieved a 97% success rate in classification of human housekeeping genes (93% for mouse and 90% for fruit fly).

CONCLUSION: The newly obtained lists of housekeeping and tissue specific genes adhere to the expected functions and tissue expression patterns for the two classes. Overall, the classifier shows promise, and in the future additional attributes might be included to improve its discriminating power.

Original language	English
Pages (from-to)	277
Number of pages	14
Journal	BMC Genomics
Volume	7
Issue number	277
DOIs	https://doi.org/10.1186/1471-2164-7-277
Publication status	Published - 2006

Keywords / Materials (for Non-textual outputs)

Animals
Base Sequence
Bayes Theorem
Chromatin
Computational Biology
DNA, Complementary
Databases, Genetic
Drosophila
Exons
Humans
Mice
Organ Specificity
RNA, Messenger
ROC Curve

Access to Document

10.1186/1471-2164-7-277

Open Access - Mining housekeeping genes with a Naive Bayes classifier
© 2006 De Ferrari and Aitken; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Final published version, 403 KB

http://www.biomedcentral.com/1471-2164/7/277

Cite this

@article{7cc82ce25f9048e88fccc7cecc6d48c4,

title = "Mining housekeeping genes with a Naive Bayes classifier",

abstract = "BACKGROUND: Traditionally, housekeeping and tissue specific genes have been classified using direct assay of mRNA presence across different tissues, but these experiments are costly and the results not easy to compare and reproduce.RESULTS: In this work, a Naive Bayes classifier based only on physical and functional characteristics of genes already available in databases, like exon length and measures of chromatin compactness, has achieved a 97% success rate in classification of human housekeeping genes (93% for mouse and 90% for fruit fly).CONCLUSION: The newly obtained lists of housekeeping and tissue specific genes adhere to the expected functions and tissue expression patterns for the two classes. Overall, the classifier shows promise, and in the future additional attributes might be included to improve its discriminating power.",

keywords = "Animals, Base Sequence, Bayes Theorem, Chromatin, Computational Biology, DNA, Complementary, Databases, Genetic, Drosophila, Exons, Humans, Mice, Organ Specificity, RNA, Messenger, ROC Curve",

author = "{De Ferrari}, Luna and Stuart Aitken",

year = "2006",

doi = "10.1186/1471-2164-7-277",

language = "English",

volume = "7",

pages = "277",

journal = "BMC Genomics",

issn = "1471-2164",

publisher = "BioMed Central",

number = "277",

}

TY - JOUR

T1 - Mining housekeeping genes with a Naive Bayes classifier

AU - De Ferrari, Luna

AU - Aitken, Stuart

PY - 2006

Y1 - 2006

N2 - BACKGROUND: Traditionally, housekeeping and tissue specific genes have been classified using direct assay of mRNA presence across different tissues, but these experiments are costly and the results not easy to compare and reproduce.RESULTS: In this work, a Naive Bayes classifier based only on physical and functional characteristics of genes already available in databases, like exon length and measures of chromatin compactness, has achieved a 97% success rate in classification of human housekeeping genes (93% for mouse and 90% for fruit fly).CONCLUSION: The newly obtained lists of housekeeping and tissue specific genes adhere to the expected functions and tissue expression patterns for the two classes. Overall, the classifier shows promise, and in the future additional attributes might be included to improve its discriminating power.

AB - BACKGROUND: Traditionally, housekeeping and tissue specific genes have been classified using direct assay of mRNA presence across different tissues, but these experiments are costly and the results not easy to compare and reproduce.RESULTS: In this work, a Naive Bayes classifier based only on physical and functional characteristics of genes already available in databases, like exon length and measures of chromatin compactness, has achieved a 97% success rate in classification of human housekeeping genes (93% for mouse and 90% for fruit fly).CONCLUSION: The newly obtained lists of housekeeping and tissue specific genes adhere to the expected functions and tissue expression patterns for the two classes. Overall, the classifier shows promise, and in the future additional attributes might be included to improve its discriminating power.

KW - Animals

KW - Base Sequence

KW - Bayes Theorem

KW - Chromatin

KW - Computational Biology

KW - DNA, Complementary

KW - Databases, Genetic

KW - Drosophila

KW - Exons

KW - Humans

KW - Mice

KW - Organ Specificity

KW - RNA, Messenger

KW - ROC Curve

U2 - 10.1186/1471-2164-7-277

DO - 10.1186/1471-2164-7-277

M3 - Article

C2 - 17074078

SN - 1471-2164

VL - 7

SP - 277

JO - BMC Genomics

JF - BMC Genomics

IS - 277

ER -

Mining housekeeping genes with a Naive Bayes classifier

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this