Statistical analysis of genemark performance by cross-validation

doi:10.1016/S0097-8485(96)80014-3

Computers & Chemistry

Volume 20, Issue 1, March 1996, Pages 123-133

https://doi.org/10.1016/S0097-8485(96)80014-3 Get rights and content

Abstract

We have explored the performance of the GeneMark gene identification method using cross-validation over learning samples of E. coli DNA sequences. The computations gave more accurate estimations of the error rates in comparison with previous results when a sample of non-coding regions was derived from GenBank sequences with many true coding regions unannotated. The error rate components have been classified and delineated. It was shown that the method performs differently on class I, II and III genes. The most frequent errors come from misinterpreting the coding potential of the complementary sequence in the same frame. The effects of stop-codons present in alternative frames were also studied to understand better the main factors contributing to GeneMark performance.

References (14)

M. Borodovsky et al.
Computers Chem.
(1993)
M. Borodovsky et al.
Trends Biochem. Sci.
(1994)
C. Medigue et al.
J. Mol. Biol.
(1991)
P. Billingsley
Ann. Math. Stat.
(1961)
M. Borodovsky et al.
Molecular Biol.
(1986)
M. Borodovsky et al.
Nucl. Acids Res.
(1994)
J.W. Fickett et al.
Nucleic Acids Res.
(1992)

There are more references available in the full text version of this article.

Cited by (4)

Rapid detection of KPC-producing Klebsiella pneumoniae in China based on MALDI-TOF MS
2022, Journal of Microbiological Methods
Citation Excerpt :
The sequenced genome was assembled using unicycler (Wick, R.R, 2017). Furthermore, tRNA-scan-SE (Kleffe et al., 1996) and Barrnap (https://github.com/tseemann/barrnap/) were used for tRNA prediction and rRNA prediction respectively and Glimmer (Delcher et al., 2007) was used for CDS prediction. The sequence alignment tool, Diamond (https://github.com/bbuchfink/diamond) was used to annotate predicted CDS from the COG database (http://www.genome.jp/kegg/).
Klebsiella pneumoniae carbapenemase-producing K. pneumoniae (KPC-Kp) represent a serious threat to public health and their timely detection is essential for patient management and the prevention of nosocomial infections. Here, matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) was used to rapidly identify dominant KPC-Kp in China, by using an automated detection of a KPC-specific peak (at 4521 m/z) by a genetic algorithm using ClinProTools software. Whole-genome sequencing (WGS) was used to understand the genetic environment of the bla_KPC-2 gene. In this study, we analyzed 235 K. pneumoniae Chinese clinical isolates, of which 175 (93 KPC-positive isolates and 82 KPC-negative isolates) isolates were used to build a model to select a KPC-specific peak, and another 60 isolates for external validation. In addition, all the spectra were visually inspected by the FlexAnalysis software to evaluate the accuracy of the automated detection. The results showed a 4521 m/z peak found in all bla_KPC-2-positive isolates but absent in bla_KPC-2-negative isolates. Interestingly, all KPC-Kp belonged to ST11, the dominant clone in China. WGS analysis of a representative isolate showed that the genetic environment of KPC-2 was IS26-ISKpn27-bla_KPC-2-ΔISKpn6-Tn1721, similar to the KPC-2 genetic environment of ST11 KPC-Kp previously reported in China. Therefore, the 4521 m/z peak is closely related to ST11 KPC-Kp. In summary, we used MALDI-TOF MS to quickly detect KPC-Kp in the process of routine bacterial identification without increasing costs or requiring further knowledge, which has broad application prospects in drug resistance analysis and infection control.
Self-identification of protein-coding regions in microbial genomes
1998, Proceedings of the National Academy of Sciences of the United States of America
GeneGenerator - A flexible algorithm for gene prediction and its application to maize sequences
1998, Bioinformatics
Applications of GeneMark in Multispecies Environments
1996, Proceedings of the 4th International Conference on Intelligent Systems for Molecular Biology, ISMB 1996

View full text

Statistical analysis of genemark performance by cross-validation

Abstract

Computers Chem.

Trends Biochem. Sci.

J. Mol. Biol.

Ann. Math. Stat.

Molecular Biol.

Nucl. Acids Res.

Nucleic Acids Res.