Book contents
- Frontmatter
- Contents
- Foreword by Steven Salzberg
- Preface
- Acknowledgements
- 1 Introduction
- 2 Mathematical preliminaries
- 3 Overview of computational gene prediction
- 4 Gene finder evaluation
- 5 A toy exon finder
- 6 Hidden Markov models
- 7 Signal and content sensors
- 8 Generalized hidden Markov models
- 9 Comparative gene finding
- 10 Machine-learning methods
- 11 Tips and tricks
- 12 Advanced topics
- Appendix
- References
- Index
11 - Tips and tricks
Published online by Cambridge University Press: 05 June 2012
- Frontmatter
- Contents
- Foreword by Steven Salzberg
- Preface
- Acknowledgements
- 1 Introduction
- 2 Mathematical preliminaries
- 3 Overview of computational gene prediction
- 4 Gene finder evaluation
- 5 A toy exon finder
- 6 Hidden Markov models
- 7 Signal and content sensors
- 8 Generalized hidden Markov models
- 9 Comparative gene finding
- 10 Machine-learning methods
- 11 Tips and tricks
- 12 Advanced topics
- Appendix
- References
- Index
Summary
In this chapter we describe a number of heuristics which we have found useful during the implementation, training, and/or deployment of practical gene finding systems for real genome annotation tasks.
Boosting
A well-known trick from the field of machine learning is boosting. This technique has been applied to the training of gene finders in the following way, with modest accuracy improvements being observed in a number of cases.
Suppose that while training a signal sensor for a GHMM-based gene finder we notice that a number of positive examples are assigned relatively poor scores by the newly trained sensor. One approach to boosting involves duplicating these examples in the training set and then re-training the sensor from scratch. The duplicated, low-scoring examples will now have a greater impact on the parameter estimation process due to their being present multiple times in the training set, so that the re-trained sensor is more likely to assign a higher score to those examples. Assuming that the low-scoring examples are not mislabeled training features, improvements to the accuracy of the resulting gene finder might be expected when the gene finder is later deployed on sequences having genes with similar characteristics to the duplicated examples. Care must be taken to avoid overtraining, however. To the extent that a gene finder with optimal genome-wide accuracy is desired, it is important that boosting not be allowed to bias the gene finder in way that is significantly inconsistent with the actual frequency of these difficult signals in the genome.
- Type
- Chapter
- Information
- Methods for Computational Gene Prediction , pp. 358 - 368Publisher: Cambridge University PressPrint publication year: 2007