Using Varying Negative Examples to Improve Computational Predictions of Transcription Factor Binding Sites

Rezwan, Faisal I.; Sun, Yi; Davey, Neil; Adams, Rod; Rust, Alistair G.; Robinson, Mark

doi:10.1007/978-3-642-32909-8_24

Cited by 1 publication

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of this is not just to characterize the classes of the existing data, but to be able to extrapolate the likely class of previously unclassified data. We have used this technique in another related bioinformatics project [86]. There are many machine learning tools that can be used, such as Support Vector Machines, Random Forests and Bayesian methods.…”

Section: Machine Learning To Identify R Genes Lacking Conserved Domainsmentioning

confidence: 99%

See 1 more Smart Citation

Review of combinations of experimental and computational techniques to identify and understand genes involved in innate immunity and effector-triggered defence

Stotz

Almeida

Davey

et al. 2017

Methods

Self Cite

View full text Add to dashboard Cite

The innate immune system includes a first layer of defence that recognises conserved pathogen-associated molecular patterns that are essential for microbial fitness. Resistance (R) gene-based recognition of pathogen effectors, which function in modulation or avoidance of host immunity, activates a second layer of plant defence. In this review, experimental and computational techniques are considered to improve understanding of the plant immune system. Biocomputation contributes to discovery of the molecular genetic basis of host resistance against pathogens. Sequenced genomes have been used to identify R genes in plants. Resistance gene enrichment sequencing based on conserved protein domains has increased the number of R genes with nucleotide-binding site and leucine-rich repeat domains. Network analysis will contribute to an improved understanding of the innate immune system and identify novel genes for partial disease resistance. Machine learning algorithms are expected to become important in defining aspects of the immune system that are less well characterised, including identification of R genes that lack conserved protein domains.

show abstract

Section: Machine Learning To Identify R Genes Lacking Conserved Domainsmentioning

confidence: 99%

“…This will be the case if ''near missies" are well represented as such cases are particularly useful in determining high quality decision boundaries. An extended discussion of this issue has been published [86].…”

Section: Machine Learning To Identify R Genes Lacking Conserved Domainsmentioning

confidence: 99%

Review of combinations of experimental and computational techniques to identify and understand genes involved in innate immunity and effector-triggered defence

Stotz

Almeida

Davey

et al. 2017

Methods

Self Cite

View full text Add to dashboard Cite

show abstract

Using Varying Negative Examples to Improve Computational Predictions of Transcription Factor Binding Sites

Cited by 1 publication

References 11 publications

Review of combinations of experimental and computational techniques to identify and understand genes involved in innate immunity and effector-triggered defence

Review of combinations of experimental and computational techniques to identify and understand genes involved in innate immunity and effector-triggered defence

Contact Info

Product

Resources

About