Back to Search
Start Over
SVM2Motif--Reconstructing Overlapping DNA Sequence Motifs by Mimicking an SVM Predictor
- Source :
- PLoS ONE, PLoS ONE, Vol 10, Iss 12, p e0144782 (2015)
- Publication Year :
- 2015
-
Abstract
- Identifying discriminative motifs underlying the functionality and evolution of organisms is a major challenge in computational biology. Machine learning approaches such as support vector machines (SVMs) achieve state-of-the-art performances in genomic discrimination tasks, but--due to its black-box character--motifs underlying its decision function are largely unknown. As a remedy, positional oligomer importance matrices (POIMs) allow us to visualize the significance of position-specific subsequences. Although being a major step towards the explanation of trained SVM models, they suffer from the fact that their size grows exponentially in the length of the motif, which renders their manual inspection feasible only for comparably small motif sizes, typically k ≤ 5. In this work, we extend the work on positional oligomer importance matrices, by presenting a new machine-learning methodology, entitled motifPOIM, to extract the truly relevant motifs--regardless of their length and complexity--underlying the predictions of a trained SVM model. Our framework thereby considers the motifs as free parameters in a probabilistic model, a task which can be phrased as a non-convex optimization problem. The exponential dependence of the POIM size on the oligomer length poses a major numerical challenge, which we address by an efficient optimization framework that allows us to find possibly overlapping motifs consisting of up to hundreds of nucleotides. We demonstrate the efficacy of our approach on a synthetic data set as well as a real-world human splice site data set.
- Subjects :
- Optimization problem
lcsh:Medicine
Synthetic data
Machine Learning
Discriminative model
Exponential growth
Humans
Nucleotide Motifs
lcsh:Science
Physics
Genetics
Multidisciplinary
Models, Genetic
business.industry
lcsh:R
Statistical model
Pattern recognition
Sequence Analysis, DNA
Support vector machine
Kernel method
ComputingMethodologies_PATTERNRECOGNITION
lcsh:Q
Artificial intelligence
business
Free parameter
Research Article
Subjects
Details
- ISSN :
- 19326203
- Volume :
- 10
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- PloS one
- Accession number :
- edsair.doi.dedup.....3b5231d7e18830dcb847af2ef26f3ac2