Cargando…
Learning Interpretable SVMs for Biological Sequence Classification
BACKGROUND: Support Vector Machines (SVMs) – using a variety of string kernels – have been successfully applied to biological sequence classification problems. While SVMs achieve high classification accuracy they lack interpretability. In many applications, it does not suffice that an algorithm just...
Autores principales: | , , |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2006
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1810320/ https://www.ncbi.nlm.nih.gov/pubmed/16723012 http://dx.doi.org/10.1186/1471-2105-7-S1-S9 |
_version_ | 1782132577800290304 |
---|---|
author | Rätsch, Gunnar Sonnenburg, Sören Schäfer, Christin |
author_facet | Rätsch, Gunnar Sonnenburg, Sören Schäfer, Christin |
author_sort | Rätsch, Gunnar |
collection | PubMed |
description | BACKGROUND: Support Vector Machines (SVMs) – using a variety of string kernels – have been successfully applied to biological sequence classification problems. While SVMs achieve high classification accuracy they lack interpretability. In many applications, it does not suffice that an algorithm just detects a biological signal in the sequence, but it should also provide means to interpret its solution in order to gain biological insight. RESULTS: We propose novel and efficient algorithms for solving the so-called Support Vector Multiple Kernel Learning problem. The developed techniques can be used to understand the obtained support vector decision function in order to extract biologically relevant knowledge about the sequence analysis problem at hand. We apply the proposed methods to the task of acceptor splice site prediction and to the problem of recognizing alternatively spliced exons. Our algorithms compute sparse weightings of substring locations, highlighting which parts of the sequence are important for discrimination. CONCLUSION: The proposed method is able to deal with thousands of examples while combining hundreds of kernels within reasonable time, and reliably identifies a few statistically significant positions. |
format | Text |
id | pubmed-1810320 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2006 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-18103202007-03-14 Learning Interpretable SVMs for Biological Sequence Classification Rätsch, Gunnar Sonnenburg, Sören Schäfer, Christin BMC Bioinformatics Proceedings BACKGROUND: Support Vector Machines (SVMs) – using a variety of string kernels – have been successfully applied to biological sequence classification problems. While SVMs achieve high classification accuracy they lack interpretability. In many applications, it does not suffice that an algorithm just detects a biological signal in the sequence, but it should also provide means to interpret its solution in order to gain biological insight. RESULTS: We propose novel and efficient algorithms for solving the so-called Support Vector Multiple Kernel Learning problem. The developed techniques can be used to understand the obtained support vector decision function in order to extract biologically relevant knowledge about the sequence analysis problem at hand. We apply the proposed methods to the task of acceptor splice site prediction and to the problem of recognizing alternatively spliced exons. Our algorithms compute sparse weightings of substring locations, highlighting which parts of the sequence are important for discrimination. CONCLUSION: The proposed method is able to deal with thousands of examples while combining hundreds of kernels within reasonable time, and reliably identifies a few statistically significant positions. BioMed Central 2006-03-20 /pmc/articles/PMC1810320/ /pubmed/16723012 http://dx.doi.org/10.1186/1471-2105-7-S1-S9 Text en |
spellingShingle | Proceedings Rätsch, Gunnar Sonnenburg, Sören Schäfer, Christin Learning Interpretable SVMs for Biological Sequence Classification |
title | Learning Interpretable SVMs for Biological Sequence Classification |
title_full | Learning Interpretable SVMs for Biological Sequence Classification |
title_fullStr | Learning Interpretable SVMs for Biological Sequence Classification |
title_full_unstemmed | Learning Interpretable SVMs for Biological Sequence Classification |
title_short | Learning Interpretable SVMs for Biological Sequence Classification |
title_sort | learning interpretable svms for biological sequence classification |
topic | Proceedings |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1810320/ https://www.ncbi.nlm.nih.gov/pubmed/16723012 http://dx.doi.org/10.1186/1471-2105-7-S1-S9 |
work_keys_str_mv | AT ratschgunnar learninginterpretablesvmsforbiologicalsequenceclassification AT sonnenburgsoren learninginterpretablesvmsforbiologicalsequenceclassification AT schaferchristin learninginterpretablesvmsforbiologicalsequenceclassification |