MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Sing, Tobias
Beerenwinkel, Niko
dblp
dblp
Not MPG Author(s):
Beerenwinkel, Niko
Editor(s):
Schölkopf, B
Platt, J.
Hoffman, T.
dblp
dblp
dblp
Not MPII Editor(s):
Schölkopf, B
Platt, J.
Hoffman, T.
BibTeX cite key*:
SingNIPS2006
Title, Booktitle
Title*:
Mutagenetic tree Fisher kernel improves prediction of HIV drug resistance from viral genotype
SingNIPS2006.pdf (100.64 KB)
Booktitle*:
Advances in Neural Information Processing Systems 19
Event, URLs
Conference URL::
http://www.nips.cc/Conferences/2006/
Downloading URL:
http://books.nips.cc/papers/files/nips19/NIPS2006_0590.pdf
Event Address*:
Vancouver, B.C., Canada
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
4 December 2006
Event End Date:
7 December 2006
Publisher
Name*:
MIT
URL:
Address*:
Cambridge, MA, USA
Type:
Vol, No, Year, pp.
Series:
Volume:
Number:
Month:
Pages:
1-9
Year*:
2007
VG Wort Pages:
ISBN/ISSN:
Sequence Number:
DOI:
Note, Abstract, ©
(LaTeX) Abstract:
Starting with the work of Jaakkola and Haussler, a variety of approaches have been proposed for coupling domain-specific generative models with statistical learning methods. The link is established by a kernel function which provides a similarity measure based inherently on the underlying model. In computational biology, the full promise of this framework has rarely ever been exploited, as most kernels are derived from very generic models, such as sequence profiles or hidden Markov models. Here, we introduce the MTreeMix kernel, which is based on a generative model tailored to the underlying biological mechanism. Specifically, the kernel quantifies the similarity of evolutionary escape from antiviral drug pressure between two viral sequence samples. We compare this novel kernel to a standard, evolution-agnostic amino acid encoding in the prediction of HIV drug resistance from genotype, using support vector regression. The results show significant improvements in predictive performance across 17 anti-HIV drugs. Thus, in our study, the generative-discriminative paradigm is key to bridging the gap between population genetic modeling and clinical decision making.
Download
Access Level:
Public

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computational Biology and Applied Algorithmics
Audience:
popular
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{SingNIPS2006,
AUTHOR = {Sing, Tobias and Beerenwinkel, Niko},
EDITOR = {Sch{\"o}lkopf, B and Platt, J. and Hoffman, T.},
TITLE = {Mutagenetic tree {F}isher kernel improves prediction of {HIV} drug resistance from viral genotype},
BOOKTITLE = {Advances in Neural Information Processing Systems 19},
PUBLISHER = {MIT},
YEAR = {2007},
PAGES = {1--9},
ADDRESS = {Vancouver, B.C., Canada},
}


Entry last modified by Elena Zotenko, 04/01/2009
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
Andre Altmann
Created
02/20/2007 04:36:34 PM
Revisions
6.
5.
4.
3.
2.
Editor(s)
Elena Zotenko
Uwe Brahm
Christine Kiesel
Christine Kiesel
Christine Kiesel
Edit Dates
04/01/2009 03:39:43 PM
2007-07-19 15:30:37
03.07.2007 16:30:22
03.07.2007 16:29:22
03.07.2007 16:12:32