Prediction of peptide bonding affinity: kernel methods for nonlinear modeling.
Tue, 08/30/2011 - 15:01 — SomNambul
Abstract
Authors: Charles Bergeron, Theresa Hepburn, C. Matthew Sundling, Michael Krein, Bill Katt, Nagamani Sukumar, Curt M. Breneman, Kristin P. Bennett
Subjects: Machine Learning
link: http://arxiv.org/abs/1108.5397Subjects: Machine Learning
Abstract
This paper presents regression models obtained from a process of blind
prediction of peptide binding affinity from provided descriptors for several
distinct datasets as part of the 2006 Comparative Evaluation of Prediction
Algorithms (COEPRA) contest. This paper finds that kernel partial least
squares, a nonlinear partial least squares (PLS) algorithm, outperforms PLS,
and that the incorporation of transferable atom equivalent features improves
predictive capability.
User login
Loading
exciting and informational.
Sat, 02/18/2012 - 15:55 — juliarobertYour article is very exciting and informational. I am trying to decide on a career move and this has helped me with one aspect. Thank you so much!
70-455/ / 70-529/ / 77-882/ / mb2-634/ / mb2-867/ / 70-175/ / 70-225/ / 70-296/ /