Research article
Pairwise covariance adds little to secondary structure prediction but improves the prediction of non-canonical local structure
-
* Corresponding author: Christopher Bystroff bystrc@rpi.edu
1 Departments of Biology and Computer Science, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy NY, USA
2 Computational Biology and Bioinformatics, Pacific Northwest National Laboratory, Richland, WA, USA
BMC Bioinformatics 2008, 9:429 doi:10.1186/1471-2105-9-429
Published: 10 October 2008Additional files
Additional file 1:
Supplementary Data and Methods. The following are included as Supplementary Data. (1) The contents and method for construction of the training and testing data sets. (2) The method for fitting the confidence curve. (3)The method for defining the nine amino acid profile classes. (4) Another case study, the amphipathic helix motif. (5) A more detailed analysis of the differences between the three training stategies. (6) The history of the I-sites Library and a short description of the web server. A sample of webserver output is shown. (7) A figure illustrating the supervised learning approach.
Format: DOC Size: 969KB Download file
This file can be viewed with: Microsoft Word Viewer
