Supplementary data for "Learning Sparse Models for a Dynamic Bayesian Network Classifier of Protein Secondary Structure"
Zafer Aydin, Ajit Singh, Jeffrey Bilmes and William Stafford Noble
Submitted for publication.
Each of the links below points to a gzipped tar file containing the specified files.
- The CB513, PDB-PC20, and SD576 benchmark data sets, each containing
- The protein sequences and the corresponding secondary structure labels in FASTA format.
- The PSI-BLAST PSSMs.
- Various python and shell scripts used in running the experiments with the real data as well as the synthetic data. See the accompanying README file for documentation.
- The GMTK Linux binary and documentation.