Skip to main content

Table 12 Performance of BioHEL on learning CN and RSA using the alphabet optimized for the other dataset.

From: Automated Alphabet Reduction for Protein Datasets

Alphabet % Acc. on CN dataset % Acc. on RSA dataset
AA 74.0 ± 0.6 70.7 ± 0.4
DualRMI 73.3 ± 0.5 70.3 ± 0.4
DualRMI-alt 73.3 ± 0.7 69.53 ± 0.7•
  1. A • marks reduced datasets where BioHEL obtains a performance significantly worse than the AA type dataset according to the statistical t-tests with a 99% confidence level. No significant differences were detected between the reduced alphabets.