advertisement: compare things at compare-stuff.com!
next up previous contents
Next: Non-ribbon architectures Up: Prediction of mainly- architectures Previous: Ribbon or not ribbon?   Contents

Ribbon, barrel or sandwich?

An alternative experiment involves performing `predictions' for only barrel, sandwich and ribbon architectures. These are not particularly useful predictions because one cannot be certain in a blind prediction that the novel sequence has one of these architectures. However, the results are interesting and are also relevant to Section 3.5. The 94 domains (see Table 3.3 for the numbers of each type) are predicted with 69% accuracy (quartiles: 83%, 75%, 74% and 46%, random accuracy 43%). The improvement (compared with 50% for 12-architecture prediction) is to be expected since the task is easier. The Matthews coefficients are also higher: $C_{ribbon}=0.735$, $C_{barrel}=0.414$ and $C_{sandwich}=0.401$.



Copyright Bob MacCallum - DISCLAIMER: this was written in 1997 and may contain out-of-date information.