Skip to main content

Table 2 Summary of the datasets employed in this study

From: Real value prediction of protein solvent accessibility using enhanced PSSM features

Dataset # of chains # of residues Mean of RSA (%) Standard deviation of RSA (%)
Barton 500 83448 28.9 28.1
   set1 166 26274 28.4 27.8
   set2 167 26720 28.7 28.1
   set3 167 30454 29.6 28.3
Carugo 338 82178 29.9 28.4
   set1 113 28871 29.3 28.4
   set2 113 27354 29.9 28.4
   set3 112 25953 30.5 28.3
Manesh 215 50682 28.5 27.3
   set1 72 18770 27.5 26.9
   set2 72 15264 29.2 27.4
   set3 71 16648 28.9 27.6
SMA11 42 6632 27.6 27.5
SMA22 42 7680 30.9 28.3
  1. 1This is a subset of the Barton set1. 2This is a subset of the Barton set3.