Skip to main content

Table 2 8 AI vs. 8 TE

From: Ab initio and template-based prediction of multi-class distance maps by two-dimensional recursive neural networks

Ā 

10

20

30

40

50

60

70

80

90

ā‰„ 90

All

8 AI

98.1

97.5

97.8

97.8

98.0

97.7

98.1

97.7

98.0

98.2

97.9

8 TE

98.1

97.7

98.5

98.9

99.2

99.3

99.5

99.3

99.5

99.7

98.9

  1. Percentage of correctly classified residue pairs for the ab initio (8 AI ) and template based 8 ƅ predictor (8 TE ) as a function of sequence identity to the best template. Template sequence identity 10 means all proteins that have a best hit template in the identity range [0, 10) %, All is the complete set.