Skip to main content

Table 11 Comparison of structures with Proteinnet DSSP8 dataset

From: AttSec: protein secondary structure prediction by capturing local patterns from attention map

Methods

TEST2018

SPOT-2016

SPOT-2016-HQ

SPOT-2018

SPOT-2018-HQ

AttSec(this work)

77.4

70.5

73.0

71.4

72.4

Transformer only

76.9

70.2

72.4

71.1

71.8

LM’s attention

75.3

68.7

70.7

69.4

70.1