Table 1 Maximum sequence similarities of test proteins to the proteins used in the model training

From: Navigating protein landscapes with a machine-learned transferable coarse-grained model

Test protein

Length (amino acids)

Sequence similarity to train (%)

DYGCSIHP

8

38

SLEAGGRG

8

50

Chignolin (2RVD)

10

40

TRPcage (2JOF)

20

35

BBA (1FME)

28

29

Villin (1YRF)

35

26

Homeodomain (1ENH)

54

20

SH3 (2NUZ)

55

24

CI2 (2CI2)

65

18

PaaA2 (3ZBE)

71

17

Alpha3D (2A3D)

73

19

S6 (1RIS)

97

16

  1. Details on sequence similarity are in Supplementary Section 5.3.