Skip to main content

Table 7 The performance of equilibrium probability across RNA families

From: Predicting RNA sequence-structure likelihood via structure-aware deep learning

Families

\(FE_{pos}>FE_{RNAfoldstr}\)

\(FE_{pos}=FE_{RNAfoldstr}\)

\(FE_{pos}<FE_{neg}\)

GI

100%

0%

33.33%

GII

100%

0%

100%

SRP

90%

0%

90%

V &P

77.78%

22.22%

83.33%

sn

83.33%

0%

83.33%

RNP

86.67%

13.33%

100%

IR

75%

0%

50%

HpR

100%

0%

36.36%

HhR

100%

0%

77.78%

oR

70.59%

17.65%

64.71%

Rbo

75%

25%

–

O

75.82%

7.69%

83.52%

C

85.15%

9.90%

–

C\(+\)

80.73%

8.85%

–

  1. Here the column \(FE_{pos}>FE_{RNAfoldstr}\) refers to the percentage of RNAs whose positive sample has greater free energy than the free energy of the corresponding RNAfold predicted structure. The column \(FE_{pos}=FE_{RNAfoldstr}\) refers to the percentage of RNAs whose positive sample has the same free energy as the corresponding RNAfold predicted structure. The column \(FE_{pos}<FE_{neg}\) refers to the percentage of RNAs whose positive sample has lower free energy than the negative sample. C refers to the combination of all RNA categories in this table except the other RNA (O). C\(+\) refers to the combination of C and other RNA (O). Ctgy is the abbreviation of category