Skip to main content

Table 1 Feature set composition, dimension, literature reference

From: Automatic learning of pre-miRNAs from different species

Feature

Feature set

 

FS1

FS2

FS3

FS4

FS 5

FS6

FS7

Select

Di-nucleotide frequencies (XY, X,Y∈{A,C,U,G})

x

       

% G+C

x

x

    

x

 

Maximal length of the amino acid string without stop codons (orf)

      

x

 

Percentage of low complexity regions (dm)

      

x

 

Triplets

   

x

 

x

  

Stacking triplets (X (((,X∈{A,C,G,U})

      

x

 

Motifs (s s−substrings)

    

x

   

Minimum free energy of folding (MFE)

     

x

  

Randfold (p)

     

x

  

Normalized MFE (dG)

x

x

x

   

x

x

MFE index 1 (M F E I 1)

x

x

x

   

x

x

MFE index 2 (M F E I 2)

x

x

x

   

x

x

MFE index 3 (M F E I 3)

x

x

    

x

x

MFE index 4 (M F E I 4)

x

x

    

x

 

Normalized Ensemble Free Energy (NEFE)

x

x

    

x

x

Normalized difference (M F E−E F E) (Diff)

x

x

    

x

x

Frequency of the MFE structure (Freq)

x

       

Normalized base-pairing propensity (dP)

x

 

x

     

Normalized Shannon entropy (dQ)

x

x

x

   

x

x

Structural diversity (Diversity)

x

x

    

x

 

Normalized base-pair distance (dD)

x

 

x

     

Average base pairs per stem (Avg_Bp_Stem)

x

x

    

x

 

Normalized A-U pairs counts (|A−U|/L)

x

x

    

x

 

Normalized G-C pairs counts (|G−C|/L)

x

x

    

x

x

Normalized G-U pairs counts (|G−U|/L)

x

x

    

x

x

Content of A-U pairs per stem (%(A−U)/s t e m s)

x

x

    

x

 

Content of G-C pairs per stem (%(G−C)/s t e m s)

x

x

    

x

 

Content of G-U pairs per stem (%(G−U)/s t e m s)

x

x

    

x

x

Cumulative size of internal loops (loops)

      

x

 

Structure entropy (dS)

x

x

    

x

x

Normalized structure entropy (d S/L)

x

x

    

x

x

Structure enthalpy (dH)

x

       

Normalized structure enthalpy (d H/L)

x

       

Melting energy of the structure

x

       

Normalized melting energy of the structure

x

       

Topological descriptor (dF)

x

x

x

   

x

x

Normalized variants (zG, zP and zQ)

x

       

Normalized variants (zD)

x

x

    

x

 

Normalized variants (zF)

x

       

Dimension

48

21

7

32

1300

34

28

13

Reference

[21]

[21]

[33]

[23]

[34]

[35]

[19]

[12]