Table 3 A ranked list of all features used in this work. The score is calculated by the ReliefF method
From: TargetSpy: a supervised machine learning approach for microRNA target prediction
Rank | Features | Score |
|---|---|---|
1 | Number of base parings to the microRNA 8-mer seed | 0.03175 |
2 | G+C content of target site | 0.01263 |
3 | Number of base pairings to the first 8 nucleotides of the microRNA 3' end | 0.01038 |
4 | Number of consecutive base-pairings to the microRNA 3' end with two allowed non-pairing positions | 0.00995 |
5 | Occurrence of CpG in target site | 0.00799 |
6 | G+C content ratio between the microRNA and the target site | 0.00642 |
7 | Compactness | 0.00619 |
8 | T9 anchor | 0.00556 |
9 | Longest stretch of consecutive base-pairings in the hybrid | 0.00513 |
10 | Number of bulges in the microRNA of size three | 0.00498 |
11 | T1 S/W anchor | 0.00491 |
12 | Total number of base-pairings | 0.00475 |
13 | Number of bulges on the target site of size seven or greater | 0.00442 |
14 | T1 anchor | 0.00434 |
15 | Number of bulges in the microRNA of size two | 0.00433 |
16 | Occurrence of CpG in the upstream flanking area | 0.00383 |
17 | Number of bulges in the target site of size one | 0.00374 |
18 | Total bulge length of the target site | 0.00362 |
19 | Length of the target site | 0.00336 |
20 | Total bulge length of the microRNA | 0.00334 |
21 | Target site position within the 3'UTR | 0.00333 |
22 | Number of symmetric bulges | 0.00290 |
23 | G + C content upstream of the target site | 0.00287 |
24 | Number of bulges on the target site | 0.00286 |
25 | Length of the second largest bulge on the target site | 0.00268 |
26 | Mean length of bulges on the target site | 0.00263 |
27 | T9 S/W anchor | 0.00261 |
28 | Binding asymmetry | 0.00255 |
29 | Number of bulges in the target site of size two | 0.00240 |
30 | Total number of G:U wobble base pairs | 0.00227 |
31 | Local RISC accessibility 30/30 | 0.00220 |
32 | Local RISC accessibility 3/15 | 0.00215 |
33 | Number of bulges in the target site of size four | 0.00210 |
34 | Difference in G+C content between the first and the last nt of the target site | 0.00201 |
35 | Occurrence of CpG in downstream flanking area | 0.00179 |
36 | Number of bulges in the microRNA of size one | 0.00179 |
37 | Length of the second largest bulge on the microRNA | 0.00174 |
38 | Number of bulges on the microRNA | 0.00153 |
39 | Number of bulges in the microRNA of size five | 0.00128 |
40 | Number of bulges in the target site of size three | 0.00113 |
41 | Difference in G + C content between the target site and the 20 nt upstream and downstream flanking region | 0.00112 |
42 | Number of bulges in the target site of size five | 0.00100 |
43 | Number of bulges in the microRNA of size four | 0.00084 |
44 | G+C content downstream of the target site | 0.00084 |
45 | Number of bulges in the target site of size six | 0.00021 |