Table 2 Univariate ranked features according to their AUPR (AUC)
From: Identification of long non-coding transcripts with feature selection: a comparative study
Human | Mouse | Zebrafish | ||||
|---|---|---|---|---|---|---|
Feature | AUPR (AUC) | Feature | AUPR (AUC) | Feature | AUPR (AUC) | |
1 | ph100m | 0.62 (0.92) | phm | 0.43 (0.90) | py8m | 0.27 (0.83) |
2 | ph20m | 0.54 (0.91) | py60m | 0.36 (0.90) | ph8m | 0.25 (0.79) |
3 | ph20mx | 0.52 (0.89) | phmx | 0.34 (0.87) | TxLen | 0.18 (0.72) |
4 | py100mx | 0.52 (0.91) | py60mx | 0.32 (0.88) | FickScore | 0.17 (0.73) |
5 | py100m | 0.48 (0.91) | phmn | 0.25 (0.81) | TxNex | 0.16 (0.77) |
6 | py20m | 0.43 (0.89) | CG | 0.16 (0.70) | GG | 0.15 (0.66) |
7 | TxNex | 0.26 (0.76) | GCG | 0.15 (0.68) | TAA | 0.15 (0.67) |
8 | ph20mn | 0.25 (0.77) | CGC | 0.14 (0.67) | AAT | 0.15 (0.65) |
9 | CG | 0.24 (0.69) | CGA | 0.14 (0.67) | GAG | 0.15 (0.65) |
10 | FickScore | 0.23 (0.76) | CCG | 0.13 (0.67) | GGA | 0.14 (0.65) |
11 | CGA | 0.22 (0.68) | CGG | 0.13 (0.68) | KOZAK | 0.14 (0.67) |
12 | TCG | 0.21 (0.66) | ACA | 0.13 (0.63) | GGC | 0.13 (0.65) |
13 | CCG | 0.21 (0.67) | FickScore | 0.13 (0.73) | TCG | 0.13 (0.63) |
14 | TxLen | 0.19 (0.66) | TCG | 0.13 (0.65) | ATT | 0.13 (0.63) |
15 | KOZAK | 0.17 (0.65) | CGT | 0.12 (0.63) | CG | 0.13 (0.62) |
16 | CGT | 0.17 (0.62) | GC | 0.12 (0.65) | TTG | 0.13 (0.59) |
17 | ACA | 0.17 (0.60) | CAT | 0.12 (0.59) | TGG | 0.13 (0.64) |
18 | ACG | 0.17 (0.63) | ACG | 0.12 (0.64) | CGG | 0.13 (0.63) |
19 | ACT | 0.16 (0.60) | ACT | 0.12 (0.61) | CGA | 0.13 (0.62) |
20 | TCT | 0.16 (0.61) | GGC | 0.11 (0.64) | CCG | 0.12 (0.62) |
21 | TGG | 0.15 (0.61) | TxNex | 0.11 (0.73) | TT | 0.12 (0.61) |
22 | AAT | 0.15 (0.63) | KOZAK | 0.10 (0.65) | TA | 0.12 (0.62) |
23 | GTG | 0.15 (0.60) | CTA | 0.10 (0.59) | AG | 0.12 (0.60) |
24 | GG | 0.15 (0.62) | TxLen | 0.10 (0.64) | AT | 0.12 (0.62) |
25 | ATA | 0.15 (0.61) | AC | 0.09 (0.59) | CAG | 0.12 (0.58) |