Table 3 Performance comparison for different deep learning models on Dataset3.
From: Hybrid framework for membrane protein type prediction based on the PSSM
Types | Methods | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Capnet | OCNN | ICNN | ||||||||||
Pre | Se | F-m | Mcc | Pre | Se | F-m | Mcc | Pre | Se | F-m | Mcc | |
Single-span type I | 0.86 | 0.86 | 0.86 | 0.84 | 0.92 | 0.87 | 0.89 | 0.88 | 0.94 | 0.91 | 0.92 | 0.92 |
Single-span type II | 0.57 | 0.72 | 0.64 | 0.63 | 0.52 | 0.82 | 0.64 | 0.65 | 0.51 | 0.97 | 0.67 | 0.70 |
Single-span type III | 0.08 | 0.17 | 0.11 | 0.11 | 0.40 | 0.33 | 0.36 | 0.36 | 0.30 | 0.50 | 0.37 | 0.39 |
Single-span type IV | 1.00 | 0.50 | 0.67 | 0.70 | 1.00 | 0.80 | 0.89 | 0.89 | 0.56 | 0.90 | 0.69 | 0.71 |
Multi-span type | 0.99 | 0.93 | 0.96 | 0.85 | 0.98 | 0.94 | 0.96 | 0.88 | 0.99 | 0.94 | 0.96 | 0.88 |
Lipid-chain-anchored | 0.41 | 0.42 | 0.42 | 0.41 | 0.64 | 0.54 | 0.58 | 0.58 | 0.64 | 0.54 | 0.58 | 0.58 |
GPI-anchored | 0.68 | 0.71 | 0.69 | 0.69 | 0.74 | 0.83 | 0.78 | 0.78 | 0.71 | 0.92 | 0.80 | 0.80 |
Peripheral | 0.68 | 0.90 | 0.78 | 0.75 | 0.75 | 0.90 | 0.81 | 0.79 | 0.80 | 0.90 | 0.85 | 0.82 |
Average | 0.66 | 0.65 | 0.64 | 0.62 | 0.74 | 0.75 | 0.74 | 0.73 | 0.68 | 0.82 | 0.73 | 0.73 |
Weighted average | 0.92 | 0.90 | 0.91 | 0.83 | 0.93 | 0.92 | 0.92 | 0.86 | 0.94 | 0.93 | 0.93 | 0.87 |
