You can visit the LinDing Group
to view more scientific achievements.
The benchmark dataset was used to build the model. You can download it for free.
Datasets Download |
||
| Training Datasets | Description | Download |
| K | It contains 266 carbonylated and 1802 non-carbonylated sequences respectively. | |
| P | It contains 114 carbonylated and 716 non-carbonylated sequences respectively. | |
| R | It contains 119 carbonylated and 754 non-carbonylated sequences respectively. | |
| T | It contains 116 carbonylated and 702 non-carbonylated sequences respectively. | |
| Testing Datasets | Description | Download |
| K | It contains 34 carbonylated and 147 non-carbonylated sequences respectively. | |
| P | It contains 12 carbonylated and 76 non-carbonylated sequences respectively. | |
| R | It contains 17 carbonylated and 93 non-carbonylated sequences respectively. | |
| T | It contains 5 carbonylated and 30 non-carbonylated sequences respectively. | |
Other Download |
||
| Description | Download | |
| Original values of nine physicochemical properties and molecular weight of the corresponding amino acid. | ||
| A software package for local computers to predict carbonylation sites. | ||