Table 1 Distribution of different data sets and it compounds (mutagens and non-mutagens) in test and train sets
From: In-silico predictive mutagenicity model generation using supervised learning approaches
Data sets | Training | Training | Test mutagen | Test non | Minority % |
|---|---|---|---|---|---|
Mutagen | Non mutagen | Mutagen | |||
Set 1 | 1916 | 1554 | 485 | 382 | 55.38 |
Set 2 | 2803 | 2407 | 700 | 602 | 53.79 |
Set 3 | 3639 | 2871 | 910 | 788 | 55.40 |