Research Article
Joint Decision-Making Model Based on Consensus Modeling Technology for the Prediction of Drug-Induced Liver Injury
Table 5
Top 10 descriptors with a significant difference between DILI positives and DILI negatives.
| No. | Name | Description | VPM | VNM | DI |
| 1 | MATS3c | Moran autocorrelation—lag 3/weighted by charges | −3.72e-3 | 6.88e-3 | 52.32 | 2 | ALogP | Ghose–Crippen LogKow | 3.74e-3 | −0.435 | 2.77 | 3 | ATSC1p | Centered Broto–Moreau autocorrelation—lag 1/weighted by polarizabilities | −0.068 | 8.86e-3 | 1.94 | 4 | MATS2c | Moran autocorrelation—lag 2/weighted by charges | 0.021 | 6.62e-3 | 0.92 | 5 | MATS2i | Moran autocorrelation—lag 2/weighted by first ionization potential | 0.021 | 0.037 | 0.60 | 6 | MATS7s | Moran autocorrelation—lag 7/weighted by I-state | −0.035 | −0.06 | 0.56 | 7 | AATSC6v | Average centered Broto–Moreau autocorrelation—lag 6/weighted by van der Waals volumes | −0.954 | −1.474 | 0.45 | 8 | AATSC2v | Average centered Broto–Moreau autocorrelation—lag 2/weighted by van der Waals volumes | 1.262 | 1.900 | 0.43 | 9 | ATSC4i | Average centered Broto–Moreau autocorrelation—lag 4/weighted by first ionization potential | −9.774 | −13.831 | 0.36 | 10 | AATSC1p | Average centered Broto–Moreau autocorrelation—lag 1/weighted by polarizabilities | −2.00e-3 | −1.51e-3 | 0.32 |
|
|