Skip to main content
. 2024 Jul 1;64(14):5492–5499. doi: 10.1021/acs.jcim.4c00485

Table 6. Model Ablationsa.

Ablation Pearson’s r
Base model (FS-CAP) 0.32 ± 0.01
No query encoding 0.30 ± 0.01
Concatenated context 0.28 ± 0.00
No context 0.17 ± 0.03
a

Mean correlation between ground-truth and predicted activities across all test targets in BindingDB using 8 context compounds. We report the mean ± one standard deviation from three independent training runs with random seeds.