. Author manuscript; available in PMC: 2024 Jul 6.

Published before final editing as: J Chem Theory Comput. 2023 Jan 6:10.1021/acs.jctc.2c01024. doi: 10.1021/acs.jctc.2c01024

Table 2.

The test performance on the Frag20-solv-678k dataset. sPhysNet-MT-ens5 is a deep ensemble of five sPhysNet-MT models. The errors are reported in kcal/mol.

Model	Metric	Target
Model	Metric	$E_{g a s}$	$E_{w a t e r}$	$E_{o c t}$	$Δ E_{g a s \to w a t e r}$	$Δ E_{g a s \to o c t}$	$Δ E_{o c t \to w a t e r}$
On the test set of Frag20-solv-678k

sPhysNet-MT	MAE	0.719	0.691	0.695	0.205	0.161	0.086
sPhysNet-MT	RMSE	1.143	1.074	1.087	0.377	0.300	0.139

sPhysNet-MT-ens5	MAE	0.599	0.571	0.573	0.187	0.145	0.079
sPhysNet-MT-ens5	RMSE	0.993	0.932	0.943	0.357	0.283	0.131