Skip to main content
. Author manuscript; available in PMC: 2021 Dec 30.
Published in final edited form as: J Phys Chem A. 2020 Oct 21;124(44):9194–9202. doi: 10.1021/acs.jpca.0c06231

Figure 2.

Figure 2.

The accuracy of TLQC is stable with respect to the choice of quantum chemical descriptors used during pretraining. Each data point represents transfer learning from one of 20 subsets of the 15 calculated quantum chemical descriptors. For four of the five targets, most TLQC models performed better than TOP (dashed line). The accuracy on most targets is not correlated with the number of quantum chemical descriptors used for transfer learning, suggesting a robust quantum chemical representation can be built even from one molecule-level quantum chemical descriptor.