Skip to main content
. 2022 Apr 21;62(10):2301–2315. doi: 10.1021/acs.jcim.1c01510

Figure 3.

Figure 3

Overall network architecture of the proposed 3D-CNN and PCN. The input for the networks is 3D atomic structures with their features (3D pose representation). The PCN uses the input data directly, whereas the 3D-CNN uses their voxelized data. The optional interaction features are concatenated with one of the fully connected layer activations.