Combined dropout for tuples (s, V). Takes tuples (s, V) as input and as output.

Graph convolution / message passing with Geometric Vector Perceptrons. Takes in a graph with node and edge embeddings, and returns new no

Combined LayerNorm for tuples (s, V). Takes tuples (s, V) as input and as output.

Protein structure representation.

Vector channel dropout where the elements of each vector channel are dropped together.

Geometric Vector Perceptron. See manuscript and README.md for more details. :param in_dims: tuple (n_scalar, n_vector) :param ou

Full graph convolution / message passing layer with Geometric Vector Perceptrons. Residually updates node embeddings with aggregated inc

Modified based on https://github.com/drorlab/gvp-pytorch/blob/main/gvp/models.py GVP-GNN for Model Quality Assessment as described in manuscr