What are the features of nodes (x) and "edge_attr" in ESOL dataset standing for?

[scu-ljy]

Can anybody explain what the numbers in feature vectors stand for? Or if there is a reference of how these feature vectors are generated will be better.

An example of a graph in ESOL dataset is below. I understand that the first number i stands for the ith element in periodic table, yet I cannot figure out what other columns stands for.

data[1].x

tensor([[6, 0, 4, 5, 3, 0, 4, 0, 0],
        [6, 0, 3, 5, 0, 0, 3, 1, 1],
        [8, 0, 2, 5, 0, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 0, 0, 3, 1, 1],
        [6, 0, 3, 5, 0, 0, 3, 0, 0],
        [8, 0, 1, 5, 0, 0, 3, 0, 0],
        [7, 0, 3, 5, 1, 0, 3, 0, 0],
        [6, 0, 3, 5, 0, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1],
        [6, 0, 3, 5, 1, 0, 3, 1, 1]])

Here is the respective edge_attr of data[1], I completely have no idea what these vectors stand for.

data[1].edge_attr
tensor([[1, 0, 0],
        [1, 0, 0],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [1, 0, 1],
        [1, 0, 1],
        [2, 0, 1],
        [1, 0, 1],
        [2, 0, 1],
        [1, 0, 1],
        [1, 0, 1],
        [1, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1],
        [4, 0, 1]])

[EdisonLeeeee]

Hi @scu-ljy you may refer to this paper for more information: Open Graph Benchmark: Datasets for Machine Learning on Graphs

Here I quote the introduction to the dataset from this paper:

Each graph represents a molecule, where nodes are atoms, and edges are chemical bonds. Input node features are 9-dimensional, containing atomic number and chirality, as well as other additional atom features such as formal charge and whether the atom is in the ring. Input edge features are 3-dimensional, containing bond type, bond stereochemistry as well as an additional bond feature indicating whether the bond is conjugated.

[scu-ljy]

Thanks, it really helps!