DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach

Table 1 Atom and bond features used in the present work

Indices	Atom description
0–100	Atomic number (1 to 100)
101–107	Degree (1 to 5)
108–113	Formal charge (− 2 to + 2)
114–118	Chiral tag (0 to 4)
119–124	Number of hydrogens (0 to 4)
125–130	Hybridization (SP, SP2, SP3, SP3D, SP3D2)
131	Aromatic atom
132	Atomic mass * 0.01

Indices	Bond description
133	Bond present
134–136	Bond type (single, double, triple)
137	Aromatic bond
138	Conjugated bond
139	Bond present in ring
140–146	Bond stereo code (RdKit)

ISSN: 1758-2946