Fig. 3From: Multi-objective de novo drug design with conditional graph generative modelThe two type of graph generative architectures explored in this work: a MolMP: this architecture treats graph generation as a Markov process, in which the transition of \(G_i\) only depends on the current state of the graph, not on the history. b MolRNN: this architecture adds a single molecule level recurrent unit to MolMPBack to article page