De novo molecule design towards biased properties via a deep generative framework and iterative transfer learning
Kianoosh Sattari, Dawei Li, Bhupalee Kalita, Yunchao Xie, Fatemeh Barmaleki Lighvan, Olexandr Isayev, Jian Lin · Digital Discovery · 2024
The RRCGAN, validated through DFT, demonstrates success in generating chemically valid molecules targeting energy gap values with 75% of the generated molecules have RE of <20% of the targeted values.