MolGPT: Molecular Generation Using a Transformer-Decoder Model

• Published in: Journal of chemical information and modeling Vol. 62; no. 9; pp. 2064 - 2076
• Main Authors: Bagal, Viraj, Aggarwal, Rishal, Vinod, P. K., Priyakumar, U. Deva
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 09.05.2022
• Subjects: Deep learning; Drug Design; Machine Learning; Natural language processing; Property values; Scaffolds; Strings; Transformers

Application of deep learning techniques for generation of molecules, termed as inverse molecular design, has been gaining enormous traction in drug design. The representation of molecules in SMILES notation as a string of characters enables the usage of state of the art models in natural language pr...