For de novo drug design, we successfully applied generative recurrent neural networks (RNN) containing long short-term memory (LSTM) cells (Merk et al., 2018). The model considers the SMILES strings for molecular representation and learns the patterns and their probabilities from pretraining for use in generation of the SMILES structures. We fine-tuned the generated structures (SMILES) for specific molecular targets or chemical series by employing transfer learning. The generative LSTM approach has proven helpful in low-data drug discovery, hit expansion, molecular design (fragment-based), and lead optimization (Gupta et al., 2018; Segler et al., 2018; Erikawa et al., 2021).
Neural Networks A Classroom Approach By Satish Kumar Pdf Free 11
Download: https://gohhs.com/2vGxtd
2ff7e9595c
Comentários