De-novo Chemical Reaction Generation by Means of Temporal Convolutional Neural Networks
This work addresses chemical reaction generation for computational chemistry, representing an incremental improvement through hybrid methods.
The authors tackled chemical reaction generation by combining Recurrent Neural Networks (RNN) and Temporal Convolutional Neural Networks (TCN) with a novel Reaction Smiles-like representation (CGRSmiles). They achieved better performance than RNN alone and demonstrated that fine-tuning protocols significantly impact generative scope via transfer learning.
We present here a combination of two networks, Recurrent Neural Networks (RNN) and Temporarily Convolutional Neural Networks (TCN) in de novo reaction generation using the novel Reaction Smiles-like representation of reactions (CGRSmiles) with atom mapping directly incorporated. Recurrent Neural Networks are known for their autoregressive properties and are frequently used in language modelling with direct application to SMILES generation. The relatively novel TCNs possess similar properties with wide receptive field while obeying the causality required for natural language processing (NLP). The combination of both latent representations expressed through TCN and RNN results in an overall better performance compared to RNN alone. Additionally, it is shown that different fine-tuning protocols have a profound impact on generative scope of the model when applied on a dataset of interest via transfer learning.