I want to build a deep learning model that can predict a continuous value (LogP in this case) given text inputs (SMILES notations in this case), the dataset is as illustrated below.
I have never tackled text data, I mostly worked with numbers-based datasets (or images).
My questions are:
- What is the best model for this case? I believe RNN based architectures, such as LSTM and GRU, are the most suitable.
- What about recent architectures such as Transformers?
- How can/should I convert (or embed, or encode) the text inputs (SMILES) to feed them to my model?