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.

SMILES notations LogP
C1CCCC(C)(C)1 1.98
... ...

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?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.