Data sets inquiry

[goznxn]

I read your recent paper “Deep learning enables rapid identification of potent DDR1 kinase inhibitors” at Nature Biotechnology. It is a really pioneering application of state-of-the-art AI approaches in real drug discovery process. I download your GENTRL codes from the github. The GENTRL model is implemented with an example trained on a MOSES dataset. but I cannot find the six datasets used in the article in the github. If the whole data sets are not publicly accessible, are there any possibility to get a subset of example data set so that we can execute the provided codes and learn the process. Thanks!