Recap

This is just a recap message so that we are on the same page.

I am working on a similarity prediction script that I should finish this week. You will see that it is quite a complex script that involves several steps. If you want, I can show it to you tomorrow and we can plan how to organize this in the pipeline.
I see that the pubchem scripts are running on the cluster. Good news.
If I am not mistaken, the steps that remain are: "similarity prediction", "projections", "scores" and "libraries".