Faster O(n) SMILES tokenizer

topazape / LSTM_Chem

Implementation of the paper - Generative Recurrent Networks for De Novo Drug Design.

The Unlicense

116 stars 55 forks source link

Faster O(n) SMILES tokenizer #5

Closed mjuchem closed 4 years ago

mjuchem commented 4 years ago

Improved SMILES tokenizer, runs O(n).

TaghizadehE commented 4 years ago

Hi,

line 36 in smiles_tekenizer2 (forked one), shouldn't be i=i+2 to make it even faster?

topazape commented 4 years ago

Thanks for the great PR! I'm currently testing @mjuchem's and @ehsanOSU's code. It seems to be about 10 times faster than my code. It will be merged into the MASTER branch soon.