AutomatedSeriesClassification update #RDKit #chemoinformatics

It was an honor for me that I could have an opportunity to present RDKit UGM 2020. My LT topic about Automated Chemical Series classification with pure RDKit. I uploaded my slide to UGM repo https://github.com/rdkit/UGM_2020/tree/master/LightningTalks.

After the UGM, I got great offer from @cthoyt. He proposed that this code convert to package which can be installed with pip. I was really happy to hear that. And after the great offer, he made PR to my repo and I merged it.

After some bug fix process, I confirmed that the code work well.

The URL is below.

https://github.com/iwatobipen/AutomatedSeriesClassification

To use the package, several packages should be installed. RDKit (of course ;)), Seaborn, pandas and xlrd. If reader uses conda, all packages are installed from conda-forge channel.

After installed them, you can install autmated_series_classification package with pip. Procedure is same as Readme.md.

git clone https://github.com/iwatobipen/AutomatedSeriesClassification
cd AutomatedSeriesClassification
pip install -e .

After installing the package, you can make dataset with following command.

$ python -m automated_series_classification.dataprep  # it'll take ~30 or more minutes on my PC

Then you can play with notebook DataPreprocessing-rdkit etc.

The code will work well but bottle neck of the approach is MCS search part I think. MCS search is NP hard problem.

So there is room for improvement at the part.

Anyway, I really thank to @cthoyt‘s great contribution and thank to @dr_greg_landrum.

And also I feel that I’m happy person because I can communicate not only many high skilled researcher in Japan but also foreign countries with chemoinformatics ;)

Any requests, comments and suggestion about the code will be highly appreciated.

Advertisement

Published by iwatobipen

I'm medicinal chemist in mid size of pharmaceutical company. I love chemoinfo, cording, organic synthesis, my family.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: