I need a dumb encoder: mol -> (MolW,cLogP,TPSA,RotB,HBA,HBD,FC)

[UnixJunkie]

I have one somewhere else. Mini dragon or I don't know what funny name.

[UnixJunkie]

copy the script from here https://github.com/UnixJunkie/chemo_lizard

[UnixJunkie]

The TranNguyen-Rognan filter:

# Step 1: Organic compound filter. Molecules bearing at
least one atom other than H, C, N, O, P, S, F, Cl, Br, and I
were removed.
# Step 3: Molecular property range filter. Remaining
actives and inactives were kept if
• 150 < Molecular weight < 800 Da
• −3.0 < AlogP < 5.0
• Number of rotatable bonds < 15
• H-bond acceptor count < 10
• H-bond donor count < 10
• −2.0 < total formal charge < + 2.0

From

Tran-Nguyen, V. K., Jacquemard, C., & Rognan, D. (2020). LIT-PCBA: An Unbiased Data Set for Machine Learning and Virtual Screening. Journal of Chemical Information and Modeling.

[UnixJunkie]

So, with option: --remove-aliens :)

[UnixJunkie]

done: bin/molenc_lizard.py

[UnixJunkie]

should be OK; except the original AlogP range for which I asked a question (the paper uses AlogP computed with pipeline pilot; while I have cLogP computed by rdkit)