François Bérenger

> Hi Francois, > > Yes, that sounds great. What format would those datasets be in? That would be a CSV file. I.e. I will take care of the encoding/vectorization...

I did play yesterday with auto-sklearn and pyCaret, both for regression. auto-sklearn gave an R2 near 0 (i.e. really did not work). pyCaret could reach R2 ~= 0.75; which is...

Hello, The dataset has been released: https://zenodo.org/record/4588239 Many protein with many molecules and their docking scores. The goal of the task is to predict ligand docking scores. The baseline model...

@adfindlater in the chemoinformatics literature, look for the keywords: "chemical fingerprint" or "molecular fingerprint" or even "molecular descriptors". Popular fingerprints these days are ECFP4 or ECFP6 (available in rdkit). For...

To find the best classification threshold automatically, you can try various thresholds for the predicted class probability, let's say from 0.01 to 1.00 (that's 100 values to try), then choose...

I know an RF implementation in OCaml, but it cannot do regression, so that's not completely OK: https://github.com/tobast/ORandForest

But, there should be one in ocaml-sklearn !!! Most of scipy, numpy and scikit-learn usable from OCaml: https://github.com/lehy/ocaml-sklearn

the most portable opam packages are the ones which vendor the code they rely on...

Thanks a lot for having implemented it!

Or, "can we constrain the obtained CG model to have one bead per input molecule heavy atom"?