You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Really cool paper! Great job finding a use-case within drug discovery which machine learning hasn't been integrated into at all.
I was wondering though whether you considered/tried using any of the additional chemical features for pharmacophore modeling provided by RDKit instead of just the three. I'm especially interested in "Pos Ionizable and Neg Ionizable' as a great deal of ligand-protein interactions are salt bridges between negative and positive charges. Is this something you tried and found it didn't help or just something you didn't explore?
The text was updated successfully, but these errors were encountered:
Hello Will,
Really cool paper! Great job finding a use-case within drug discovery which machine learning hasn't been integrated into at all.
I was wondering though whether you considered/tried using any of the additional chemical features for pharmacophore modeling provided by RDKit instead of just the three. I'm especially interested in "Pos Ionizable and Neg Ionizable' as a great deal of ligand-protein interactions are salt bridges between negative and positive charges. Is this something you tried and found it didn't help or just something you didn't explore?
The text was updated successfully, but these errors were encountered: