Dear academic, biotech & drug discovery twitter colleagues, I need your help!
I'm collecting a list of benchmarks & evaluation datasets for protein-small molecule affinity and virtual screening capacity (e.g. published hit discovery campaign results), which ones do you recommend?
11
11
76
Replies
Tagging a few people from whom I would love to have their opinion
@david_koes
@olexandr
@CGorgulla
@akshat_ai
@jchodera
@alshedivat
🙏
0
0
2
@GabriCorso
openff protein-ligand benchmark has a pretty diverse set of targets (although # of ligands per target is small): . another one that comes to mind is merck fep, but you already mentioned it.
1
1
3
@alshedivat
Thanks Maruan! I actually was not aware of this one! Let me know if similar ones come to mind!
0
0
0
@GabriCorso
If you need solved structures:
PDB Bind:
DUDE:
If you don't care about having the structure:
1
0
2
@_judewells
Yeah though from my experience these (without particular filterings) are all of somewhat bad quality and not very representative of what is actually useful in research/industry
0
0
2
And connected to it, what is the right way of fairly evaluating methods on these (of course after blind prospective studies)? E.g. ensuring test proteins/pockets/ligands are never seen during training...
2
0
1
@GabriCorso
Long story short. It depends on what you want to prove and achieve. Why not posebuster?
1
0
0
@GM_Randazzo
Posebusters is only structural as far as I know, mostly interested in affinity here!
1
0
0
@clemensisert
Thank you, yes this is very interesting (although I guess performance for a single target might be somewhat biased)!
0
0
1
@GabriCorso
BindingDB protein-ligand validation sets. Old but contains lots of docked congeneric series data and some crystals.
1
1
0
@GabriCorso
I've trıed a dataset with Molecular Mechanic features derived from a subset of the PDBBind database. However, I would advise examining some of these features more closely.
Paper:
Dataset:
1
0
0
@GabriCorso
Hey there, just matching keywords here (I know almost nothing of the field), but could this be of some interest for you?
It's from a few colleagues of mine, let me know if it may be relevant
0
0
0
@GabriCorso
I recommend getting in touch with
@cas_wognum
, he is at the center of a bio/pharma consortium for better benchmarks
0
0
5