For instance, compound B1, the least selective ligand in the panel, was predicted to be active for only nine out of the 31 kinases for which activity was found.
False positives are compounds that are predicted to be active, but are not.
The human genome encodes almost 90 DUBs of which 79 are predicted to be active.
f p and f n values represent the number of molecules incorrectly predicted to be active and inactive respectively.
For these a threshold can be selected, above which a molecule is predicted to be active against the target.
The numbers of compounds containing a certain descriptor d, predicted to be active n act d and inactive n inact d, were calculated for each descriptor.
In one of our studies the objective of the Agent is to generate molecules that are predicted to be active against a biological target.
where n act and n inact are total number of compounds, predicted to be active or, respectively, inactive, by the model at issue.
Subsequently, ten compounds from an external library (HitFinder) predicted to be active on two of the enriched targets, P-glycoprotein 1 and Topoisomerase I, were tested in vitro.
Apart from generating a higher fraction of structures that are predicted to be active, both Agents also generate a significantly higher fraction of valid SMILES (Table 4).
Finally, when tuning the model towards generating compounds predicted to be active against the dopamine receptor type 2, the model generates structures of which more than 95% are predicted to be active, including experimentally confirmed actives that have not been included in either the generative model nor the activity prediction model.
