chemicalx
chemicalx copied to clipboard
How are the methods implemented outside of the domain they are designed for?
For example, DeepSynergy
and MatchMaker
are requiring cell line information, and they are both implemented in the DrugBankDDI & TWOSIDES benchmarks where no cell line information is available at all (and TWOSIDES is even at the patient level), with DS reaching the highest performance among all methods. What then was the "cell line gene expression" component in both methods replaced within those tasks? Also, does this ensure a fair comparison?
I also noticed that all drug features
are set to be Morgan FP by design. However, a lot of those models rely on specific features, e.g. SSI-DDI
, CASTER
both explicitly leverage substructure features. I am not so sure why features are all unified anyways...?