Loading
A model that claims to have learned biology should, without being told, point at the known mechanism of a known drug or the known marker of a known cell type; recovering such known biology is an orthogonal check that a correlation is not an artefact.
A drug's mechanism of action is the specific biochemical interaction through which it produces its effect, usually naming its molecular target (Wikipedia). For a drug-response or perturbation model, ranking the MEK pathway genes first for a MEK inhibitor, or HER2 and its amplicon for trastuzumab, is a probe that costs nothing and catches models that learned tissue or batch instead. The same logic underlies tertiary lymphoid structures as a probe for spatial models and responder-versus-non-responder framing as the application that matters.
Shares Ablation study and multi-task heads, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Tertiary lymphoid structures (TLS), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Ablation study and multi-task heads, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Virtual cell models and in-silico perturbation screens, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Cancer AI vocabulary (CanSim terms map), RAS / RAF / MEK / ERK (MAPK) and the tag cansim-terms.
Shares Cancer AI vocabulary (CanSim terms map), RAS / RAF / MEK / ERK (MAPK) and the tag cansim-terms.
Shares Cancer AI vocabulary (CanSim terms map), RAS / RAF / MEK / ERK (MAPK) and the tag cansim-terms.
Shares Virtual cell models and in-silico perturbation screens, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.