On Modelability and Generalizability: Are Machine Learning Models for Drug Synergy Exploiting Artefacts and Biases in Available Data?

Synergy models are useful tools for exploring drug combinatorial search space and identifying promising sub-spaces for in vitro/vivo experiments. Here, we report that distributional biases in the training-validation-test sets used for predictive modeling of drug synergy can explain much of the variability observed in model performances (up to $0.22$ $\Delta$AUPRC). We built 145 classification models spanning 4,577 unique drugs and 75,276 pair-wise drug combinations extracted from DrugComb, and examined spurious correlations in both the input feature and output label spaces. We posit that some synergy datasets are easier to model than others due to factors such as synergy spread, class separation, chemical structural diversity, physicochemical diversity, combinatorial tests per drug, and combinatorial label entropy. We simulate distribution shifts for these dataset attributes and report that the drug-wise homogeneity of combinatorial labels most influences modelability ($0.16\pm0.06$ $\Delta$AUPRC). Our findings imply that seemingly high-performing drug synergy models may not generalize well to broader medicinal space. We caution that the synergy modeling community's efforts may be better expended in examining data-specific artefacts and biases rigorously prior to model building.