DeepSynBa: Actionable Drug Combination Prediction with Complete Dose-Response Profiles

MotivationMany cancer monotherapies demonstrate limited clinical efficacy, making combination therapies a relevant treatment strategy. The extensive number of potential drug combinations and context-specific response profiles complicates the prediction of drug combination responses. Existing computational models are typically trained to predict a single aggregated synergy score, which summarises drug responses across different dosage combinations, such as Bliss or Loewe scores. This oversimplification of the drug-response surface leads to high prediction uncertainty and limited actionability because these models fail to differentiate between potency and efficacy. ResultsWe introduce DeepSynBa, an actionable model that predicts the complete dose-response matrix of drug pairs instead of relying on an aggregated synergy score. This is achieved by predicting parameters describing the response surface as an intermediate layer in the model. We evaluated DeepSynBa on the NCI-ALMANAC dataset, which comprises nearly 300,000 drug pair-cell line combinations. DeepSynBa outperforms the state-of-the-art methods in the dose-response matrix prediction task across multiple evaluation scenarios, including testing on novel drug combinations, cell lines, and drugs, across nine different tissue types. We also show that DeepSynBa yields reliable synergy score predictions. More importantly, DeepSynBa can predict drug combination responses across different dosages for untested combinations. The intermediate dose-response parameter layer allows for separating efficacy from potency, which informs the selection of dosage ranges that optimise efficacy while limiting off-target toxicity in experimental screens. The predictive capability and the downstream actionability make DeepSynBa a powerful tool for advancing drug combination research beyond the limitations of the current approaches. AvailabilityThe code and the dataset for DeepSynBa are available at https://github.com/hikuru/DeepSynBa. Contactmarta.milo@astrazeneca.com or otastan@sabanciuniv.edu