Based on the popular Moomins series of children's books, Snufkin: Melody of Moominvalley might be the gentlest game about anarchy and ecoterrorism ever made. You play as the titular Snufkin, a free-spirited, harmonica-playing nomad and friend to the doughy, innocent Moomins. Upon venturing back to the Moomins' village to visit his best friend, the earnest and eager Moomintroll, he finds that the once-beautiful valley has been ravaged by the Park Keeper, a dopey bureaucrat who has caged animals, sectioned off private parks and generally tried to tame the wild into something tidier and more civilized. That, of course, will not do. So you take it upon yourself to undermine the Park Keeper's efforts, putting out the fires he and his fellow cops have caused (sometimes literally) and letting nature be nature again.

We propose the molecular omics network (MOOMIN) a multimodal graph neural network that can predict the synergistic effect of drug combinations for cancer treatment. Our model captures the representation based on the context of drugs at multiple scales based on a drug-protein interaction network and metadata. Structural properties of the compounds and proteins are encoded to create vertex features for a message-passing scheme that operates on the bipartite interaction graph. Propagated messages form multi-resolution drug representations which we utilized to create drug pair descriptors. By conditioning the drug combination representations on the cancer cell type we define a synergy scoring function that can inductively score unseen pairs of drugs. Experimental results on the synergy scoring task demonstrate that MOOMIN outperforms state-of-the-art graph fingerprinting, proximity preserving node embedding, and existing deep learning approaches. Further results establish that the predictive performance of our model is robust to hyperparameter changes. We demonstrate that the model makes high-quality predictions over a wide range of cancer cell line tissues, out-of-sample predictions can be validated with external synergy databases, and that the proposed model is data-efficient at learning.