Since its first release in 2011, canSAR (1–4) continues to be the largest, public, cancer drug discovery resource, used by academia and industry (5) from over 300 countries worldwide. canSAR was originally created to inform target selection for cancer drug discovery. To achieve this goal, we developed canSAR to be a scalable, adaptable and fully integrative knowledgebase. It integrates data from multi-omic profiling of cancer tissue from patients and cancer cell lines, together with data on genetic vulnerabilities and dependencies. These data are fully integrated with vast medicinal chemistry and pharmacology data, annotation of the entire human proteome, protein 3D structure, protein-protein-interactions, drug approvals and clinical trials among other data. The full integration (rather than simple collation) of data means that non-obvious connections can be identified, helping discovery of novel targets and insights for cancer drug discovery and therapy (6–9). We have developed a suite of machine-learning algorithms to learn from these vast integrated data to provide the world's most comprehensive, rapidly updated target druggability/ligandability assessment. These methods assess target feasibility for drug discovery based on 3D structure, known chemistry, behaviour in protein interaction networks, and availability to antibody/biotherapeutics.
