Fig. 1 | Nature Communications

Fig. 1

From: Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen

Fig. 1

Drug combinations and cell lines profiled. a Molecular characterization of the cell lines included genetics, epigenetics, and transcriptomics. b Participants were encouraged to mine external data and pathway resources. c Participants were provided the putative targets for all and chemical structures for ~\({\raise0.5ex\hbox{$\scriptstyle 1$}\kern-0.1em/\kern-0.15em \lower0.25ex\hbox{$\scriptstyle 3$}}\) of drugs (with this manuscript structures are now provided for all drugs). d The cell line panel contained 85 cell lines from six different cancer types, combination synergy scores capped within a range of −100 to 100. e The drug portfolio comprised approximately half oncogenic signaling targeting agents, and half cytotoxic drugs of which 14 were untargeted chemotherapies. f Drugs split by the putative targeted pathway. g Sparse data was split into training set, leaderboard, and independent test set for SC1 and SC2

Back to article page