Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Predicting clinically promising therapeutic hypotheses using tensor factorization

Fig. 1

Data representation and model benchmark schematic. a Tensor representation of the dataset. The last “slice” matrix represents the clinical outcomes of target-indication pairs. b Illustration of three schemes of benchmarking models on predicting clinical outcomes. Each matrix represents the clinical outcomes of targets (rows) and indications (columns). Grey and green cells are target-indications pairs used for training and testing, respectively. Blank cells represent unknown clinical outcomes of target-indication pairs

Back to article page