Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: Bayesian inference for identifying tumour-specific cancer dependencies through integration of ex-vivo drug response assays and drug-protein profiling

Fig. 4

Feature Selection Comparison: Sets of kinases reported in Batzilla et al. [3] and the ones selected by our proposed model under the hyperparameters \(\nu ^*\) that lead to the minimal normalized MSE. We highlight the kinases that appear in more than one of the reported subsets. Top: Selected kinases in the GDSC1 dataset. Compared with DepInfeR, the proposed models also suggest that CCNK and DYRK1A are informative to the sensitivity measure. Mid: Selected kinases in the EMBL dataset. The proposed models also suggest that CDK16, CDK6, EIF3J, GSKIP, PDXK, PTK2B and TAOK2 are also informative. Bottom: Selected kinases in the EMBL dataset. he proposed models also suggest that ACAD11 and STK26 are informative

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us