Skip to main content

Table 7 Mean AUROC on external test set for the ablation study

From: A fair experimental comparison of neural network architectures for latent representations of multi-omics for drug response prediction

Drug

Omics stacking

Complete integration

Without integration

Integration

Without triplet loss

Gemcitabine TCGA

0.646 ± 0.048

0.641 ± 0.056

0.655 ± 0.029

0.624 ± 0.068

Gemcitabine PDX

0.656 ± 0.049

0.630 ± 0.066

0.714 ± 0.089

0.665 ± 0.078

Cisplatin

0.668 ± 0.046

0.685 ± 0.078

0.644 ± 0.087

0.680 ± 0.063

Docetaxel

0.613 ± 0.058

0.597 ± 0.046

0.584 ± 0.101

0.600 ± 0.090

Erlotinib

0.704 ± 0.141

0.715 ± 0.193

0.744 ± 0.065

0.741 ± 0.077

Cetuximab

0.529 ± 0.052

0.599 ± 0.173

0.575 ± 0.049

0.466 ± 0.122

Paclitaxel

0.511 ± 0.106

0.432 ± 0.087

0.619 ± 0.152

0.419 ± 0.082

Rank

2.57

2.57

2.00

2.86

  1. Best results are shown in bold and second best are italic. The values represent the means and standard deviations over five iterations
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us