Skip to main content

Table 6 Mean AUPRC on test sets from cross-validation 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

0.143 ± 0.053

0.136 ± 0.054

0.161 ± 0.053

0.149 ± 0.074

Gemcitabine PDX

0.138 ± 0.046

0.204 ± 0.092

0.151 ± 0.085

0.119 ± 0.046

Cisplatin

0.288 ± 0.072

0.293 ± 0.074

0.293 ± 0.089

0.277 ± 0.084

Docetaxel

0.317 ± 0.064

0.262 ± 0.072

0.316 ± 0.083

0.358 ± 0.046

Erlotinib

0.422 ± 0.704

0.440 ± 0.149

0.479 ± 0.153

0.352 ± 0.111

Cetuximab

0.379 ± 0.102

0.264 ± 0.042

0.376 ± 0.104

0.350 ± 0.049

Paclitaxel

0.186 ± 0.076

0.188 ± 0.103

0.220 ± 0.108

0.090 ± 0.024

Rank

2.57

2.57

1.71

3.14

  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