Skip to main content

Table 8 Mean AUPRC on the 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

0.537 ± 0.040

0.545 ± 0.088

0.581 ± 0.074

0.489 ± 0.070

Gemcitabine PDX

0.522 ± 0.087

0.455 ± 0.072

0.510 ± 0.132

0.483 ± 0.109

Cisplatin

0.954 ± 0.009

0.953 ± 0.022

0.942 ± 0.027

0.955 ± 0.012

Docetaxel

0.571 ± 0.028

0.644 ± 0.048

0.560 ± 0.051

0.568 ± 0.056

Erlotinib

0.400 ± 0.171

0.482 ± 0.251

0.440 ± 0.075

0.421 ± 0.126

Cetuximab

0.107 ± 0.012

0.188 ± 0.164

0.125 ± 0.018

0.102 ± 0.024

Paclitaxel

0.176 ± 0.094

0.127 ± 0.027

0.256 ± 0.147

0.121 ± 0.017

Rank

2.43

2.14

2.29

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