Fig 1.
The architecture of TranSynergy.
The input features include vector representations of Drug A, Drug B, and cell line vector, respectively. The first input dimension reduction component reduces the input dimension from 2401x3 to 512x3. The second component is a scaled dot product self-attention transformer. The third component is a fully connected neural network. Be noted that input matrix dimension changes to 2401x4 when both gene expression and gene dependency profiles are used for cell line representation.
Fig 2.
Illustration of genome-wide drug-target profile.
Observed drug target profile is processed with RWR to infer drug effects on both targets and non-target proteins.
Fig 3.
Illustration of three training/test dataset splitting scenarios.
Each data point is composed of two drugs and a cell line. The data samples in white and red are the training/validation dataset and test dataset, respectively. A) Leave drug combination out scenario. In this example, drug pairs, including drug1+drug2 and drug3+drug4, are colored red and held out as test dataset. B) Leave cell line out scenario. In this example, the cell line 2 is colored red and held out as test dataset. C) Leave drug out scenario. In this example, the drug 3 and all drug pairs including the drug 3 are colored red and held out as test dataset.
Table 1.
Performance comparison of TranSynergy and DeepSynergy models in regression scenarios.
Table 2.
Performance comparison of TranSynergy with different cell line features to DeepSynergy model in classification scenarios.
Fig 4.
Tissue-specific and cell line-specific prediction performances of TranSynergy and DeepSynergy.
The top two panels (A and B) are tissue-specific performance with Pearson correlation and Spearman correlation as the metrics. The bottom two panels (C and D) are cell line-specific performance with Pearson correlation and Spearman correlation as the metrics.
Fig 5.
Visualization of different cell lines with t-SNE analysis.
High dimensional cell line vector representations are projected into 2-D space with the first two t-SNE components. A) Different colors indicate assigned clusters of each cell line by the affinity propagation method. B) Different colors indicate different tissues of each cell line.
Table 3.
Performance of TranSynergy and DeepSyenrgy on leave cell out scenario and leave drug out scenario for the regression task.
Table 4.
Performance of TranSynergy and DeepSyenrgy on leave cell out scenario and leave drug out scenario for the classification task.
Fig 6.
Visualization of drug features with t-SNE analysis.
High dimensional ECFP representations are projected into 2D space with the first two t-SNE components. Different colors indicate assigned clusters of each drug by affinity propagation method.
Table 5.
Ablation study of TranSynergy models.
Table 6.
The most important oncogenic signatures revealed by SA-GSEA.
Table 7.
Examples of predicted synergistic novel drug pairs.