Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ALNSynergy: a graph convolutional network with multi-representation alignment for drug synergy prediction

Xinxing Yang, Jiachen Li, Xiao Kang, Guojin Pei, Keyu Liu, Genke Yang, Jian Chu

TL;DR

In the ALNSynergy model, a graph convolutional network with multi-representation alignment function suitable for the drug synergy prediction task so that the positional relationship between drug representations and cell line representation is reflected in the embedding space.

Abstract

Drug combination refers to the use of two or more drugs to treat a specific disease at the same time. It is currently the mainstream way to treat complex diseases. Compared with single drugs, drug combinations have better efficacy and can better inhibit toxicity and drug resistance. The computational model based on deep learning concatenates the representation of multiple drugs and the corresponding cell line feature as input, and the output is whether the drug combination can have an inhibitory effect on the cell line. However, this strategy of concatenating multiple representations has the following defects: the alignment of drug representation and cell line representation is ignored, resulting in the synergistic relationship not being reflected positionally in the embedding space. Moreover, the alignment measurement function in deep learning cannot be suitable for drug synergy prediction tasks due to differences in input types. Therefore, in this work, we propose ALNSynergy, a graph convolutional network with multi-representation alignment for predicting drug synergy. In the ALNSynergy model, we designed a multi-representation alignment function suitable for the drug synergy prediction task so that the positional relationship between drug representations and cell line representation is reflected in the embedding space. In addition, the vector modulus of drug representations and cell line representation is considered to improve the accuracy of calculation results and accelerate model convergence. Finally, many relevant experiments were run on multiple drug synergy datasets to verify the effectiveness of the above innovative elements and the excellence of the ALNSynergy model.

ALNSynergy: a graph convolutional network with multi-representation alignment for drug synergy prediction

TL;DR

In the ALNSynergy model, a graph convolutional network with multi-representation alignment function suitable for the drug synergy prediction task so that the positional relationship between drug representations and cell line representation is reflected in the embedding space.

Abstract

Drug combination refers to the use of two or more drugs to treat a specific disease at the same time. It is currently the mainstream way to treat complex diseases. Compared with single drugs, drug combinations have better efficacy and can better inhibit toxicity and drug resistance. The computational model based on deep learning concatenates the representation of multiple drugs and the corresponding cell line feature as input, and the output is whether the drug combination can have an inhibitory effect on the cell line. However, this strategy of concatenating multiple representations has the following defects: the alignment of drug representation and cell line representation is ignored, resulting in the synergistic relationship not being reflected positionally in the embedding space. Moreover, the alignment measurement function in deep learning cannot be suitable for drug synergy prediction tasks due to differences in input types. Therefore, in this work, we propose ALNSynergy, a graph convolutional network with multi-representation alignment for predicting drug synergy. In the ALNSynergy model, we designed a multi-representation alignment function suitable for the drug synergy prediction task so that the positional relationship between drug representations and cell line representation is reflected in the embedding space. In addition, the vector modulus of drug representations and cell line representation is considered to improve the accuracy of calculation results and accelerate model convergence. Finally, many relevant experiments were run on multiple drug synergy datasets to verify the effectiveness of the above innovative elements and the excellence of the ALNSynergy model.
Paper Structure (15 sections, 9 equations, 5 figures, 6 tables)

This paper contains 15 sections, 9 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Drug representation learning module
  4. Cell line representation learning module
  5. Prediction module
  6. Multi-representation alignment function
  7. Multi-representation alignment function with adaptive module length
  8. Experiments and Discussion
  9. Datasets
  10. Experimental settings and evaluation metrics
  11. Hyperparameter settings
  12. Effectiveness of multi-representation alignment function
  13. Effectiveness of multi-representation alignment function with adaptive module length
  14. Comparison experiment
  15. Conclusion

Figures (5)

  • Figure 1: The architecture of the ALNSynergy model
  • Figure 2: Example of alignment function in two-dimensional space when temperature coefficient is 1
  • Figure 3: The changing trend and improvement percentage of the ALNSynergy model under different $\alpha$ values
  • Figure 4: The changing trend and improvement percentage of the ALNSynergy-NA model, ALNSynergy-NM model and ALNSynergy-WM model
  • Figure 5: The convergence speed of ALNSynergy-WM model, ALNSynergy-NM model and ALNSynergy-NA model