CMMS-GCL: Cross-Modality Metabolic Stability Prediction with Graph Contrastive Learning

Requirements

• Python == 3.8
• PyTorch == 2.0
• scikit-learn == 1.2.2
• pandas == 2.0.2
• numpy == 1.23.5
• RDKit == 2023.03.1
• network == 2.8.4
• PyG == 2.3.1
• Install pytorch_geometric following instruction at https://github.com/rusty1s/pytorch_geometric

Dataset

The HLM dataset and External dataset were adopted from [1].

Acknowledgements

Part of the code was adopted and revised from [2],[3] and [4].

References

[1] Li, L. et al. (2022). In Silico Prediction of Human and Rat Liver Microsomal Stability via Machine Learning Methods. Chemical Research in Toxicology 35(9), 1614–1624.

[2] Nguyen, T., et al.(2021). GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics 37(8), 1140-1147.

[3] Mastropietro, A.et al. (2022). EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks. Iscience, 25(10), 105043.

[4] You, Y., et al. (2020). Graph contrastive learning with augmentations. Advances in neural information processing systems 33, 5812–5823.