SynProtX: A Large-Scale Proteomics-Based Deep Learning Model for Predicting Synergistic Anticancer Drug Combinations

SynProtX: A Large-Scale Proteomics-Based Deep Learning Model for Predicting Synergistic Anticancer Drug Combinations SynProtX is a deep learning model that integrates large-scale proteomics data, molecular graphs, and chemical fingerprints to predict synergistic effects of anticancer drug combinations. It provides robust performance across tissue-specific and study-specific datasets, enhancing reproducibility and biological relevance in drug synergy prediction. This Zenodo repository includes a .tar.gz archive containing all essential components to reproduce the experiments described in the study. This archive is designed to work seamlessly with the coding pipeline available at: https://github.com/manbaritone/SynProtX. License: Creative Commons Zero v1.0 Universal (CC0)This work is released under CC0, dedicating it to the public domain. You are free to use, modify, and distribute it without restriction. Archive Contents: This compressed file includes: Datasets- Tissue Datasets: ALMANAC-Breast, ALMANAC-Lung, ALMANAC-Ovary, ALMANAC-Skin- Study Datasets: FRIEDMAN, ONEIL Supporting Files- Raw and preprocessed data- Feature dictionaries- Hyperparameter configurations- Trained model weights Folder Structure: SynProtX/├── data/ # Raw and preprocessed data│ ├── export/ # Processed protein/gene expression & drug combinations│ ├── nps/ # Numpy arrays for all datasets│ ├── nps_intersected/ # Dataset-specific numpy arrays│ └── raw/ # Original data from DrugComb, CCLE, COSMIC, ChEMBL V31, ProCan-DepMapSanger├── feature_dicts/ # Feature dictionaries for drug combinations├── hyperparams/ # Hyperparameter configs for SynProtX-GATFP│ ├── classification/ # For classification tasks│ └── regression/ # For regression tasks├── state_dict/ # Trained model weights│ ├── classification/ # PyTorch checkpoints for classification│ └── regression/ # PyTorch checkpoints for regression└── README_Zenodo.md # This file For more information, please visit: GitHub: https://github.com/manbaritone/SynProtX