Data, Scripts, and Models Necessary to Reproduce the EGAT Paper

Full Data, Scripts, and Models Necessary to Reproduce the EGAT Paper. Figshare only has ensemble models, splits, and DFT runs for the main paper. Please unpack the tarballs to run them. Hyperparameter Tuning is set in a separate zenodo repository cited in the Data and Code Availability Section in the ChemArXiv paper [https://chemrxiv.org/engage/chemrxiv/article-details/65410dc248dad23120c6e954], due to file size limits. 

Data Splits: EGAT_Splits.tar.gz

Ensemble Models and Respective Analysis: RGD-ensemble.tar.gz

Dataset Size Models: RGD-datasetsize.tar.gz

Training EGAT on subsets of data: b2f2.tar.gz,b3f3.tar.gz,R1P1.tar.gz,R2P2.tar.gz,R2P1.tar.gz

Jupyter notebooks on obtaining all results: AdditionalJupyter.tar.gz

All Chemprop Models: Chemprop.tar.gz.

IRC runs for Training and Testing set: IRC_best_worst.tar.gz

Conformational Sampling Results: CS.tar.gz