Saved in:
Bibliographic Details
Main Author: Sneha Sil
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.17553385
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>Source code is attached in this release if you would like to edit the code to suit your particular cheminformatics pipeline. Functions can be commented out/adjusted in functions.py, classes.py is where the graph elements are constructed as dictionaries, and graph.py is where it all comes together.</p> <p>The datasets_regression_tar_files.zip folder contains:</p> <ul> <li>.csv files for all of the regression-type datasets used in our study</li> <li>.tar files containing Cartesian coordinates/Shermo output/JANPA output/NBO output files for each molecule in each dataset (which can be unpacked and loaded into a database using graphpancake)</li> </ul> <p>The datasets_classification_tar_files.zip folder contains:</p> <ul> <li>.csv files for all of the classification-type datasets used in our study</li> <li>.tar files containing Cartesian coordinates/Shermo output/JANPA output/NBO output files for each molecule in each dataset (which can be unpacked and loaded into a database using graphpancake)</li> </ul> <p>The datasets_db_files.zip folder contains:</p> <ul> <li>.db files corresponding to aforementioned unpacking/loading with graphpancake for all (classification and regression) datasets used in our study</li> </ul> <p>The ML_scripts.zip folder contains:</p> <ul> <li>csvs: our datasets, with data and labels</li> <li>data_files: .db files</li> <li>scripts: our machine learning (RF, message passing neural networks) scripts</li> </ul> <p>Note: this is a re-release to receive a DOI from Zenodo.</p>