Skip to main content
zenodoopen

HITS Inc.'s models and data for Dacon challenge, Jump AI 2023

<p>Here deposits model&nbsp;and data files developed during HITS Inc.&#39;s participation in the Dacon challenge, Jump AI 2023:</p> <p><a href="https://dacon.io/competitions/official/236127/overview/description">https://dacon.io/competitions/official/236127/overview/description</a></p> <p>Note that the files here alone are less useful unless appropriate codes are employed.</p> <p><strong>File description:</strong></p> <ul> <li>pred_model_AutoGluon.tar.xz: AutoGluon model parameters for prediction.</li> <li>valid_model_AutoGluon.tar.xz: AutoGluon model parameters for validation.</li> <li>ckpts_original.tar.xz: fine-tuned <a href="https://github.com/yuyangw/MolCLR">MolCLR</a> model parameters.</li> <li>qc_out.tar.xz: molecular electronic structure files (.wfn).</li> <li>sdf_optimized.tar.xz: molecular structure files (.sdf).</li> <li>atomwfn.tar.xz: atomic electronic structure files (.wfn).</li> </ul>

ShareScore

44/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
8
Access
16
Reuse readiness
8
Engagement
4

Topics

ScienceDex for faculty

Your academic CV and NIH biosketch

Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.