Highly curated Nav1.5 dataset of 1723 unique molecular compounds with corresponding potency values

<p>This dataset was built during a research project, in the field of Computer-Aided Drug Discovery (CADD),&nbsp;funded by&nbsp;the Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery grant. The aim of the project was to build descriptor-based machine learning models for Nav1.5 cardiotoxicity liability predictions. The dataset includes a total of 1723&nbsp;unique molecular compounds gathered from&nbsp;ChEMBL and PubChem publicly available bioactivity databases. The list&nbsp;is split into 2 sets, 1550 for training and 173 for testing. All molecular compounds are represented in their SMILE format with their corresponding&nbsp;PIC50 potency values.</p> <p>To access the full original&nbsp;work, please visit the following link:&nbsp;&nbsp;<a href="https://arxiv.org/abs/2112.13467">Manuscript</a>&nbsp;<br><strong>Refer to a much larger and latest&nbsp;dataset here: <a href="../record/8359714">link</a>&nbsp;</strong></p> <p><br><strong>Note:</strong> Upon usage of this data, kindly cite both the dataset and the original manuscript&nbsp;describing the curation process as written&nbsp;below.<br><br><em>Arab I, Barakat K. ToxTree: Descriptor-based machine learning models for both hERG and Nav1. 5 cardiotoxicity liability predictions. arXiv preprint arXiv:2112.13467. 2021</em></p> <p><em>Arab, Issar, &amp; Barakat, Khaled. (2021). Highly curated Nav1.5 dataset of 1723 unique molecular compounds with corresponding potency values [Data set]. Zenodo. https://doi.org/10.5281/zenodo.5807731</em></p>