Modelling data and model results Tox21

<p>The data sets accompany the manuscript&nbsp;</p> <ul> <li><a href="https://doi.org/10.1101/2023.11.15.567095" target="_blank" rel="noopener">10.1101/2023.11.15.567095</a></li> </ul> <p>The data sets rely on previous work from&nbsp;</p> <p>M. Lovrić, "Razvoj i primjena modela za procjenu ekotoksikolo&scaron;kih rizika bioaktivnih kemijskih spojeva", Disertacija, Sveučili&scaron;te u Zagrebu, Prirodoslovno-matematički fakultet, Zagreb, 2021. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:217:730117</p> <p>and</p> <p>Lovrić M, Malev O, Klobučar G, Kern R, Liu JJ, Lučić B. Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem. Molecules. 2021 Mar 15;26(6):1617. doi: 10.3390/molecules26061617</p> <p>the original data was downloaded from the Tox21 challenge https://tripod.nih.gov/tox21/challenge/data.jsp&nbsp;</p> <p>The files comprise of:</p> <ol> <li>tox21_desc_p194.csv&nbsp; &nbsp;- descriptor data for the prepared Tox21 data set</li> <li>tox21_fp_all.csv - fingerprint and maccs data for the prepared Tox21 data set</li> <li>tox21_target_all.csv - 12 binary Tox21 target(labels)&nbsp;</li> <li>standardizer_pipeline.xml - structure standardizer pipeline for ChemAxon Standardizer&nbsp;</li> <li>tox21_models_metadata.json - model metadata such as sklearn hyperparameters and descriptor feature lists</li> </ol> <p>&nbsp;</p> <p>&nbsp;</p>