Computed Descriptors of the Compounds Dataset (PubChem + ChEMBL) for training DrLungker
收藏Figshare2025-12-02 更新2026-04-08 收录
下载链接：
https://figshare.com/articles/dataset/_i_DrLungker_A_Deep_Ensemble_Learning_Framework_for_Predicting_Anti-Lung_Cancer_Compound_Activity_and_Validating_Multitarget_Potency_through_WaterMap_DFT_MD_Simulations_and_MM-GBSA_Analysis_i_/30763082/2
下载链接
链接失效反馈官方服务：
资源简介：
<b>Project Description</b><b>Published in:</b> <i>Advanced Theory and Simulations</i><br><b>Manuscript DOI:</b> https://doi.org/10.1002/adts.202501550<br><b>More Information:</b> https://github.com/ShabanAhmad/DrLungker<br>This (DrLungker_Dataset.csv) contains the complete curated dataset used to train the DrLungker deep ensemble predictor.<br>Data were sourced from PubChem and ChEMBL lung cancer bioassays and underwent structure standardisation, duplicate removal, descriptor generation (AlvaDesc + QikProp), and quality filtering.<br>The final dataset includes <b>26,396 unique compounds</b>, each represented by <b>5,883 molecular descriptors</b>, and was used to train the hybrid ResNet–FNN–LSTM ensemble using Averaging, Voting, and Stacking techniques.
提供机构：
Raza, Khalid; Ahmad, Shaban
创建时间：
2025-12-02
