Systematic Data Analysis and Diagnostic Machine Learning Reveal Differences between Compounds with Single- and Multitarget Activity

Christian Feldmann, Dimitar Yonchev, Dagmar Stumpfe, Jürgen BajorathZenodo 2020 · DOI · OpenAlex

Abstract

The deposited files contain balanced data sets of multi-target (MT) and single-target (ST) compounds (CPDs) used for machine learning studies (https://dx.doi.org/10.1021/acs.molpharmaceut.0c00901). The first file (st_mt_data.tsv) contains 15,142 MT- and 15,081 ST-CPDs and the second (st_dt_data.tsv) 1828 DT- and 1776 ST-CPDs. For each CPD, a nonstereo_aromatic_SMILES representation, the original ChEMBL_cid, UniProt (target) IDs, and CPD category (CPD_CAT) (i.e. DT/MT/ST) is provided. DT stands for 'diverse-target' and denotes a subset of MT-CPDs (as detailed in the publication). In addition, a CPD is tagged “Y” if it continued to be present in the data set after removal of 50% randomly selected CPDs or 50% CPD nearest neighbors (NN), respectively.
BibTeX
@inproceedings{feldmann2020systematic,
  author = {Christian Feldmann and Dimitar Yonchev and Dagmar Stumpfe and Jürgen Bajorath and Christian Wolfgang Feldmann},
  title = {{Systematic Data Analysis and Diagnostic Machine Learning Reveal Differences between Compounds with Single- and Multitarget Activity}},
  booktitle = {Zenodo},
  year = {2020},
  doi = {10.5281/zenodo.4190987},
}

Loading related content...

Figure