A comparison between 2D and 3D descriptors in QSAR modeling based on bio-active conformations

Malkeet Singh Bahia, Omer Kaspi, Meir Touitou, Idan Binayev, Seema Dhail, Jacob Spiegel, Netaly Khazanov, Abraham Yosipof, Hanoch Senderowitz

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


QSAR models are widely and successfully used in many research areas. The success of such models highly depends on molecular descriptors typically classified as 1D, 2D, 3D, or 4D. While 3D information is likely important, e. g., for modeling ligand-protein binding, previous comparisons between the performances of 2D and 3D descriptors were inconclusive. Yet in such comparisons the modeled ligands were not necessarily represented by their bioactive conformations. With this in mind, we mined the PDB for sets of protein-ligand complexes sharing the same protein for which uniform activity data were reported. The results, totaling 461 structures spread across six series were compiled into a carefully curated, first of its kind dataset in which each ligand is represented by its bioactive conformation. Next, each set was characterized by 2D, 3D and 2D + 3D descriptors and modeled using three machine learning algorithms, namely, k-Nearest Neighbors, Random Forest and Lasso Regression. Models’ performances were evaluated on external test sets derived from the parent datasets either randomly or in a rational manner. We found that many more significant models were obtained when combining 2D and 3D descriptors. We attribute these improvements to the ability of 2D and 3D descriptors to code for different, yet complementary molecular properties.

Original languageEnglish
Article number2200186
JournalMolecular Informatics
Issue number4
Early online date8 Jan 2023
StatePublished - Apr 2023

Bibliographical note

Publisher Copyright:
© 2023 The Authors. Electroanalysis published by Wiley-VCH Verlag GmbH.


The authors are grateful to the Planning and Budgeting Committee (PBC) of the Council for Higher Education in Israel for providing postdoctoral fellowship to Dr. Malkeet Singh Bahia at Bar‐Ilan University (BIU), Ramat Gan, Israel. The authors are also thankful to the developers of Mendeley for providing academically free version of the program.

FundersFunder number
Council for Higher Education


    • 2D vs. 3D descriptors comparison
    • 2D-descriptors
    • 3D-descriptors
    • bioactive conformations
    • machine learning


    Dive into the research topics of 'A comparison between 2D and 3D descriptors in QSAR modeling based on bio-active conformations'. Together they form a unique fingerprint.

    Cite this