EUVIMEDEUVIMED entdecken
Crossref

Systematic Multi-Target QSAR Benchmarking: Machine Learning Algorithms, Molecular Descriptors, and Validation

Salah A Alshehade iD, Ghazi Al Jabal, Iqbal H Jebril

Journal of Chemical Information and Modeling · 10.08.2026 · 66 (15) · 8923-8941

DOI: 10.1021/acs.jcim.6c01237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 16.06.2026. Verfasst von Salah A Alshehade und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacology, Faculty of Pharmacy, Universiti Sultan Zainal Abidin, 22200Besut, Terengganu, Malaysia. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Machine Learning, Drug Discovery. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantitative structure–activity relationship (QSAR) modeling underpins computational drug discovery, yet the factors governing model generalizability across structurally novel compounds, and across protein families, remain incompletely understood. This study addresses that gap through systematic 2D-QSAR benchmarking across four therapeutically diverse ChEMBL targets, EGFR (kinase, n = 10, 036), DRD2 (GPCR, n = 7, 558), BACE-1 (protease, n = 8, 080), and hERG (ion channel, n = 8, 077), totaling 33,751 compounds under identical experimental conditions. Three principal findings emerge. First, scaffold-based splitting revealed target-dependent generalization gaps varying 2-fold across targets (mean gap: 0.084–0.171 R2 units across five random seeds), demonstrating that the interpolation-to-extrapolation performance penalty is a data set property, not an algorithmic limitation. Second, applicability domain (AD) analysis confirmed substantial prediction quality degradation outside the Tanimoto-based chemical domain (0.31–0.51 R2 drop), with hERG showing near-total loss of predictive power for structurally distant compounds (R2: 0.62 → 0.11). Third, algorithm rankings were remarkably consistent across all four protein families (mean Spearman ρ = 0.92), with tree-based ensemble methods, particularly Random Forest, on ECFP4 fingerprints providing the most consistent performance (scaffold-split R2: 0.40–0.59). A basic 3-layer graph convolutional network (without edge features or pretraining) underperformed RF + ECFP4 on every target (mean deficit: −0.22 R2). These results establish reproducible prospective baselines and demonstrate that AD reporting is an essential, not optional, component of QSAR model evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipMachine LearningDrug DiscoveryBenchmarkingAmyloid Precursor Protein SecretasesAspartic Acid EndopeptidasesHumansReceptors, Dopamine D2AlgorithmsEther-A-Go-Go Potassium Channels

Substanzen

Amyloid Precursor Protein SecretasesAspartic Acid EndopeptidasesReceptors, Dopamine D2Ether-A-Go-Go Potassium ChannelsBACE1 protein, human

Autor:innen und Institutionen

  • Department of Pharmacology, Faculty of Pharmacy, Universiti Sultan Zainal Abidin, 22200Besut, Terengganu, Malaysia.
  • Department of Pharmaceutical Chemistry, Faculty of Pharmacy and Biomedical Sciences, MAHSA University, Bandar Saujana Putra, 42610Jenjarom, Selangor, Malaysia.
  • Faculty of Pharmacy, Yarmouk Private University, Jbab, Daraa00000, Syria.
  • Department of Mathematics, Al-Zaytoonah University of Jordan, Amman11733, Jordan.

ORCID-Profile: Salah A Alshehade

Zitieren

APA

Alshehade, S. A., Al Jabal, G., & Jebril, I. H. (2026). Systematic Multi-Target QSAR Benchmarking: Machine Learning Algorithms, Molecular Descriptors, and Validation. Journal of Chemical Information and Modeling, 66(15), 8923-8941. https://doi.org/10.1021/acs.jcim.6c01237

Vancouver

Alshehade SA, Al Jabal G, Jebril IH. Systematic Multi-Target QSAR Benchmarking: Machine Learning Algorithms, Molecular Descriptors, and Validation. Journal of Chemical Information and Modeling. 2026;66(15):8923-8941. doi:10.1021/acs.jcim.6c01237

BibTeX
@article{Alshehade2026,
  author = {Alshehade, Salah A and Al Jabal, Ghazi and Jebril, Iqbal H},
  title = {Systematic Multi-Target QSAR Benchmarking: Machine Learning Algorithms, Molecular Descriptors, and Validation},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {15},
  pages = {8923--8941},
  doi = {10.1021/acs.jcim.6c01237}
}
Kostenlos starten →