EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Domain-Aware Feature Engineering for Prediction of Molecular Optical Interference in High-Throughput Screening

Filip Stefaniak iD

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c02217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Filip Stefaniak. Beteiligte Einrichtung: Laboratory of Bioinformatics and Protein Engineering, International Institute of Molecular and Cell Biology in Warsaw, Warsaw02-109, Poland. Hauptthemen laut MEDLINE: High-Throughput Screening Assays, Small Molecule Libraries, Optical Phenomena. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Fundacja na rzecz Nauki Polskiej, Narodowe Centrum Nauki.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optical interference from small molecules─compounds that absorb UV/visible light or exhibit intrinsic fluorescence─is a significant source of false positives and false negatives in fluorescence- and absorbance-based high-throughput screening assays. Computational prediction of optical activity from molecular structure offers a promising route to early triage of such compounds, yet the problem is challenging due to its quantum mechanical underpinnings and the extreme class imbalance characteristic of diverse drug-like libraries. Here I describe a domain-aware feature engineering and automated hyperparameter optimization approach developed for the EUOS25 Challenge, a benchmark comprising approximately 100,000 small organic compounds with experimentally measured UV/visible absorbance and fluorescence spectra. Beyond standard RDKit physicochemical descriptors and molecular fingerprints, I developed four domain-specific descriptor groups that encode prior chemical knowledge about chromophoric systems: count fingerprints of Murcko scaffolds derived from known dyes and fluorophores, binary indicators for manually curated chromophoric substructures, semiempirical quantum-mechanical descriptors from GFN2-xTB calculations, and ML-predicted quantum properties trained on the QM9 data set. Meta-learning features - probability outputs of baseline models trained on structurally related, easier-to-model end points - were included as cross-task inputs. Hyperparameter optimization was performed using the FLAML automated machine learning framework. The best model for each end point was selected from three complementary strategies: single best model, ensemble consensus, and semisupervised pseudolabeling. Postchallenge feature importance and ablation analyses showed that cross-task meta-features were the dominant driver of predictive accuracy for physically related end points. Semiempirical xTB descriptors─in particular─HOMO–LUMO gap and dipole/quadrupole terms - rank among the top-weighted CatBoost features and provide a physically interpretable account of model behavior. The dye-scaffold and chromophore-indicator descriptors, by contrast, carry genuine but redundant signal: used in isolation they classify well above chance for the two well-predicted end points, yet their removal from the full feature set produces no statistically significant change for any end point, indicating that the fingerprint/2D backbone already encodes this information. These results demonstrate that combining a standard cheminformatics backbone with cross-task meta-learning and automated hyperparameter optimization yields highly competitive predictive models on this benchmark.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

High-Throughput Screening AssaysSmall Molecule LibrariesOptical PhenomenaMachine LearningQuantum TheoryQuantum Mechanics

Substanzen

Small Molecule Libraries

Autor:innen und Institutionen

  • Laboratory of Bioinformatics and Protein Engineering, International Institute of Molecular and Cell Biology in Warsaw, Warsaw02-109, Poland.

ORCID-Profile: Filip Stefaniak

Förderung

  • Fundacja na rzecz Nauki Polskiej
  • Narodowe Centrum Nauki

Zitieren

APA

Stefaniak, F. (2026). Domain-Aware Feature Engineering for Prediction of Molecular Optical Interference in High-Throughput Screening. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02217

Vancouver

Stefaniak F. Domain-Aware Feature Engineering for Prediction of Molecular Optical Interference in High-Throughput Screening. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02217

BibTeX
@article{Stefaniak2026,
  author = {Stefaniak, Filip},
  title = {Domain-Aware Feature Engineering for Prediction of Molecular Optical Interference in High-Throughput Screening},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c02217}
}
Kostenlos starten →