EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Feature Down-Selection to Improve Supervised Classification by Machine Learning on Mass Spectrometry Imaging Data

Braysen Miller iD, Aleesa E Chua iD, Madeline Isom, Eden P Go, Emily R Sekera iD, Amanda B Hummon, Heather Desaire iD

Molecules · 13.06.2026 · 31 (12) · 2077

DOI: 10.3390/molecules31122077 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecules, online erschienen am 13.06.2026. Verfasst von Braysen Miller und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, University of Kansas, 1450 Jayhawk Blvd, Lawrence, KS 66045, USA. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NIH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advancements made in the mass spectrometry imaging (MSI) field have allowed for the generation of very large-scale data sets. These data are often interrogated by machine learning (ML), although storing and handling data sets of this size can be difficult. To aid impacted researchers, we seek to evaluate feature reduction strategies that will minimize the amount of data stored while still maintaining the ability to correctly classify the data. Two different feature selection strategies are tested on six different data sets, leveraging XGBoost as the machine learning algorithm. The study provides evidence that selecting features based on the greatest average abundance across all samples is best suited to scale down the feature set at a more modest trimming level, while selecting features based on statistical analysis via a Student’s t-test is better suited for a more aggressive trimming level. These trends were present regardless of training set size or cross-validation strategy. The results from this work provide insight into when these feature filtering steps can be used effectively and when another data reduction strategy, including not restricting the data set, should be considered.

Schlagwörter

Stichwörter der Autor:innen

data analysisfeature selectionlipidsmachine learningmass spectrometrymass spectrometry imagingspheroids

Autor:innen und Institutionen

  • Department of Chemistry, University of Kansas, 1450 Jayhawk Blvd, Lawrence, KS 66045, USA.
  • Department of Chemistry and Biochemistry, The Ohio State University, 281 W Lane Ave, Columbus, OH 43210, USA.

ORCID-Profile: Braysen Miller, Aleesa E Chua, Emily R Sekera, Heather Desaire

Förderung

  • NIH HHS
  • NIH

Zitieren

APA

Miller, B., Chua, A. E., Isom, M., Go, E. P., Sekera, E. R., Hummon, A. B., & Desaire, H. (2026). Feature Down-Selection to Improve Supervised Classification by Machine Learning on Mass Spectrometry Imaging Data. Molecules, 31(12), 2077. https://doi.org/10.3390/molecules31122077

Vancouver

Miller B, Chua AE, Isom M, Go EP, Sekera ER, Hummon AB, et al. Feature Down-Selection to Improve Supervised Classification by Machine Learning on Mass Spectrometry Imaging Data. Molecules. 2026;31(12):2077. doi:10.3390/molecules31122077

BibTeX
@article{Miller2026,
  author = {Miller, Braysen and Chua, Aleesa E and Isom, Madeline and Go, Eden P and Sekera, Emily R and Hummon, Amanda B and Desaire, Heather},
  title = {Feature Down-Selection to Improve Supervised Classification by Machine Learning on Mass Spectrometry Imaging Data},
  journal = {Molecules},
  year = {2026},
  volume = {31},
  number = {12},
  pages = {2077},
  doi = {10.3390/molecules31122077}
}
Kostenlos starten →