Classification with Missing Data─A NIFty Pipeline for Single-Cell Proteomics
Journal of Proteome Research · 20.11.2026
DOI: 10.1021/acs.jproteome.6c00354 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Proteome Research, online erschienen am 20.11.2026. Verfasst von Alyssa A. Nitz und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of General Medical Sciences, College of Life Sciences, Brigham Young University, Simmons Center for Cancer Research, Brigham Young University.
Abstract (Originalsprache)
Single-cell proteomics (SCP) is uniquely suited for cell-type characterization, trajectory-based inference, and microenvironment mapping. Evaluating biological hypotheses in these experiments requires labeled cells. Without a premeasurement label, machine learning is used to identify features that characterize the cell types and classify unlabeled samples. Current implementations of annotation methods come with several statistical and computational disadvantages. First, machine-learning methods require complete data, leading to large amounts of missing-value imputation in SCP. Additionally, some machine-learning methods select features and classify samples via cross-sample comparisons, nullifying downstream cross-sample comparisons, like differential expression, through double dipping. Finally, measurements from different proteomic experiments are not directly comparable due to batch effects, significantly limiting the accuracy of classifiers trained on external data. Here we present NIFty, a top-scoring pairs based feature selection method, implemented in a full classification pipeline, that does not require preimputed data as input or employ circular analysis techniques, and overcomes batch effects without batch correction. When tested on imputed vs unimputed data, data with large batch effects, and multiclass data, NIFty successfully overcame the targeted classification challenges and comparably, or more accurately, classified the samples in the varied data sets.
Förderung
- National Institute of General Medical Sciences
- College of Life Sciences, Brigham Young University
- Simmons Center for Cancer Research, Brigham Young University
Zitieren
APA
Nitz, A. A., McGee, B., Echarry, B., Estoque, N. B., & Payne, S. H. (2026). Classification with Missing Data─A NIFty Pipeline for Single-Cell Proteomics. Journal of Proteome Research. https://doi.org/10.1021/acs.jproteome.6c00354
Vancouver
Nitz AA, McGee B, Echarry B, Estoque NB, Payne SH. Classification with Missing Data─A NIFty Pipeline for Single-Cell Proteomics. Journal of Proteome Research. 2026. doi:10.1021/acs.jproteome.6c00354
BibTeX
@article{Nitz2026,
author = {Nitz, Alyssa A. and McGee, Blake and Echarry, Benjamin and Estoque, Nathan B. and Payne, Samuel H.},
title = {Classification with Missing Data─A NIFty Pipeline for Single-Cell Proteomics},
journal = {Journal of Proteome Research},
year = {2026},
doi = {10.1021/acs.jproteome.6c00354}
}
EUVIMED