EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PathMED: an R toolkit for single-sample molecular scoring and machine learning with omics data

Jordi Martorell-Marugán iD, Ivan Ellson, Raúl López-Domínguez iD, Pablo Pedro Jurado-Bascón, Juan Antonio Villatoro-García, Chang Wang, Frédéric Baribaud, Daniel Toro-Domínguez iD, Pedro Carmona-Sáez

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag519 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Jordi Martorell-Marugán und 8 weiteren Autor:innen. Beteiligte Einrichtung: Computational Neuroscience, Joint Unit in Biomedical Imaging and Artificial Intelligence FISABIO-CIPF, Foundation for the Promotion of Health and Bio…. Hauptthemen laut MEDLINE: Software, Machine Learning, Multiomics. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MICIU/AEI/10.13039/501100011033/FEDER, UE, FEDER/Junta de Andalucía-Consejería de Universidad.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Molecular scoring is a popular approach for studying pathway-level functional alterations with omics data. Using molecular scores for tasks such as single-sample molecular characterisation, phenotype prediction or disease stratification has several advantages compared to using omics data directly. Molecular scores provide biological interpretability and are more generalisable across datasets, facilitating data integration and machine learning applications. However, numerous scoring methods are available through different software packages, and currently there is a lack of tools to easily use these scores for model training and prediction. Results We developed pathMED, an R/Bioconductor package that unifies various scoring methods in a simple framework. Furthermore, pathMED also contains a machine learning module to train and test models that use the calculated molecular scores to predict clinical outcomes. We demonstrate some of its potential applications in three use cases using public omics data. We showed the generalisability of machine learning models trained on transcriptomic scores in predicting clinical outcomes when deploying on proteomic scores. We also demonstrated the application of transcriptomics scores in predicting breast cancer treatment response and identifying pathways strongly associated to tumour biology and treatment response. Finally, we demonstrated the benefit of integrating a novel gene set dissection step into the analysis pipeline to resolve disease heterogeneity at the pathway level. Availability PathMED is freely available in the Bioconductor repository (https://bioconductor.org/packages/release/bioc/html/pathMED.html). Code to reproduce the analyses is publicly available at https://github.com/GENyO-BioInformatics/pathMED_article.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareMachine LearningMultiomicsGenomicsHumansAdenocarcinoma of LungBreast NeoplasmsColitis, Ulcerative

Autor:innen und Institutionen

  • Computational Neuroscience, Joint Unit in Biomedical Imaging and Artificial Intelligence FISABIO-CIPF, Foundation for the Promotion of Health and Biomedical Research in the Valencian Region (FISABIO), Valencia 46012, Sp…
  • Bioinformatics and Health Data Science, GENYO, Centre for Genomics and Oncological Research: Pfizer, University of Granada, Andalusian Regional Government, PTS Granada, Granada 18016, Spain.
  • Fundación para la Investigación Biosanitaria de Andalucía Oriental-Alejandro Otero (FIBAO), Granada 18012, Spain.
  • Department of Statistics and Operational Research, University of Granada, Granada 18071, Spain.
  • Translational Early Program Lead, ICV Translational Early Development, Bristol Myers Squibb, Lawrence, NJ 08543, United States.
  • Department of Environmental Medicine, Karolinska Institutet, Unit of Inflammatory Diseases, Solna, Sweden.

ORCID-Profile: Jordi Martorell-Marugán, Raúl López-Domínguez, Daniel Toro-Domínguez

Förderung

  • MICIU/AEI/10.13039/501100011033/FEDER
  • UE
  • FEDER/Junta de Andalucía-Consejería de Universidad
  • Investigación e Innovación
  • MICIU/AEI/10.13039/501100011033
  • ESF

Zitieren

APA

Martorell-Marugán, J., Ellson, I., López-Domínguez, R., Jurado-Bascón, P. P., Villatoro-García, J. A., Wang, C., Baribaud, F., Toro-Domínguez, D., & Carmona-Sáez, P. (2026). PathMED: an R toolkit for single-sample molecular scoring and machine learning with omics data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag519

Vancouver

Martorell-Marugán J, Ellson I, López-Domínguez R, Jurado-Bascón PP, Villatoro-García JA, Wang C, et al. PathMED: an R toolkit for single-sample molecular scoring and machine learning with omics data. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag519

BibTeX
@article{MartorellMarugn2026,
  author = {Martorell-Marugán, Jordi and Ellson, Ivan and López-Domínguez, Raúl and Jurado-Bascón, Pablo Pedro and Villatoro-García, Juan Antonio and Wang, Chang and Baribaud, Frédéric and Toro-Domínguez, Daniel and Carmona-Sáez, Pedro},
  title = {PathMED: an R toolkit for single-sample molecular scoring and machine learning with omics data},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag519}
}
Kostenlos starten →