PACMOS: an R package for Projection And Classification of Multi-Omic Samples
Abstract
Motivation Integrated multi-omic analyses have transformed our understanding of cancer biology, giving rise to data-driven molecular classifications that capture disease heterogeneity beyond conventional histopathology. Among these approaches, multi-omic factor analysis (MOFA), a multimodal extension of principal component analysis, has been widely used to identify sources of molecular variation across omic layers and classify samples into molecular groups. However, classifying query samples according to an existing MOFA-based classification remains challenging, as there is no validated computational method for projecting samples into pretrained MOFA latent factor spaces. Results We present PACMOS, an R package that provides a generalizable approach to project query samples into pretrained MOFA latent factor spaces. We validate PACMOS using two cancer datasets with published MOFA-based classifications—lung neuroendocrine neoplasms and pleural mesothelioma—showing that PACMOS preserves the existing MOFA latent factor space while allowing query samples to be classified. Availability and implementation PACMOS is an open-source R package available at https://github.com/IARCbioinfo/PACMOS and archived on Zenodo at https://doi.org/10.5281/zenodo.20933824 , along with installation instructions and a vignette. Supplementary information Supplementary data are available in separate files. Key messages PACMOS enables the projection of query cancer samples into pretrained multi-omic latent factor spaces. The package supports both continuous and discrete classifications. PACMOS provides a reproducible, per-sample workflow implemented in an R package. PACMOS demonstrates robust performance on pleural mesothelioma and lung neuroendocrine tumor datasets.
Related
- Soybean paste functional peptides: Fermentation-driven formation, characterization, classification, structure-activity relationships, and multi-omics insights.
- CMGL: confidence-guided multi-omics graph learning for cancer subtype classification
- GONet: A Molecular Interaction-Guided Graph Learning Framework for Multi-Omics Cancer Classification
- LGH-Transformer: A Hybrid CNN–Transformer Model for Multi-Class Bladder Tissue Classification from Cystoscopic Images
- miR2Meth: An R package for dissecting DNA methylation heterogeneity at microRNA promoters.
BibTeX
@misc{kalson2026pacmos,
title = {{PACMOS: an R package for Projection And Classification of Multi-Omic Samples}},
author = {Lipika Kalson and Alexandra Sexton-Oates and Gabrielle Drevet and Lynnette Fernandez-Cuesta and Matthieu Foll and Nicolas Alcala},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.64898/2026.07.01.735542},
url = {https://hal.science/hal-05842972v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - PACMOS: an R package for Projection And Classification of Multi-Omic Samples
AU - Lipika Kalson
AU - Alexandra Sexton-Oates
AU - Gabrielle Drevet
AU - Lynnette Fernandez-Cuesta
AU - Matthieu Foll
AU - Nicolas Alcala
PY - 2026
DA - 2026/10/28
PB - HAL
DO - 10.64898/2026.07.01.735542
UR - https://hal.science/hal-05842972v1
AB - Motivation Integrated multi-omic analyses have transformed our understanding of cancer biology, giving rise to data-driven molecular classifications that capture disease heterogeneity beyond conventional histopathology. Among these approaches, multi-omic factor analysis (MOFA), a multimodal extension of principal component analysis, has been widely used to identify sources of molecular variation across omic layers and classify samples into molecular groups. However, classifying query samples according to an existing MOFA-based classification remains challenging, as there is no validated computational method for projecting samples into pretrained MOFA latent factor spaces. Results We present PACMOS, an R package that provides a generalizable approach to project query samples into pretrained MOFA latent factor spaces. We validate PACMOS using two cancer datasets with published MOFA-based classifications—lung neuroendocrine neoplasms and pleural mesothelioma—showing that PACMOS preserves the existing MOFA latent factor space while allowing query samples to be classified. Availability and implementation PACMOS is an open-source R package available at https://github.com/IARCbioinfo/PACMOS and archived on Zenodo at https://doi.org/10.5281/zenodo.20933824 , along with installation instructions and a vignette. Supplementary information Supplementary data are available in separate files. Key messages PACMOS enables the projection of query cancer samples into pretrained multi-omic latent factor spaces. The package supports both continuous and discrete classifications. PACMOS provides a reproducible, per-sample workflow implemented in an R package. PACMOS demonstrates robust performance on pleural mesothelioma and lung neuroendocrine tumor datasets.
ER -