Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BYBioinformatics advances

Multi-omic spectral clustering with the flag mean.

  • Charlie M Carpenter1
  • Ziwei Tian1
  • Jonathan K Harris2
  • Michael Kirby3
  • Traci Lyons4
  • Christopher Peterson3
  • Brandie D Wagner1
  • Debashis Ghosh1
4 affiliations
  1. 1Department of Biostatistics and Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, United States.
  2. 2Department of Pediatrics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, United States.
  3. 3Department of Mathematics, Colorado State University, Fort Collins, CO 80523, United States.
  4. 4Division of Medical Oncology, Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, United States.
Read full textPDFDOICite

Abstract

Motivation

One common goal in multi-omics studies is to identify subgroups within the study's cohort. Many methods create subgroups through unsupervised clustering, and, to our knowledge, all of these methods attempt to infer a common subspace or latent cluster across multiple views. We argue that this is a strict assumption that may not truly exist in many datasets.Results

We use the classic spectral clustering algorithm in conjunction with the flag manifold. Together, this allows for differing cluster structures across the omics profiles, leading to a novel approach for more flexible subtyping in multi-omics studies. We study a dataset on ventilator associated pneumonia in children. These data contain airway microbiome and transcriptome. Through simulation studies, we demonstrate that the flag mean of separate clustering subspaces can accurately capture the span of a joint clustering space. It is also robust to varying noise structures and number of features across omics profiles. Our proposed method also outperforms popular multi-omics clustering methods in the presence of differing group sizes. This proposed method is general enough to apply to other multi-omics studies as well as any multi-view study that uses spectral clustering.Availability and implementation

Code for these methods are written in R and are freely available through GitHub at https://github.com/Ghoshlab/MMOC or through CRAN at https://cran.r-project.org/web/packages/MMOC/index.html.

Related

  1. Multi-Omic Profiling Defines the Renal Mechanisms of Cardiovascular-Kidney-Metabolic Syndrome in Pulmonary Arterial Hypertension
    M. Blake, S. Prins, J. B. Mendelson +7
    bioRxivPreprintAll rights reservedFull textMolecular biology & gene regulationbioRxiv
  2. Multi-Omic Integration of the miRNome and Transcriptome in Dermal Fibroblasts from Hypermobile Ehlers–Danlos Syndrome and Hypermobility Spectrum Disorders Identifies Convergent Candidate miRNA-mRNA Regulatory Networks Linking Extracellular Matrix Remodeling and Inflammation
    Iulia Andreea Pelisenco, Valeria Cinquina, Nicola Chiarelli +10
    International journal of molecular sciencesPeer-reviewedCC BYFull textGeneral biochemistryEurope PMC
  3. Population-scale single-nucleus multi-omic profiling of skeletal muscle reveals extensive context-specific genetic regulation
    Arushi Varshney, Nandini Manickam, Peter Orchard +33
    Nature GeneticsPeer-reviewedLicence not stated22 citedMolecular biology & gene regulationOpenAlex
  4. Single-cell multi-omic atlas and morphogen screening informs midbrain and hindbrain organoid engineering
    Nadezhda V. Azbukina, Zhisong He, Hsiu‐Chuan Lin +12
    Nature NeurosciencePeer-reviewedCC BY9 citedMolecular biology & gene regulationOpenAlex
  5. Multi-omic profiling reveals impaired luteal resolution and CHK2-regulated inflammation in ovarian aging
    L. Yang, Z. Sun, X. Luo +10
    bioRxivPreprintCC BY-NCFull textMolecular biology & gene regulationbioRxiv

Cite

BibTeXRIS
BibTeX
@article{carpenter2026multiomic,
  title = {{Multi-omic spectral clustering with the flag mean.}},
  author = {Charlie M Carpenter and Ziwei Tian and Jonathan K Harris and Michael Kirby and Traci Lyons and Christopher Peterson and Brandie D Wagner and Debashis Ghosh},
  journal = {Bioinformatics advances},
  year = {2026},
  month = aug,
  doi = {10.1093/bioadv/vbag217},
  url = {https://europepmc.org/article/MED/42921377},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Multi-omic spectral clustering with the flag mean.
AU  - Charlie M Carpenter
AU  - Ziwei Tian
AU  - Jonathan K Harris
AU  - Michael Kirby
AU  - Traci Lyons
AU  - Christopher Peterson
AU  - Brandie D Wagner
AU  - Debashis Ghosh
PY  - 2026
DA  - 2026/08/04
JO  - Bioinformatics advances
DO  - 10.1093/bioadv/vbag217
UR  - https://europepmc.org/article/MED/42921377
AB  - Motivation  One common goal in multi-omics studies is to identify subgroups within the study's cohort. Many methods create subgroups through unsupervised clustering, and, to our knowledge, all of these methods attempt to infer a common subspace or latent cluster across multiple views. We argue that this is a strict assumption that may not truly exist in many datasets.Results  We use the classic spectral clustering algorithm in conjunction with the flag manifold. Together, this allows for differing cluster structures across the omics profiles, leading to a novel approach for more flexible subtyping in multi-omics studies. We study a dataset on ventilator associated pneumonia in children. These data contain airway microbiome and transcriptome. Through simulation studies, we demonstrate that the flag mean of separate clustering subspaces can accurately capture the span of a joint clustering space. It is also robust to varying noise structures and number of features across omics profiles. Our proposed method also outperforms popular multi-omics clustering methods in the presence of differing group sizes. This proposed method is general enough to apply to other multi-omics studies as well as any multi-view study that uses spectral clustering.Availability and implementation  Code for these methods are written in R and are freely available through GitHub at https://github.com/Ghoshlab/MMOC or through CRAN at https://cran.r-project.org/web/packages/MMOC/index.html.
SN  - 2635-0041
ER  -