Skip to content
DraconiticResearch
Search Sources API
186,123 studies31 sourcesUpdated 9 min ago
Peer-reviewedCC BY 4.0Cell Reports Methods

SwitchClass distinguishes baseline- and perturbation-aligned features across intermediate molecular states

  • Di Xiao1,2
  • Siqu Long1
  • Pengyi Yang1,2,3,4
4 affiliations
  1. 1Computational Systems Biology Unit, Children’s Medical Research Institute, Faculty of Medicine and Health, The University of Sydney, Westmead, NSW 2145, Australia
  2. 2Sydney Precision Data Science Centre, The University of Sydney, Sydney, NSW 2006, Australia
  3. 3School of Mathematics and Statistics, Faculty of Science, The University of Sydney, Sydney, NSW 2006, Australia
  4. 4Charles Perkins Centre, The University of Sydney, Sydney, NSW 2006, Australia
Read full textDOICite

Abstract

Biological systems often exhibit intermediate molecular states under perturbation, showing changes that align with baseline condition or perturbed state. Capturing these complex patterns is critical for understanding molecular resilience and maladaptive persistence. We introduce SwitchClass, a label-switch classification framework that distinguishes features whose intermediate-state profiles align with baseline or perturbed condition. By training a dual classifier with inverted labels, SwitchClass computes a directional importance score (δ), which quantifies each feature’s alignment across biological states. Applied to colorectal cancer proteomics, SwitchClass reveals proteins that normalize after therapy and those remaining dysregulated, uncovering partial molecular recovery. In dietary perturbation and reversal phosphoproteomics, it uncovers the phosphorylation sites linked to incomplete restoration of insulin signaling. In single-cell transcriptomes from COVID-19 patients with varying severities, it identifies cell-type-specific transcripts marking resolution or persistence of inflammatory activity. Together, these analyses demonstrate SwitchClass as an interpretable framework for mapping directional molecular changes in systems with intermediate states.

Related

  1. STRUCTURAL AND MOLECULAR DYNAMICS ANALYSIS OF HUMAN β-DEFENSIN 1 VARIANTS REVEALS DISTINCT PERTURBATION SIGNATURES
    R. J. Fogarty, R. Urrutia, F. Pinto e Vairo +2
    bioRxivPreprintAll rights reservedFull textBiophysicsbioRxiv
  2. [Melanocytomas : Intermediate melanocytic neoplasms with distinct morphology and molecular background].
    Daniela Mihic-Probst, Francesca Saro
    Pathologie (Heidelberg, Germany)Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. A transition state-like acylenzyme conformation distinguishes carbapenemase activity in class A β-lactamases
    M. Beer, J. Spencer, A. J. Mulholland
    bioRxivPreprintCC BY-NDFull textGeneral biochemistrybioRxiv
  4. Quantitative lipidomics reveals Lipid perturbation of plasma apoptotic extracellular vesicles during physiological aging
    Maojiao Li, Haisen Huang, Qi Tang
    Frontiers in cell and developmental biologyPeer-reviewedCC BYFull textGeneral biochemistryEurope PMC
  5. Localized thermal perturbation alters lipid bilayer structure and daunorubicin interactions in MscL-containing membrane systems
    M. A. Dashti, D. Mohammad-Aghaie, O. Bavi
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref

Cite

BibTeXRIS
BibTeX
@article{xiao2026switchclass,
  title = {{SwitchClass distinguishes baseline- and perturbation-aligned features across intermediate molecular states}},
  author = {Di Xiao and Siqu Long and Pengyi Yang},
  journal = {Cell Reports Methods},
  year = {2026},
  month = aug,
  doi = {10.1016/j.crmeth.2026.101547},
  url = {https://doi.org/10.1016/j.crmeth.2026.101547},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - SwitchClass distinguishes baseline- and perturbation-aligned features across intermediate molecular states
AU  - Di Xiao
AU  - Siqu Long
AU  - Pengyi Yang
PY  - 2026
DA  - 2026/08/12
JO  - Cell Reports Methods
DO  - 10.1016/j.crmeth.2026.101547
UR  - https://doi.org/10.1016/j.crmeth.2026.101547
AB  - Biological systems often exhibit intermediate molecular states under perturbation, showing changes that align with baseline condition or perturbed state. Capturing these complex patterns is critical for understanding molecular resilience and maladaptive persistence. We introduce SwitchClass, a label-switch classification framework that distinguishes features whose intermediate-state profiles align with baseline or perturbed condition. By training a dual classifier with inverted labels, SwitchClass computes a directional importance score (δ), which quantifies each feature’s alignment across biological states. Applied to colorectal cancer proteomics, SwitchClass reveals proteins that normalize after therapy and those remaining dysregulated, uncovering partial molecular recovery. In dietary perturbation and reversal phosphoproteomics, it uncovers the phosphorylation sites linked to incomplete restoration of insulin signaling. In single-cell transcriptomes from COVID-19 patients with varying severities, it identifies cell-type-specific transcripts marking resolution or persistence of inflammatory activity. Together, these analyses demonstrate SwitchClass as an interpretable framework for mapping directional molecular changes in systems with intermediate states.
SN  - 2667-2375
ER  -