Subtypes estimation in single-cell multi-omics data via S-multi-SNE
Clinical Snapshot
PICO Framework
| P — Population | Single-cell RNA sequencing (scRNA-seq) datasets from various tissues and organisms, including multi-omics data (scRNA-seq and scATAC-seq) |
| I — Intervention | S-multi-SNE (supervised multi-view stochastic neighbour embedding) algorithm for dimensionality reduction and classification |
| C — Comparator | Other machine learning techniques and existing reference-based single-cell classification algorithms |
| O — Outcomes | Cell subtype identification accuracy, visualization quality, and classification performance across different species and sequencing technologies |
Bottom Line
S-multi-SNE represents a promising computational advance for single-cell multi-omics analysis, offering improved cell subtype identification across different species and sequencing platforms. The method's ability to integrate scRNA-seq and scATAC-seq data addresses a critical need in precision medicine and biomarker discovery. However, the abstract lacks specific performance metrics, statistical validation, and implementation details necessary for clinical adoption. While the approach shows theoretical promise for enhancing cellular characterization in research and diagnostic applications, clinicians should await peer review and detailed methodology before considering implementation. The technique may prove particularly valuable for cancer subtyping, immunophenotyping, and drug target identification, but requires validation in clinical cohorts with known outcomes.
Key Findings
P Value: Not reported in abstract
Effect Size: Consistent outperformance of other machine learning techniques (specific metrics not provided)
Primary Outcome: Cell subtype identification accuracy using S-multi-SNE algorithm
Nnt Or Sensitivity: Sensitivity and specificity for cell subtype classification not specified in abstract
Confidence Interval: Not reported in abstract
Clinical Application
High feasibility as computational method requiring only standard single-cell sequencing data Relevant to Australian research institutions and clinical laboratories performing single-cell analysis, particularly in cancer research and immunology applications supported by NHMRC funding Researchers and clinicians using single-cell sequencing for disease characterization, drug discovery, and precision medicine applications
Abstract
Single-cell RNA sequencing (scRNA-seq) has rapidly become an essential method in modern biology, as it allows global characterisation of transcriptomics in individual cells from different tissues, or organisms. scRNA-seq data are collected from a single individual organism and they are composed as mRNA count matrices with rows representing the cells and columns the genes. New technologies further allow multi-omics data to be obtained on the same set of single cells. In this paper, multi-SNE and S-multi-SNE, two multi-view dimensionality reduction approaches, are adapted for visualization and classification of cellular subtypes, two important challenges in the analysis of scRNA-seq data. S-multi-SNE has been adapted for cell subtype estimation of scRNA-seq data. In a series of experiments we illustrate that it is possible to identify cell subtypes by leveraging information from individuals from the same species, from different species, and when data are generated by different sequencing technologies. In the conducted analyses, we show that S-multi-SNE consistently outperformed several other machine learning techniques and, in most comparisons, surpassed existing reference-based single-cell classification algorithms. We further illustrate how two single-cell multi-omics datasets, scATAC-seq and scRNA-seq, can be integrated together through S-multi-SNE for improved cell subtype identification.
References
- 1.Rodosthenous, T., Shahrezaei, V., & Evangelou, M. (2026). Subtypes estimation in single-cell multi-omics data via S-multi-SNE. Journal of Theoretical Biology, 112442. https://doi.org/10.1016/j.jtbi.2026.112442
Related Research
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
3 Aug 2026
Journal of chemical information and modeling
ProphDR: An Interpretable Deep Learning Model for Predicting Cancer Drug Response via Multi-Omics and Cross-Attention Mechanisms
28 July 2026
PloS one
Multi-view graph-regularized deep metric subspace clustering network
26 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service