Single‐cell marker gene clustering: A unified deep learning framework for marker gene‐based clustering of single‐cell RNA‐sequencing data
Shahriar Rahman Niloy, Toushif Muktashid Hasan, Md Saiduzzaman Apu, Fahim Hafiz, Salekul Islam, Riasat Azim · 2026
Read Single‐cell marker gene clustering: A unified deep learning framework for marker gene‐based clustering of single‐cell RNA‐sequencing data by Shahriar Rahman Niloy, Toushif Muktashid Hasan, Md Saiduzzaman Apu, Fahim Hafiz, Salekul Islam, Riasat Azim (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13642092.txt.
Description
Shahriar Rahman Niloy and five colleagues present a 2026 deep learning framework, scMGC, for grouping single cells by their gene activity. Single-cell RNA data are sparse and noisy because many genes drop out during measurement, which blurs cell types.
The framework first cleans the data with an autoencoder, then scores marker genes by combining several selection methods before graph-based clustering. Against seven rival methods on seven datasets, it improved clustering accuracy by roughly thirty percent on standard measures. Enrichment checks showed the clusters made biological and clinical sense. Code and data are posted publicly for reuse.
Catalog record
| CREATOR | Shahriar Rahman Niloy, Toushif Muktashid Hasan, Md Saiduzzaman Apu, Fahim Hafiz, Salekul Islam, Riasat Azim |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |