Peer-reviewedCC BY 4.0PLOS Computational Biology5 Oct 2026

A graph-attentive GAN for rare-cell-aware single-cell RNA-seq data generation

Ritwik Ganguly¹
Sana Aafrine²
Sk Md Mosaddek Hossain³
Sumanta Ray

¹Computer Science and Engineering, Aliah University, Kolkata, India
²Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India
³Data Science, The West Bengal National University of Juridical Sciences, Kolkata, India

Abstract

A central challenge in downstream single-cell RNA sequencing (scRNA-seq) analysis is the high-dimensional, small-sample (HDSS) regime, often compounded by class imbalance from rare cell types. These factors hinder robust feature (gene) selection and cell clustering and limit the realism of samples generated by existing simulators. We introduce GARAGE, a Graph-Attentive RAre-cell aware single-cell data GEneration that augments the generator’s input with a small, attention-weighted ‘leakage’ of real cells in addition to prior noise. Specifically, we build a k-nearest-neighbour cell graph and use a graph attention network (GAT) to prioritize nodes that likely represent under-sampled (rare) subpopulations; these high-attention cell embeddings are injected into the generator input to steer synthesis toward biologically plausible regions of the data manifold while respecting cell-type proportions. This attention-guided leakage accelerates training, reduces mode dropping, and yields realistic synthetic cells that preserve rare-cell structure. Across real scRNA-seq benchmarks, GARAGE improves downstream feature selection and clustering compared with state-of-the-art baselines. In summary, GARAGE directly addresses HDSS and rarity in scRNA-seq by coupling graph attention with adversarial generation to produce high-fidelity synthetic cells that enhance downstream analyses. The corresponding software is available at: https://github.com/RitwikGanguly/GARAGE. Author summary: Researchers frequently analyze single-cell transcriptomic data to unravel the mechanisms behind complex diseases. Yet, rare but important cell types are often too scarce in patient samples to study reliably. We introduce GARAGE - Graph-Attentive RAre-cell aware single-cell data GEneration - a two-step framework that explicitly couples graph attention with adversarial learning. First, a neighborhood graph with attention weights surfaces “exemplar cells”, prioritizing rare populations. Second, we apply an attention-guided “leakage”: a small, curated set of these high-score real cells is injected into the GAN’s input alongside noise. This graph-attentive prior steers the generator to the full data manifold, accelerates and stabilizes GAN convergence, and prevents mode dropping, so rare cell types are synthesized faithfully. Across real scRNA-seq benchmarks, GARAGE produces more complete, biologically coherent datasets and consistently outperforms state-of-the-art methods in downstream feature selection and clustering. By tackling the high-dimensional, small-sample regime head-on, GARAGE delivers realistic synthetic cells that preserve rare-cell structure and diversity, providing a practical tool to power robust analyses and speed discovery.

Edge-Aware Graph Attention Networks for Interpreting Biophysical Mechanisms from Molecular Dynamics Simulations
M. Ahsan, C. Pindi, G. Palermo
bioRxiv3 Sep 2026PreprintAll rights reservedFull textBiophysicsbioRxiv
GLASS: a graph learning algorithm for screening splice-aware alignments of long-read RNA-seq data
Jiahao Li, Zeming Tan, Guojun Li +1
BMC Genomics30 Sep 2026Peer-reviewedCC BY-NC-ND 4.0Molecular biology & gene regulationCrossref
Topology-Aware Multi-Omics Tensor Graph Clustering for Cancer Subtype Identification
Hanrui Shi, Man-Fai Leung
Biomolecules1 Sep 2026Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCDOAJ
EvoGraph: synergizing evolutionary semantics and tail-aware graph contrastive learning for protein-protein interaction prediction.
Yilou Zhang, Yuan Zhao, Jue Zhou +2
Briefings in bioinformatics1 Sep 2026Peer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMCPMC
Relation-Aware Heterogeneous Graph Learning for miRNA–Drug Response Association Prediction Under Cold-Start Generalization
Murtada K. Elbashir
International Journal of Molecular Sciences11 Oct 2026Peer-reviewedCC BY 4.0Full textGeneral biochemistryCrossrefEurope PMC

Cite

BibTeX RIS

BibTeX

@article{ganguly2026graphattentive,
  title = {{A graph-attentive GAN for rare-cell-aware single-cell RNA-seq data generation}},
  author = {Ritwik Ganguly and Sana Aafrine and Sk Md Mosaddek Hossain and Sumanta Ray},
  journal = {PLOS Computational Biology},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pcbi.1014601},
  url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014601},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - A graph-attentive GAN for rare-cell-aware single-cell RNA-seq data generation
AU  - Ritwik Ganguly
AU  - Sana Aafrine
AU  - Sk Md Mosaddek Hossain
AU  - Sumanta Ray
PY  - 2026
DA  - 2026/10/05
JO  - PLOS Computational Biology
DO  - 10.1371/journal.pcbi.1014601
UR  - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014601
AB  - A central challenge in downstream single-cell RNA sequencing (scRNA-seq) analysis is the high-dimensional, small-sample (HDSS) regime, often compounded by class imbalance from rare cell types. These factors hinder robust feature (gene) selection and cell clustering and limit the realism of samples generated by existing simulators. We introduce GARAGE, a Graph-Attentive RAre-cell aware single-cell data GEneration that augments the generator’s input with a small, attention-weighted ‘leakage’ of real cells in addition to prior noise. Specifically, we build a k-nearest-neighbour cell graph and use a graph attention network (GAT) to prioritize nodes that likely represent under-sampled (rare) subpopulations; these high-attention cell embeddings are injected into the generator input to steer synthesis toward biologically plausible regions of the data manifold while respecting cell-type proportions. This attention-guided leakage accelerates training, reduces mode dropping, and yields realistic synthetic cells that preserve rare-cell structure. Across real scRNA-seq benchmarks, GARAGE improves downstream feature selection and clustering compared with state-of-the-art baselines. In summary, GARAGE directly addresses HDSS and rarity in scRNA-seq by coupling graph attention with adversarial generation to produce high-fidelity synthetic cells that enhance downstream analyses. The corresponding software is available at: https://github.com/RitwikGanguly/GARAGE. Author summary: Researchers frequently analyze single-cell transcriptomic data to unravel the mechanisms behind complex diseases. Yet, rare but important cell types are often too scarce in patient samples to study reliably. We introduce GARAGE - Graph-Attentive RAre-cell aware single-cell data GEneration - a two-step framework that explicitly couples graph attention with adversarial learning. First, a neighborhood graph with attention weights surfaces “exemplar cells”, prioritizing rare populations. Second, we apply an attention-guided “leakage”: a small, curated set of these high-score real cells is injected into the GAN’s input alongside noise. This graph-attentive prior steers the generator to the full data manifold, accelerates and stabilizes GAN convergence, and prevents mode dropping, so rare cell types are synthesized faithfully. Across real scRNA-seq benchmarks, GARAGE produces more complete, biologically coherent datasets and consistently outperforms state-of-the-art methods in downstream feature selection and clustering. By tackling the high-dimensional, small-sample regime head-on, GARAGE delivers realistic synthetic cells that preserve rare-cell structure and diversity, providing a practical tool to power robust analyses and speed discovery.
SN  - 1553-7358
ER  -

Abstract

Related

Cite