{ "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.", "abstract_shown": true, "affiliations": [ "Computer Science and Engineering, Aliah University, Kolkata, India", "Computational Biology, Indraprastha Institute of Information Technology, New Delhi, India", "Data Science, The West Bengal National University of Juridical Sciences, Kolkata, India" ], "article_type": "Methods", "arxiv": null, "author_total": 4, "authors": [ { "affs": [ 0 ], "name": "Ritwik Ganguly" }, { "affs": [ 1 ], "name": "Sana Aafrine" }, { "affs": [ 2 ], "name": "Sk Md Mosaddek Hossain" }, { "name": "Sumanta Ray" } ], "bibtex": "https://research.draconitic.com/paper/fvnr8cr9xsfmr.bib", "cited_by": 0, "doi": "10.1371/journal.pcbi.1014601", "fulltext_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014601", "id": "fvnr8cr9xsfmr", "issns": [ "1553-7358" ], "landing_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014601", "language": null, "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "journal", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "openalex", "1312|Single-cell and spatial transcriptomics" ], [ "plos", "/Biology and life sciences/Computational biology/Genome analysis/Transcriptome analysis" ], [ "plos", "/Biology and life sciences/Genetics/Gene expression" ], [ "plos", "/Biology and life sciences/Genetics/Genomics/Genome analysis/Transcriptome analysis" ], [ "plos", "/Biology and life sciences/Molecular biology/Molecular biology techniques/Marker genes" ], [ "plos", "/Biology and life sciences/Plant science/Plant anatomy/Pollen" ], [ "plos", "/Computer and information sciences/Network analysis" ], [ "plos", "/Computer and information sciences/Software engineering/Preprocessing" ], [ "plos", "/Engineering and technology/Software engineering/Preprocessing" ], [ "plos", "/Physical sciences/Mathematics/Statistics/Statistical data" ], [ "plos", "/Research and analysis methods/Cell enumeration techniques/Total cell counting" ], [ "plos", "/Research and analysis methods/Molecular biology techniques/Marker genes" ] ], "openalex": "W7220437427", "pdf_url": "https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1014601&type=printable", "pmcid": null, "pmid": null, "published": "2026-10-05", "publisher": "Public Library of Science", "ris": "https://research.draconitic.com/paper/fvnr8cr9xsfmr.ris", "sources": [ { "first_seen": "2026-10-30T12:17:37Z", "native_id": "10.1371/journal.pcbi.1014601", "source": "plos", "url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014601" } ], "subjects": [ { "field": "biochemistry", "origin": "plos:gene expression", "subfield": "molecular-biology" }, { "field": "biology", "origin": "plos:computational biology", "subfield": "bioinformatics" }, { "field": "biology", "origin": "plos:genomics", "subfield": "genetics-genomics" } ], "title": "A graph-attentive GAN for rare-cell-aware single-cell RNA-seq data generation", "title_text": "A graph-attentive GAN for rare-cell-aware single-cell RNA-seq data generation", "type": "peer-reviewed", "updated_at": "2026-10-30T12:17:37Z", "url": "https://research.draconitic.com/paper/fvnr8cr9xsfmr", "venue": "PLOS Computational Biology", "versions": [] }