{"entity": "publication", "iuid": "98f7aaff031e4021a76e169e6ca3343c", "timestamp": "2026-08-29T04:36:57.801Z", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/98f7aaff031e4021a76e169e6ca3343c.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/98f7aaff031e4021a76e169e6ca3343c"}}, "title": "scAEGAN: Unification of single-cell genomics data by adversarial learning of latent space correspondences.", "authors": [{"family": "Khan", "given": "Sumeer Ahmad", "initials": "SA", "orcid": "0000-0002-3345-5904", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c26975353fe144209200135f5fd3e6ad.json"}}, {"family": "Lehmann", "given": "Robert", "initials": "R"}, {"family": "Martinez-de-Morentin", "given": "Xabier", "initials": "X"}, {"family": "Maillo", "given": "Alberto", "initials": "A"}, {"family": "Lagani", "given": "Vincenzo", "initials": "V"}, {"family": "Kiani", "given": "Narsis A", "initials": "NA"}, {"family": "Gomez-Cabrero", "given": "David", "initials": "D"}, {"family": "Tegner", "given": "Jesper", "initials": "J", "orcid": "0000-0002-9568-5588", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/b115e5faf68a4acbb6f947c711fd37ec.json"}}], "type": "journal article", "published": "2023-02-03", "journal": {"title": "PLoS ONE", "issn": "1932-6203", "volume": "18", "issue": "2", "pages": "e0281315", "issn-l": "1932-6203"}, "abstract": "Recent progress in Single-Cell Genomics has produced different library protocols and techniques for molecular profiling. We formulate a unifying, data-driven, integrative, and predictive methodology for different libraries, samples, and paired-unpaired data modalities. Our design of scAEGAN includes an autoencoder (AE) network integrated with adversarial learning by a cycleGAN (cGAN) network. The AE learns a low-dimensional embedding of each condition, whereas the cGAN learns a non-linear mapping between the AE representations. We evaluate scAEGAN using simulated data and real scRNA-seq datasets, different library preparations (Fluidigm C1, CelSeq, CelSeq2, SmartSeq), and several data modalities as paired scRNA-seq and scATAC-seq. The scAEGAN outperforms Seurat3 in library integration, is more robust against data sparsity, and beats Seurat 4 in integrating paired data from the same cell. Furthermore, in predicting one data modality from another, scAEGAN outperforms Babel. We conclude that scAEGAN surpasses current state-of-the-art methods and unifies integration and prediction challenges.", "doi": "10.1371/journal.pone.0281315", "pmid": "36735690", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC9897517"}, {"db": "pii", "key": "PONE-D-22-30403"}], "notes": [], "created": "2026-08-21T12:52:28.794Z", "modified": "2026-08-21T12:52:28.883Z"}