{
  "abstract": "Correcting batch effects and integrating single-cell sequencing datasets has been a crucial step in large-scale biological studies. Many methods have been published for this task, and excel in various scenarios. Our previous work, LIGER, leveraging integrative non-negative matrix factorization (iNMF), stands out in providing an interpretable low-dimensional representation. To adapt to the modern need for integrating millions of cells, we developed a highly-optimized parallel factorization solution with on-demand loading from disk. The upgraded LIGER algorithm shows significant improvements in time and memory efficiency for single-cell data integration. We also developed a new downstream embedding alignment method significantly improved performance in conserving biological variation while still aligning corresponding cell types across datasets.",
  "abstract_shown": true,
  "affiliations": [
    "University of Michigan"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "Y. Wang"
    },
    {
      "name": "A. Robbins"
    },
    {
      "name": "G. Gadhvi"
    },
    {
      "affs": [
        0
      ],
      "name": "J. D. Welch"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/47mf7vgj1pf17.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.08.750130",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.08.750130v1.full",
  "id": "47mf7vgj1pf17",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.08.750130v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7213204180",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.08.750130v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/47mf7vgj1pf17.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:21Z",
      "native_id": "10.64898/2026.09.08.750130",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.08.750130v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "LIGER2: Scalable Single-Cell Integration with On-Disk Datasets",
  "title_text": "LIGER2: Scalable Single-Cell Integration with On-Disk Datasets",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:21Z",
  "url": "https://research.draconitic.com/paper/47mf7vgj1pf17",
  "venue": "bioRxiv",
  "versions": []
}