{
  "abstract": "Mass spectrometry-based proteomics, including single-cell applications, are often confounded by batch effects, inter-laboratory variation, and signal drift that can obscure biological interpretation. NMFBatch addresses these sources of unwanted variation through a unified framework that combines non-negative matrix factorization with generalized additive modelling to jointly capture discrete and continuous technical effects from protein expression data. It handles missing values directly through masking and on-the-fly imputation. Benchmarking across reference datasets, plasma proteomics cohorts, simulations, and single-cell data demonstrated that NMFBatch reduced technical variation while preserving biological structure. These results establish NMFBatch as a robust framework for batch correction, harmonization, and integrative proteomics analysis from protein expression data.",
  "abstract_shown": true,
  "affiliations": [
    "Turku Bioscience Centre, University of Turku and Abo Akademi University, Turku 20520, Finland"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. M. Anwar"
    },
    {
      "name": "S. Bayoumi"
    },
    {
      "name": "L. Lahti"
    },
    {
      "name": "E. Coffey"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/evyymtmb2b7nv.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.05.19.726178",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.05.19.726178v3.full",
  "id": "evyymtmb2b7nv",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.05.19.726178v3",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1607|Advanced Proteomics Techniques and Applications"
    ]
  ],
  "openalex": "W7162004914",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.05.19.726178v3.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/evyymtmb2b7nv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:02Z",
      "native_id": "10.64898/2026.05.19.726178",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.05.19.726178v3"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "A Unified Framework for Batch Correction and Imputation in Modern Mass Spectrometry Proteomics",
  "title_text": "A Unified Framework for Batch Correction and Imputation in Modern Mass Spectrometry Proteomics",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:02Z",
  "url": "https://research.draconitic.com/paper/evyymtmb2b7nv",
  "venue": "bioRxiv",
  "versions": []
}