{
  "abstract": "Cross-platform harmonization of bulk transcriptomic datasets remains a fundamental challenge for developing cancer biomarkers because of persistent unresolved batch effects. Most harmonization tools are benchmarked on datasets with large inter-group biological differences (for example TCGA tumor types), whereas actionable biomarker mining requires preserving subtle transcriptional distinctions between closely related diagnoses. Here we present ComboBatch, a benchmarking pipeline that evaluates the full cross-product of 14 batch-removal strategies, 3 imputation methods, 33 harmonization algorithms and 2 post-removal conditions across 7,174 samples from 88 germinal-center B-cell lymphoma cohorts spanning four transcriptomic platforms. Scoring 87 quality metrics across 2,234 harmonization approaches, we show that method choice (R2 0.36) and batch-removal strategy (0.26) are the principal determinants of harmonization quality, whereas imputation (0.016) and post-removal (<0.01) are secondary. Feature Specific Quantile Normalization and Surrogate Variable Analysis were the top methods, jointly resolving follicular lymphoma, diffuse large B-cell lymphoma and normal germinal-center B-cell differences in multi-platform and RNA-seq-only compositions, respectively. We provide a data-driven five-scenario decision tree for harmonization method selection, applicable to any retrospective multi-platform transcriptomic study. The ComboBatch pipeline is available on GitHub and can be used for harmonization, allowing bioinformaticians to utilize 33 harmonization and 3 imputation methods according to their needs.",
  "abstract_shown": true,
  "affiliations": [
    "Institute of Molecular Biology, National Academy of Science of the Republic of Armenia, Yerevan, 0014, Armenia"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "D. Nikitin"
    },
    {
      "name": "N. M. Borisov"
    },
    {
      "name": "M. Savchenko"
    },
    {
      "name": "A. Bobe"
    },
    {
      "name": "M. Meerson"
    },
    {
      "name": "A. Nesmelov"
    },
    {
      "name": "N. Harutyunyan"
    },
    {
      "name": "S. Paponova"
    },
    {
      "name": "A. Kravets"
    },
    {
      "name": "A. Zaitsev"
    },
    {
      "name": "A. Bagaev"
    },
    {
      "name": "A. Arakelyan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5jpwtd7xsma25.bib",
  "cited_by": 1,
  "doi": "10.64898/2026.09.15.751825",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751825v1.full",
  "id": "5jpwtd7xsma25",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751825v1",
  "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",
      "cancer biology"
    ],
    [
      "openalex",
      "1312|Gene expression and cancer classification"
    ]
  ],
  "openalex": "W7213512789",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751825v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5jpwtd7xsma25.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:55Z",
      "native_id": "10.64898/2026.09.15.751825",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751825v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "biorxiv:cancer biology",
      "subfield": "oncology"
    }
  ],
  "title": "Benchmarking of bulk transcriptomic harmonization tools in a multi-platform B-cell lymphoma cohort identifies feature-specific quantile normalization and surrogate variable analysis as top-performing methods",
  "title_text": "Benchmarking of bulk transcriptomic harmonization tools in a multi-platform B-cell lymphoma cohort identifies feature-specific quantile normalization and surrogate variable analysis as top-performing methods",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:55Z",
  "url": "https://research.draconitic.com/paper/5jpwtd7xsma25",
  "venue": "bioRxiv",
  "versions": []
}