{
  "abstract": "Data availability is critical for understanding complex disease pathways and developing robust predictive models. Although high-throughput omics technologies have improved insight into disease mechanisms, data acquisition from inaccessible tissues such as the central nervous system remains a major limitation, causing small sample sizes and complicating early prediction of neurodegenerative disorders such as Alzheimer's and Parkinson's diseases. Generative modeling has emerged as a powerful approach for synthesizing data to support downstream clustering and prediction with small sample size, but existing methods rarely handle high-dimensional tabular omics data effectively. Adversarial random forests (ARFs) provide a well-performing framework for tabular data generation but are not designed for high-dimensional settings. To address this limitation, we introduce high-dimensional ARF (h-ARF), an extension of ARF optimized for integrated clinical and high-dimensional omics data. Using benchmarks across nine datasets and eight performance metrics, we show that h-ARF better preserves both feature distributions, and downstream clustering and prediction utilities compared with ARFs. The method is implemented in the open-source R package harf, available on CRAN.",
  "abstract_shown": true,
  "affiliations": [
    "Emory University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "C. J. Kuete Fouodo"
    },
    {
      "name": "J. Kapar"
    },
    {
      "name": "A. Huels"
    },
    {
      "name": "D. Liang"
    },
    {
      "name": "M. N. Wright"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/26xv64whjk44r.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.09.750490",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.09.750490v1.full",
  "id": "26xv64whjk44r",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.09.750490v1",
  "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|Bioinformatics and Genomic Networks"
    ]
  ],
  "openalex": "W7213274237",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.09.750490v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/26xv64whjk44r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:35Z",
      "native_id": "10.64898/2026.09.09.750490",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.09.750490v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Adversarial random forests for omics synthesis",
  "title_text": "Adversarial random forests for omics synthesis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:35Z",
  "url": "https://research.draconitic.com/paper/26xv64whjk44r",
  "venue": "bioRxiv",
  "versions": []
}