{
  "abstract": "Identifying which target-indication (T-I) hypotheses can translate into clinical success remains a central challenge in drug discovery. We present PRIORITI (Prospective Rationale-Informed Outcome Reasoning for Integrated Target-indication Intelligence), a leakage-resistant framework that separates upstream biological evidence synthesis from outcome prediction. Given only a target gene and disease indication, a domain-instructed large language model (LLM) synthesizes drug-agnostic human genetics across prespecified channels. These evidence were embedded and combined with static entity context derived from gene summaries and disease definitions. The resulting representation is used to fit a supervised model trained on 6,784 temporally curated historical T-I outcomes, which is one of the largest cohorts assembled for this task. On a held-out historical test set of 1,696 T-I pairs, PRIORITI achieved a ROC-AUC of 0.883 and an expected calibration error (ECE) of 0.023, outperforming both a static target and indication context baseline and a human-curated genetic-evidence reference. On a strictly post-cutoff out-of-time benchmark of 765 T-I pairs, the largest such evaluation cohort reported to date, performance remained robust, with ROC-AUC 0.817, PR-AUC 0.357 and ECE 0.044, exceeding static target and indication context baseline and direct zero-shot LLM forecasting. A label-blinded LLM-based explainer further converted locked predictions into auditable prioritization rationales. Together, PRIORITI provides a calibrated, biology-first probability together with decision-oriented rationales for T-I prioritization before downstream translational investment.",
  "abstract_shown": true,
  "affiliations": [
    "UT MD Anderson Cancer Center"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "name": "W. Zhang"
    },
    {
      "name": "J. Xu"
    },
    {
      "name": "Z. Zhang"
    },
    {
      "name": "M. Liu"
    },
    {
      "name": "R. Sun"
    },
    {
      "name": "B. Al-lazikani"
    },
    {
      "name": "X. Shen"
    },
    {
      "name": "S. Kopetz"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Wu"
    },
    {
      "name": "B. Zhao"
    },
    {
      "affs": [
        0
      ],
      "name": "C. Wu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e429bdnpm0pxg.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.754137",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754137v1.full",
  "id": "e429bdnpm0pxg",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754137v1",
  "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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7214975325",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754137v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e429bdnpm0pxg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:20Z",
      "native_id": "10.64898/2026.09.24.754137",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754137v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Biological rationales from language models enable leakage-resistant forecasts of target-indication success",
  "title_text": "Biological rationales from language models enable leakage-resistant forecasts of target-indication success",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:20Z",
  "url": "https://research.draconitic.com/paper/e429bdnpm0pxg",
  "venue": "bioRxiv",
  "versions": []
}