{
  "abstract": "Cytochrome P450 (CYP) enzymes metabolize roughly three-quarters of clinically used drugs, and genetic variation in these enzymes is a leading source of interindividual differences in drug response. Predicting a variant's functional effect is therefore critical, yet the consequences of most CYP variants remain unknown. Many state-of-the-art variant-effect predictors rest on a homology-based paradigm that scores variants by evolutionary conservation -- an assumption that pharmacogenes, including CYPs, violate. Focusing on human CYPs, we show that homology-based models fail systematically. AlphaMissense (AM) assigns variants to its \"ambiguous\" class at nearly twice the proteome-wide rate across six clinically important CYPs, and within that class its scores are essentially uninformative about measured CYP2C9 deep mutational scan (DMS) activity ({rho}=-0.130). Using catalytic activity and cellular abundance from the same CYP2C9 DMS, we show that AM is largely an abundance signal: it tracks activity well for destabilizing, low-abundance variants ({rho}=-0.568) but far more weakly for abundance-independent variants ({rho}=-0.357; Fisher r-to-z z=-8.99, p<1e-18). We further hypothesized that non-homology-based features (sequence position, substitution chemistry, distance to the substrate-recognition sites, and secondary structure) might account for where AM errs, but their explanatory power is weak. Using CYP2C9 DMS activity as ground truth, we built a k-nearest-neighbors model over ESM-2 embeddings and ensembled it with AM and ESM-2 masked marginal probability, raising the correlation between predicted and measured activity within the ambiguous class from {rho}=0.080 for AM alone to 0.399, and reaching an overall {rho}=0.721 that exceeds every out-of-the-box predictor we tested ({rho}=0.523 to 0.686). However, neither this improved ensemble model nor any other method agrees significantly with clinical annotations. Drawing on evidence that a variant's effect can depend on the drug, we hypothesize that substrate identity is the key missing feature in current models, and that predicting function for these multi-substrate enzymes may require redefining function as substrate-conditioned.",
  "abstract_shown": true,
  "affiliations": [
    "Stanford University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "H. Xu"
    },
    {
      "name": "I. Samori"
    },
    {
      "name": "G. Nayar"
    },
    {
      "affs": [
        0
      ],
      "name": "R. B. Altman"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1grfgsrf08hy4.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.07.30.741616",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.07.30.741616v2.full",
  "id": "1grfgsrf08hy4",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.07.30.741616v2",
  "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",
      "3004|Pharmacogenetics and Drug Metabolism"
    ]
  ],
  "openalex": "W7172514724",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.07.30.741616v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1grfgsrf08hy4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:49Z",
      "native_id": "10.64898/2026.07.30.741616",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.07.30.741616v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Homology-Based Variant-Effect Predictors Break Down on Cytochrome P450 Pharmacogenes",
  "title_text": "Homology-Based Variant-Effect Predictors Break Down on Cytochrome P450 Pharmacogenes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:49Z",
  "url": "https://research.draconitic.com/paper/1grfgsrf08hy4",
  "venue": "bioRxiv",
  "versions": []
}