{
  "abstract": "Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.24538",
  "author_total": 2,
  "authors": [
    {
      "name": "Demian Pavlyshenko"
    },
    {
      "name": "Bohdan Pavlyshenko"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d77zaca5c6225.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.24538",
  "fulltext_url": null,
  "id": "d77zaca5c6225",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.24538",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7214055351",
  "pdf_url": "https://arxiv.org/pdf/2609.24538",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d77zaca5c6225.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:28Z",
      "native_id": "2609.24538",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.24538"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation",
  "title_text": "QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:28Z",
  "url": "https://research.draconitic.com/paper/d77zaca5c6225",
  "venue": "arXiv",
  "versions": []
}