{
  "abstract": "The Practical Molecular Optimization (PMO) benchmark standardized evaluation in molecular optimization, but it is built on simple property-based oracles that do not capture structure-based drug design. As the field has moved to docking-based objectives, evaluation practice has become unstandardized, and different methods report results on different docking tasks, often without a shared protocol for fair comparison or sample-efficiency constraints. To address this, we introduce Practical Molecular Optimization for Docking (PMO-Dock), a benchmark and protocol for docking-based optimization consisting of 25 tasks covering hit generation, lead optimization, and a new specificity task requiring strong on-target binding while penalizing off-target interactions. The protocol separates model development from final evaluation: validation tasks are used for hyperparameter tuning, and test tasks are held out for final evaluation and are not used during development. Evaluation on the test tasks is done under a strict oracle budget to reflect realistic drug-discovery settings. We benchmark four diverse high-performing methods spanning different optimization paradigms, Saturn (reinforcement learning), GenMol (discrete diffusion), Genetic-guided GFlowNet, and ChemLlama (LLM-based evolutionary search). Our results show no universally best method across tasks, additional analyses of hyperparameter transfer (cross-task and cross-category) and sensitivity show that transfer is often limited and varies by method, motivating method-dependent selection strategies. This benchmark provides a concrete standard for evaluating generalization to unseen tasks and sample efficiency under a limited test-time oracle budget.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.19011",
  "author_total": 5,
  "authors": [
    {
      "name": "Gor Simonyan"
    },
    {
      "name": "Tatevik Abrahamyan"
    },
    {
      "name": "Narek Abelyan"
    },
    {
      "name": "Tigran Fahradyan"
    },
    {
      "name": "Hrant Khachatrian"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fg5awky32avkb.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.19011",
  "fulltext_url": null,
  "id": "fg5awky32avkb",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.19011",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7221878784",
  "pdf_url": "https://arxiv.org/pdf/2610.19011",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fg5awky32avkb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:36Z",
      "native_id": "2610.19011",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.19011"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization",
  "title_text": "PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:36Z",
  "url": "https://research.draconitic.com/paper/fg5awky32avkb",
  "venue": "arXiv",
  "versions": []
}