{
  "abstract": "Optimizing a molecular generator against a single activity-model estimate can reward structures for which that estimate is unreliable. We extended our published ChemBERTa–reinforcement-learning (RL) workflow for human epidermal growth factor receptor (EGFR) with scaffold-separated activity modeling, empirically calibrated lower scores, bounded chemistry rewards, and matched-seed evaluation. From ChEMBL 37, we curated 6,476 unique structures with Reference/unspecified biochemical EGFR IC50 measurements; 4,491, 680, and 1,305 structures were assigned to scaffold-disjoint training, calibration, and test sets. The random-forest reward model achieved a test mean absolute error of 0.610 pIC50 units and R2 = 0.615. Uniform or potency-enriched masked-language-model continuation was crossed with three RL rewards, with three seeds and 600 generation attempts per combination. The locked LCB-versus-mean-only comparison changed GNN potency-screen yield by +0.28 percentage points (95% descriptive t interval,-1.10 to +1.66) across three seed-cluster means. In the pipeline-level comparison with the published-form baseline, Robust-LCB increased the GNN joint-screen yield in all six matched blocks; averaged across the two MLM arms, the yield rose from 0.72% to 1.22%. Two structures passed the full RF–GNN consensus funnel. These results support a pipeline-level increase in joint predicted-potency and drug-like yield, while the incremental contribution of the lower-score term alone remains uncertain. These comparisons describe computational variability; activity estimates for generated molecules require biochemical testing.",
  "abstract_shown": true,
  "affiliations": [
    "Shanghai World Foreign Language Academy",
    "Department of Chemistry",
    "Duke University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yutong Guo"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Xiao Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8serbtmaeqw8b.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008490/v1",
  "fulltext_url": null,
  "id": "8serbtmaeqw8b",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008490/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7211935761",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008490/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/8serbtmaeqw8b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008490",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008490/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Robust Multi-Objective Reinforcement Learning Improves Joint Predicted-Potency and Drug-Likeness Yield in EGFR Molecule Generation",
  "title_text": "Robust Multi-Objective Reinforcement Learning Improves Joint Predicted-Potency and Drug-Likeness Yield in EGFR Molecule Generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/8serbtmaeqw8b",
  "venue": "ChemRxiv",
  "versions": []
}