{
  "abstract": "Fragment-based drug discovery (FBDD) uses small molecular fragments as starting points for drug development, and machine-learning models that operate on molecular string representations are increasingly applied to fragment-related tasks. SMILES is the dominant such representation, but its paired ring closures and balanced parentheses introduce syntactic complexity that can affect model behavior. We present a controlled study of how molecular string representation influences transformer-based fragment recovery, using an FBDD-motivated label pipeline: reference fragments are derived from known drugs via RECAP fragmentation and docking-based ranking, and the model is scored on recovering them. We introduce DeepBERTa, a ChemBERTa-derived transformer pretrained on DeepSMILES, and evaluate it against a matched SMILES baseline under identical architecture, data splits, and optimization (approximately 34,000 drug-fragment pairs). DeepSMILES produces syntactically valid predictions more often than SMILES (54.2% vs. 43.5%) and a higher full test-set mean Tanimoto similarity (0.36 vs. 0.29). A per-sample selection between the two representations raises mean Tanimoto to 0.43, and a deployable variant that selects on model confidence rather than the reference recovers most of this gain. Among molecules where one representation strictly wins, DeepSMILES wins more often than SMILES (27.8% vs. 16.3% of test molecules). These results show that string representation meaningfully influences transformer fragment recovery and that representation-aware selection outperforms either representation alone.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science & Engineering, Aspiring Scholars Directed Research Program, Fremont, CA, 94539, USA.",
    "Department of Chemistry, Biochemistry, and Physical Science, Aspiring Scholars Directed Research Program, Fremont, CA, 94539, USA.",
    "Department of Computer Science & Engineering, Aspiring Scholars Directed Research Program, Fremont, CA, 94539, USA. marx.akl@asdrp.org."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Aayush Kothari"
    },
    {
      "affs": [
        0
      ],
      "name": "Amish Gupta"
    },
    {
      "affs": [
        1
      ],
      "name": "Nisarg Shah"
    },
    {
      "affs": [
        1
      ],
      "name": "Thomas Reed"
    },
    {
      "affs": [
        1
      ],
      "name": "Anvita Nattuva"
    },
    {
      "affs": [
        1
      ],
      "name": "Rahima Nazirudeen"
    },
    {
      "affs": [
        1
      ],
      "name": "Harman Brah"
    },
    {
      "affs": [
        2
      ],
      "name": "Marx Akl"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8cggxh670hkq6.bib",
  "cited_by": 0,
  "doi": "10.1186/s13321-026-01255-w",
  "fulltext_url": "https://europepmc.org/articles/PMC13721515",
  "id": "8cggxh670hkq6",
  "issns": [
    "1758-2946"
  ],
  "landing_url": "https://europepmc.org/article/MED/42958454",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Research"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7171946210",
  "pdf_url": "https://europepmc.org/articles/PMC13721515?pdf=render",
  "pmcid": "PMC13721515",
  "pmid": "42958454",
  "published": "2026-07-31",
  "publisher": "BMC",
  "ris": "https://research.draconitic.com/paper/8cggxh670hkq6.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T00:20:47Z",
      "native_id": "MED:42958454",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42958454"
    },
    {
      "first_seen": "2026-11-03T12:22:11Z",
      "native_id": "PMC13721515",
      "source": "pmc",
      "url": "https://doi.org/10.1186/s13321-026-01255-w"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "issn:1758-2946",
      "subfield": "theoretical"
    }
  ],
  "title": "Transformer-based molecular fragment prediction using SMILES and DeepSMILES representations in a fragment-based drug discovery pipeline.",
  "title_text": "Transformer-based molecular fragment prediction using SMILES and DeepSMILES representations in a fragment-based drug discovery pipeline.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:22:11Z",
  "url": "https://research.draconitic.com/paper/8cggxh670hkq6",
  "venue": "Journal of cheminformatics",
  "versions": []
}