{
  "abstract": "Protein scaffold gap filling is an important computational task in protein sequence reconstruction, where missing amino acid regions must be inferred from incomplete scaffold information. This study proposes a hybrid machine learning and mass constrained reranking framework for protein scaffold gap filling under known-gap-size and known-gapmass settings. Homologous protein sequences from MabCampath, P5A proteoform, and carbonic anhydrase 2 were used to generate masked 11-mer residue-level samples and fullgap evaluation cases. The residue prediction task was formulated as a 20-class amino acid classification problem using first-, middle-, and last-position masking. Multiple classical machine learning models were trained using raw encoded, row-average, and SVD-reduced features, and the strongest models were combined through a validation-accuracy-weighted ensemble. For known-size gap reconstruction, beam search was used to generate complete missing peptide sequences from residue-level probability estimates. For known-mass reconstruction, mass-constrained homologous candidate retrieval was combined with hybrid reranking based on mass validity, homologous frequency, context support, ensemble likelihood, mass error, and length penalty. The proposed framework achieved 95.41% residue-level validation accuracy, 87.50% known-size exact-match accuracy, and 100% top-5 recovery on seven CAH2 known-mass benchmark cases. These results indicate that the proposed framework can effectively reconstruct missing protein regions by integrating local sequence learning, homologous evidence, peptide mass constraints, and biochemical validation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.05436",
  "author_total": 3,
  "authors": [
    {
      "name": "Tahmid Enam Shrestha"
    },
    {
      "name": "Md. Manzurul Hasan"
    },
    {
      "name": "Md. Rafiqul Islam"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2nmr0xrskbc1k.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.05436",
  "fulltext_url": null,
  "id": "2nmr0xrskbc1k",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.05436",
  "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.BM"
    ],
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7212042004",
  "pdf_url": "https://arxiv.org/pdf/2609.05436",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2nmr0xrskbc1k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:02Z",
      "native_id": "2609.05436",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.05436"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking",
  "title_text": "Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:02Z",
  "url": "https://research.draconitic.com/paper/2nmr0xrskbc1k",
  "venue": "arXiv",
  "versions": []
}