{
  "abstract": "In this work, we focus on predicting fold-switching phenomena observed in certain protein structures. Proteins that undergo fold-switching are called metamorphic proteins. We model fold-switch prediction in proteins as a position/residue-wise classification task. We use various features extracted from a protein's sequence as well as structure to train the classifiers. We propose a novel class of handcrafted parametrised features that encode the structural context of a residue. We also use embeddings from existing protein language models (PLMs) to train the classifiers. We train binary and 3-class classifiers, with the 3-class classifiers providing granular information on the type of fold-switch. In our computations, higher classification performance is achieved for binary prediction as compared to 3-class granular prediction. The handcrafted features perform comparably with the PLM embeddings on our standard test set. A rigorous error analysis by us during the review period revealed a critical data-leakage vulnerability in the metamorphic protein test data. This analysis also revealed that the PLM-based classifier suffers sequence-memorisation bias and fails to generalise to novel fold-switching sequences. On the other hand, one of our domain-informed handcrafted feature based classifier detects fold-switching without relying on sequence memory.",
  "abstract_shown": true,
  "affiliations": [
    "Indian Institute of Technology Bombay"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "P. Machingal"
    },
    {
      "name": "N. Hemachandra"
    },
    {
      "name": "P. V. Balaji"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1c0ewndv0tmzj.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.30.755750",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.30.755750v1.full",
  "id": "1c0ewndv0tmzj",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.30.755750v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7220954298",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.30.755750v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1c0ewndv0tmzj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:41Z",
      "native_id": "10.64898/2026.09.30.755750",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.30.755750v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features",
  "title_text": "Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:46Z",
  "url": "https://research.draconitic.com/paper/1c0ewndv0tmzj",
  "venue": "bioRxiv",
  "versions": []
}