{
  "abstract": "Motivation: Antibody-antigen affinity determines which antibodies advance in therapeutic discovery, repertoire analysis and affinity maturation, but experimental measurements are sparse relative to the scale of sequence libraries. Structure-based predictors can exploit interface geometry when reliable complexes are available, yet early discovery often requires ranking many heavy-light chain pairs against antigens for which no complex structure exists. Existing sequence-based models are scalable, but frequently compress heavy and light chains into a single antibody representation or concatenate antibody and antigen features, potentially obscuring the chain-specific and epitope-specific signals that drive binding. Results: We present AbAffinity, a sequence-only chain-aware three-stream architecture that maintains heavy chain, light chain and antigen as distinct streams. It integrates frozen ESM-2 embeddings with heavy-chain CDR-focused pooling, heavy-light self-attention, adaptive fusion and gated cross-attention, training only a compact interaction module. Under nested ten-fold cross-validation on SAAINT-DB, AbAffinity achieves Pearson r = 0.838 {+/-} 0.033, Spearman {rho} = 0.828 {+/-} 0.027 and RMSE = 0.738 {+/-} 0.078. AbAffinity maintains meaningful performance on stricter PDB-disjoint and antigen sequence-identity splits, and held-out complexes. Evaluation on external natural-complex benchmarks further supports consistent transfer. Partner-shuffling, attribution and uncertainty analyses support partner-conditioned prediction and biologically plausible residue-level hypotheses. AbAffinity provides a lightweight, explainable sequence-first framework for antibody triage when structural information is limited or unavailable.",
  "abstract_shown": true,
  "affiliations": [
    "Shiv Nadar Institution of Eminence (Deemed to be University), Delhi-NCR"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "H. Singh"
    },
    {
      "name": "A. Malhotra"
    },
    {
      "name": "S. P. Srivastava"
    },
    {
      "affs": [
        0
      ],
      "name": "R. K. SINGH"
    },
    {
      "name": "R. Gorantla"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3tptyr2k34nxa.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.06.19.733375",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.06.19.733375v2.full",
  "id": "3tptyr2k34nxa",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.06.19.733375v2",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7165474119",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.06.19.733375v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3tptyr2k34nxa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:56Z",
      "native_id": "10.64898/2026.06.19.733375",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.06.19.733375v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Antibody-Antigen Affinity Prediction with Chain-Aware Protein Language Modeling",
  "title_text": "Antibody-Antigen Affinity Prediction with Chain-Aware Protein Language Modeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:56Z",
  "url": "https://research.draconitic.com/paper/3tptyr2k34nxa",
  "venue": "bioRxiv",
  "versions": []
}