EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

When multimodal fusion fails: contrastive alignment as a necessary stabilizer for TCR–peptide binding prediction

Cong Qi iD, Wenbo Wang, Hanzhang Fang, Zhi Wei iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Cong Qi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, United States. Hauptthemen laut MEDLINE: Receptors, Antigen, T-Cell, Peptides, Sequence Alignment, Computational Biology. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Multimodal learning is often assumed to improve predictive performance by combining complementary views, yet in biological applications auxiliary modalities are frequently imperfect, incomplete, or derived from upstream predictors and heuristics. We study this issue in TCR–peptide binding prediction, where sequence embeddings from pretrained protein language models are strong and transferable, but structure-derived residue graphs must be built from predicted folds and discretized contacts. These structural views can therefore be noisy, inconsistent across proteins, and sensitive to modeling choices, making them difficult to optimize jointly with sequence features. In this setting, naive sequence + graph fusion can destabilize training and degrade generalization, falling below a sequence-only baseline when supervision is scarce or contacts are noisy. This motivates a practical goal: use imperfect structural information when it helps, without sacrificing stability when it does not. Results We introduce TRACE, a lightweight framework that encodes each entity (TCR and peptide) with parallel sequence (frozen ESM-2) and residue-graph (GNN) towers, then applies CLIP-style intra-entity contrastive alignment before interaction modeling. The alignment encourages modality-consistent representations for the same biological entity, preventing noisy graph signals from dominating fusion. We evaluate under a leakage-controlled TCHard RN protocol with pair-disjoint splits, training-only model selection, and exclusion of negative-sampling metadata that otherwise trivially inflates AUROC. In this setting the task is near chance for all methods, and we do not claim state-of-the-art accuracy; our contribution is the failure-mode analysis, the alignment stabilizer, and the audited protocol itself. Among matched baselines TRACE attains the best mean AUROC (0.578±0.033 over five folds), and an ablation shows that intra-entity alignment acts as a stabilizer: it gives a small but consistent full-data gain (better on 4 of 5 folds), stays robust under substantial graph-edge corruption, and prevents collapse toward chance under limited supervision (+0.05 AUROC at 10%–20% of labels), the regime where unconstrained fusion fails. How modalities are integrated, and how carefully they are evaluated, matters more than how many are used. Availability and implementation Code is available at https://github.com/MineSelf2016/TRACE and archived at https://doi.org/10.5281/zenodo.20635593. Data are available at https://doi.org/10.6084/m9.figshare.31991007.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Receptors, Antigen, T-CellPeptidesSequence AlignmentComputational BiologyProtein BindingAlgorithms

Substanzen

Receptors, Antigen, T-CellPeptides

Autor:innen und Institutionen

  • Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, United States.
  • Department of Computer Science, Hamilton College, Clinton, NY 13323, United States.

ORCID-Profile: Cong Qi, Zhi Wei

Förderung

  • NIGMS NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Qi, C., Wang, W., Fang, H., & Wei, Z. (2026). When multimodal fusion fails: contrastive alignment as a necessary stabilizer for TCR–peptide binding prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag573

Vancouver

Qi C, Wang W, Fang H, Wei Z. When multimodal fusion fails: contrastive alignment as a necessary stabilizer for TCR–peptide binding prediction. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag573

BibTeX
@article{Qi2026,
  author = {Qi, Cong and Wang, Wenbo and Fang, Hanzhang and Wei, Zhi},
  title = {When multimodal fusion fails: contrastive alignment as a necessary stabilizer for TCR–peptide binding prediction},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag573}
}
Kostenlos starten →