Skip to main navigation Skip to search Skip to main content

Contrastive learning unites sequence and structure in a global representation of protein space

  • Guy Yanai
  • , Gabriel Axel
  • , Liam M. Longo*
  • , Nir Ben-Tal*
  • , Rachel Kolodny*
  • *Corresponding author for this work
  • University of Haifa
  • Institute of Science Tokyo
  • Blue Marble Space Institute of Science

Research output: Contribution to journal › Article › peer-review

Abstract

Establishing a coherent mapping of the relationships among all known proteins is crucial for elucidating processes of protein emergence and evolution. Yet the capacity to fully capture relationships of protein similarity is complicated by the nonstraightforward interplay between sequence and structure; indeed, proteins with unrelated sequences can adopt similar structures, and, conversely, proteins with similar or identical sequences can manifest radically different structures. Here, we introduce Contrastive Learning Sequence–Structure (CLSS), a contrastive protein language model (PLM) trained to coembed sequence and structure information in a self-supervised manner, facilitating a holistic representation of protein relatedness. CLSS represents the structures and sequences of full domains and domain subsequences as vectors in the same high-dimensional latent space. We show that this approach yields meaningful shared representations, which recapitulate the extensive structure- and sequence-based knowledge encoded in human-curated hierarchical protein classification systems (ECOD and CATH). Moreover, the representations generated by CLSS outperform those generated by alternative state-of-the-art PLMs in downstream classification tasks. Notably, we show that even the far larger space of domain subsequences is successfully coembedded, establishing a PLM tailored to these evolutionarily meaningful objects. CLSS embeddings produce informative representations of the protein universe without further downstream processing, as we demonstrate by analyzing preferential associations between protein architectures and ligand types across protein space.

Original languageEnglish
Article numbere2532702123
JournalProceedings of the National Academy of Sciences of the United States of America
Volume123
Issue number32
DOIs
StatePublished - 11 Aug 2026

Funding

FundersFunder number
Minerva Foundation
Israel Science Foundation1764/21
Human Frontier Science ProgramRGEC29/2025

    Keywords

    • contrastive learning
    • maps of protein space
    • protein domains
    • protein sequence and structure
    • protein universe

    Fingerprint

    Dive into the research topics of 'Contrastive learning unites sequence and structure in a global representation of protein space'. Together they form a unique fingerprint.

    Cite this