ProtAlign: Contrastive learning paradigm for Sequence and structure alignment

2026-03-06

AI Summary

Existing protein language models often neglect structural information, and conventional approaches struggle to effectively align sequence and structure representations. This work proposes a sequence–structure contrastive alignment framework that, for the first time, introduces contrastive learning to this task by constructing a shared embedding space to achieve consistent representations across modalities. Leveraging large-scale paired sequence–structure data, the method enables cross-modal retrieval and establishes interpretable sequence–structure correspondences. It significantly outperforms current state-of-the-art approaches on downstream tasks such as functional annotation and stability prediction, and efficiently retrieves structurally similar neighbors directly from sequence inputs.

Technology Category

• Machine Learning: Structured Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and structure separately, limiting the ability to exploit the alignment between the structure and protein sequence embeddings. In this paper, we introduce a sequence structure contrastive alignment framework, which learns a shared embedding space where proteins are represented consistently across modalities. By training on large-scale pairs of sequences and experimentally resolved or predicted structures, the model maximizes agreement between matched sequence structure pairs while pushing apart unrelated pairs. This alignment enables cross-modal retrieval (e.g., finding structural neighbors given a sequence), improves downstream prediction tasks such as function annotation and stability estimation, and provides interpretable links between sequence variation and structural organization. Our results demonstrate that contrastive learning can serve as a powerful bridge between protein sequences and structures, offering a unified representation for understanding and engineering proteins.

Problem

• protein sequence
• protein structure
• sequence-structure alignment
• multimodal representation
• contrastive learning

Innovation

• contrastive learning
• protein sequence-structure alignment
• shared embedding space
• cross-modal retrieval
• protein language models