ProTok 用多码本量化统一蛋白质序列、结构与功能三种模态
ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization
一篇蛋白质领域的 tokenizer 论文，三种模态共用一套离散词表，28 个测试切分里 21 个拿第一，还能联合生成骨架和序列，做蛋白质设计的可以看看。
ProTok 是一个统一蛋白质 tokenizer，通过模块化多码本量化和 modality dropout，把序列、结构、功能注释映射进同一离散词表，单一 checkpoint 支持任意模态子集推理。在 StructTokenBench 的 14 个任务、28 个测试切分上，ProTok 平均排名第一，21 个切分居首，27 个进入前二。重建质量上，其 token 在 CATH 4.2 上达到 0.939 lDDT。零样本功能检索方面，其结构 token 在 CATH、Enzyme Commission、Gene Ontology 标签层级上领先所有基线结构 tokenizer。用 ProTok token 从零训练的小型语言模型可联合生成骨架和序列，52% 采样骨架可设计，参数量对齐的 GeoBPE 基线为 21%。
ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization
Protein sequence, structure, and functional annotations each capture complementary aspects of protein biology, yet existing tokenizers encode each modality independently, limiting the expressiveness of discrete protein representations. We present ProTok, a unified protein tokenizer that maps all three modalities into a modular discrete vocabulary via product quantization with per-modality codebook groups and modality dropout. A single ProTok checkpoint supports flexible inference from any modality subset without retraining. On seven StructTokenBench benchmarks spanning 14 tasks and 28 test splits, ProTok achieves an average rank of 1.4 across all structure-only tokenizers, placing first on 21 splits and among the top two on 27 of the 28. These gains come without sacrificing reconstruction: ProTok's tokens reach 0.939 lDDT on CATH 4.2, showing that multi-codebook quantization and multi-modal training yield tokens that are both reconstructable and informative. ProTok's structure tokens further lead all baseline structure tokenizers on zero-shot functional retrieval across CATH, Enzyme Commission, and Gene Ontology label hierarchies. The vocabulary also supports generation: a compact language model trained from scratch over ProTok tokens jointly generates backbone and sequence, with 52% of sampled backbones designable versus 21% for a parameter-matched GeoBPE baseline. ProTok shows that structure, sequence, and function can share one discrete vocabulary, motivating protein language models that reason over a unified token stream.
