ProTok：基于模块化多码本量化的统一蛋白质分词器
ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization
AI总结：
ProTok是一种统一蛋白质分词器，通过模块化多码本量化将蛋白质的序列、结构、功能三种模态映射到同一离散词汇表，在StructTokenBench基准上表现优异，其生成的标记兼具可重构性与信息性，还能提升蛋白质主链和序列的生成性能。
摘要：
蛋白质的序列、结构和功能注释分别捕捉了蛋白质生物学的互补方面，但现有的分词器对每种模态进行独立编码，限制了离散蛋白质表示的表达能力。我们提出了ProTok，一种统一的蛋白质分词器，它通过带模态专属码本组和模态弃权（不执行）的乘积量化，将所有三种模态映射到模块化离散词汇表。单个ProTok检查点支持对任意模态子集进行灵活推理，无需重新训练。在涵盖14个任务和28个测试拆分的7个StructTokenBench基准上，ProTok在所有仅结构分词器中平均排名为1.4，在21个拆分中排名第一，在28个拆分中的27个中排名前两位。这些提升并未牺牲重构能力：ProTok的标记在CATH 4.2上达到0.939的lDDT值，表明多码本量化和多模态训练产生的标记兼具可重构性和信息性。ProTok的结构标记在CATH、酶委员会和基因本体论标签层次结构上的零样本功能检索中，领先所有基线结构分词器。该词汇表还支持生成：一个从零开始训练的紧凑语言模型，基于ProTok标记联合生成主链和序列，采样的主链可设计比例为52%，而参数匹配的GeoBPE基线仅为21%。ProTok表明结构、序列和功能可以共享一个离散词汇表，为在统一标记流上进行推理的蛋白质语言模型提供了动力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
