NovoCRF：基于前体质量格的全局归一化从头肽测序方法
NovoCRF: Globally Normalized De Novo Peptide Sequencing on a Prefix-Mass Lattice
一个只有 31 万参数的 CRF 模型，肽测序准确率超过 Casanovo v5，速度快 55 倍，CPU 就能跑，做蛋白质谱的分析师可以看看。
NovoCRF 是一个条件随机场（CRF）模型，以 prefix mass 作为状态，路径精确限定在前体质量 ±0.06 Da 内的所有肽上，据作者称这是首个对所有质量可行肽做精确全局归一化训练的从头测序方法。整个软件包含 precursor mass finder、CRF 的精确 k-best 解码和两个 BiGRU 重排器三个模块，模型仅 310k 参数，训练约 17 GPU 小时。在 2026 年发表的 7 个 DDA 数据集（126,262 张标注谱图）上，NovoCRF 的平均肽召回率 42.4%，高于 Casanovo v5 五束搜索的 39.1%；氨基酸召回率 64.0% 对 53.1%。推理速度达 1,746 谱图/秒（18 CPU 线程），是 Casanovo GPU 吞吐的 55 倍。它还能按精确质量搜索训练时未见的修饰，在狮子骨样本中找到 32.1% 的羟脯氨酸肽。
NovoCRF: Globally Normalized De Novo Peptide Sequencing on a Prefix-Mass Lattice
De novo peptide sequencing has moved from dynamic programming over hand-designed or generative scores to large transformers that learn the task end to end. We present NovoCRF, a conditional random field (CRF) whose states are prefix masses, so that its paths are exactly the peptides within +/-0.06 Da of the precursor mass. A small network scores each edge from physics-derived ion-match features and is trained with its scores globally normalized over all mass-feasible peptides. To our knowledge, NovoCRF is the first de novo method trained with exact normalization over all mass-feasible peptides. Our software has three modules, each with exactly one job: a precursor mass finder recovers the accurate precursor mass from MS1, the CRF finds the peptides that fit the precursor mass by exact k-best decoding, and two BiGRU rerankers add sequence context and internal-fragment evidence. The model has 310k parameters and trains in about 17 GPU-hours. On seven held-out data-dependent acquisition datasets published in 2026 (126,262 labeled spectra), NovoCRF's mean peptide recall is 42.4%, against 39.1% for Casanovo v5 with five beams, and its amino-acid recall 64.0% against 53.1%, at 1,746 spectra/s on 18 CPU threads, 55x Casanovo's throughput on a GPU. Split by fragment evidence, NovoCRF leads on labels with up to three peptide bonds without a b or y ion, and Casanovo only beyond. NovoCRF can also search modifications it was never trained on at their exact mass: it finds 32.1% of the hydroxyproline peptides of a lion bone sample.