Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network.
Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network.
复制标题
DOI：
10.1021/acs.analchem.9b04867
复制
发表时间：
2020-03-17
影响因子：
7.4
通讯作者：
Tang H
中科院分区：
文献类型：
--
作者：
Liu K;Li S;Wang L;Ye Y;Tang H
从多肽序列中预测串联质谱图的能力可以显著提高我们对多肽裂解过程的理解，并可以改进蛋白质组学中的多肽鉴定。然而，目前预测高能碰撞解离(HCD)谱的方法仅限于预测预期离子类型的强度，即a/b/c/x/y/z离子及其中性损耗导数(称为主干离子)。实际上，主链离子只占HCD谱总离子强度的70%，这表明许多强离子被电流预报器忽略了。在本文中，我们提出了一种深度学习方法，可以直接从多肽序列预测完整的光谱(包括主干和非主干离子)。我们没有对预测哪种离子做任何假设或期望，而是预测了所有可能的m/z的强度。训练这个模型不需要对碎片离子的注释，也不需要任何关于碎片规则的先验知识。我们的分析表明，预测的2+和3+HCD光谱与实验光谱高度相似，平均全谱余弦相似度分别为0.820(±0.088)和0.786(±0.085)，非常接近实验复制光谱之间的相似性。相比之下，性能最好的纯主干模型只能在2+和3+光谱的平均相似度分别低于0.75和0.70以下。此外，我们开发了一种用于预测训练样本不足的光谱的多任务学习(MTL)方法，这使得我们的模型能够准确地预测电子转移解离(ETD)谱和较少丰度电荷(1+和4+)的HCD谱。
The ability to predict tandem mass (MS/MS) spectra from peptide sequences can significantly enhance our understanding of the peptide fragmentation process and could improve peptide identification in proteomics. However, current approaches for predicting high-energy collisional dissociation (HCD) spectra are limited to predict the intensities of expected ion types, i.e., the a/b/c/x/y/z ions and their neutral loss derivatives (referred to as backbone ions). In practice, backbone ions only account for < 70% of total ion intensities in HCD spectra, indicating many intense ions are ignored by current predictors. In this paper, we present a deep learning approach that can predict the complete spectra (both backbone and non-backbone ions) directly from peptide sequences. We made no assumptions or expectations on which kind of ions to predict but instead predicting the intensities for all possible m/z. Training this model needs no annotations of fragment ion nor any prior knowledge of the fragmentation rules. Our analyses show that the predicted 2+ and 3+ HCD spectra are highly similar to the experimental spectra, with average full-spectrum cosine similarities of 0.820 (±0.088) and 0.786 (±0.085), respectively, very close to the similarities between the experimental replicated spectra. In contrast, the best-performed backbone only models can only achieve an average similarity below 0.75 and 0.70 for 2+ and 3+ spectra, respectively. Furthermore, we developed a multi-task learning (MTL) approach for predicting spectra of insufficient training samples, which allows our model to make accurate predictions for electron transfer dissociation (ETD) spectra and HCD spectra of less abundant charges (1+ and 4+).
登录
查看更多内容
DOI：
10.1093/bioinformatics/btn189
发表时间：
2008-07-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Klammer AA;Reynolds SM;Bilmes JA;MacCoss MJ;Noble WS
通讯作者：
Noble WS
影响因子：
5.8
作者：
Degroeve, Sven;Martens, Lennart
通讯作者：
Martens, Lennart
影响因子：
2
作者：
Liu J;Bell AW;Bergeron JJ;Yanofsky CM;Carrillo B;Beaudrie CE;Kearney RE
通讯作者：
Kearney RE
影响因子：
7.4
作者：
Li, Sujun;Arnold, Randy J.;Tang, Haixu;Radivojac, Predrag
通讯作者：
Radivojac, Predrag
影响因子：
3.4
作者：
Shao, Wenguang;Zhu, Kan;Lam, Henry
通讯作者：
Lam, Henry