Motivation

The discrimination ability of score functions to separate correct from incorrect peptide-spectrum matches in database-searching-based spectrum identification are hindered by many superfluous peaks belonging to unexpected fragmentation ions or by the lacking peaks of anticipated fragmentation ions.

Results

Here, we present a new method, called BoltzMatch, to learn score functions using a particular stochastic neural networks, called restricted Boltzmann machines, in order to enhance their discrimination ability. BoltzMatch learns chemically explainable patterns among peak pairs in the spectrum data, and it can augment peaks depending on their semantic context or even reconstruct lacking peaks of expected ions during its internal scoring mechanism. As a result, BoltzMatch achieved 50% and 33% more annotations on high- and low-resolution MS2 data than XCorr at a 0.1% false discovery rate in our benchmark; conversely, XCorr yielded the same number of spectrum annotations as BoltzMatch, albeit with 4-6 times more errors. In addition, BoltzMatch alone does yield 14% more annotations than Prosit (which runs with Percolator), and BoltzMatch with Percolator yields 32% more annotations than Prosit at 0.1% FDR level in our benchmark.

Availability

BoltzMatch is freely available at: https://github.com/kfattila/BoltzMatch

Supporting information

Supplementary materials are available at Bioinformatics Online.

中文翻译：

---

在shot弹枪蛋白质组学中使用随机神经网络注释串联质谱数据。

动机

在基于数据库搜索的光谱识别中，评分函数区分正确肽段和错误肽段的正确性的区分能力受到许多属于意外碎片离子的多余峰或缺少预期碎片离子的干扰。

结果

在这里，我们提出了一种称为BoltzMatch的新方法，该方法使用特定的随机神经网络（称为受限Boltzmann机器）来学习评分函数，以增强其判别能力。BoltzMatch在光谱数据中的峰对之间学习化学上可解释的模式，它可以根据其语义环境来增强峰，甚至可以在其内部评分机制中重建缺少预期离子的峰。结果，在我们的基准测试中，BoltzMatch在X2分辨率上的误发现率比XCorr高50％，在X2R和低分辨率MS2数据上分别增加了33％。相反，XCorr产生了与BoltzMatch相同数量的频谱注释，尽管出现了4-6倍的错误。此外，与Prosit（与Percolator一起运行）相比，仅BoltzMatch就能产生14％的注释，

可用性

BoltzMatch可从以下网址免费获得：https：//github.com/kfattila/BoltzMatch

配套信息

补充材料可从在线生物信息学获得。