Scholarlink

<p>Mass-based filtering significantly reduces the peptide candidate pool for subsequent scoring in database search algorithms. While useful, filtering based on one property may lead to exclusion of non-abundant spectra and uncharacterized peptides – potentially exacerbating the <i>streetlight</i> effect. Here we present <i>ProteoRift</i>, a novel attention and multitask deep-network, which can <i>predict</i> multiple peptide properties (length, missed cleavages, and modification status) directly from spectra 77.8% of the time. Integrating ProteoRift into an end-to-end pipeline significantly reduces the search space compared to mass-only filtering. This delivers 8x to 12x speedups while maintaining peptide deduction accuracy comparable to established algorithmic techniques. We also developed uncertainty estimation metrics, which can distinguish between in-distribution and out-of-distribution data (ROC-AUC 0.99) and predict high-scoring mass spectra against the correct peptide (ROC-AUC 0.94). These models and metrics are integrated in an end-to-end pipeline available at <a href="https://github.com/pcdslab/ProteoRift">https://github.com/pcdslab/ProteoRift</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

End-to-end deep attention-based multitask pipeline for predicting uncertainty-quantified peptide properties from mass spectrometry data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月13日

查看全文
  • Usman Tariq,
  • Bilal Shabbir,
  • Fahad Saeed

摘要

Mass-based filtering significantly reduces the peptide candidate pool for subsequent scoring in database search algorithms. While useful, filtering based on one property may lead to exclusion of non-abundant spectra and uncharacterized peptides – potentially exacerbating the streetlight effect. Here we present ProteoRift, a novel attention and multitask deep-network, which can predict multiple peptide properties (length, missed cleavages, and modification status) directly from spectra 77.8% of the time. Integrating ProteoRift into an end-to-end pipeline significantly reduces the search space compared to mass-only filtering. This delivers 8x to 12x speedups while maintaining peptide deduction accuracy comparable to established algorithmic techniques. We also developed uncertainty estimation metrics, which can distinguish between in-distribution and out-of-distribution data (ROC-AUC 0.99) and predict high-scoring mass spectra against the correct peptide (ROC-AUC 0.94). These models and metrics are integrated in an end-to-end pipeline available at https://github.com/pcdslab/ProteoRift.