Dataset Information

Enhancing Peptide Identification in Metaproteomics through Curriculum Learning in Deep Learning

ABSTRACT: Metaproteomics offers a powerful window into the active functions of microbial communities, but accurately identifying peptides remains challenging due to the size and incompleteness of protein databases derived from metagenomes. These databases often contain vastly more sequences than those from single organisms, creating a computational bottleneck in peptide-spectrum match (PSM) filtering. Here we present WinnowNet, a deep learning–based method for PSM filtering, available in two versions: one using transformers and the other convolutional neural networks. Both variants are designed to handle the unordered nature of PSM data and are trained using a curriculum learning strategy that moves from simple to complex examples. WinnowNet consistently achieves more true identifications at equivalent false discovery rates compared to leading tools, including Percolator, MS$^2$Rescore, and DeepFilter, and outperforms filters integrated into popular analysis pipelines. It also uncovers more gut microbiome biomarkers related to diet and health, highlighting its potential to support advances in personalized medicine

INSTRUMENT(S):

ORGANISM(S): Soil Metagenome Human Gut Metagenome Marine Metagenome

SUBMITTER: Shichao Feng

LAB HEAD: Xuan Guo

PROVIDER: PXD067277 | Pride | 2025-10-20

REPOSITORIES: Pride

ACCESS DATA

Dataset's files

Source:

			Action	DRS
	Marine_shuffled.fasta	Fasta
	Mock_Comm_RefDB_V3_shuffled.fasta	Fasta
	OSU_D2_FASP_Elite_02262014_01.pepXML	Pepxml
	OSU_D2_FASP_Elite_02262014_01.raw	Raw
	OSU_D2_FASP_Elite_02262014_01.txt	Txt

Items per page:

1 - 5 of 160

Publications

Enhancing peptide identification in metaproteomics through curriculum learning in deep learning.

Feng Shichao S Zhang Bailu B Wang Huan H Xiong Yi Y Tian Athena A Yuan Xiaohui X Pan Chongle C Guo Xuan X

Nature communications 20251008 1

Metaproteomics offers a powerful window into the active functions of microbial communities, but accurately identifying peptides remains challenging due to the size and incompleteness of protein databases derived from metagenomes. These databases often contain vastly more sequences than those from single organisms, creating a computational bottleneck in peptide-spectrum match (PSM) filtering. Here we present WinnowNet, a deep learning-based method for PSM filtering, available in two versions: one ...[more]

PMID: 41062510

Similar Datasets

Project description:All large-scale LC-MS/MS post-translational methylation site discovery experiments require methylpeptide spectrum matches (methyl-PSMs) to be identified at acceptably low false discovery rates (FDRs). To meet estimated methyl-PSM FDRs, methyl-PSM filtering criteria are often determined using the target-decoy approach. The efficacy of this methyl-PSM filtering approach has, however, yet to be thoroughly evaluated. Here we conduct a systematic analysis of methyl-PSM FDRs across a range of sample preparation workflows (each differing in their exposure to the alcohols methanol and isopropanol) and mass spectrometric instrument platforms (each employing a different mode of MS/MS dissociation). Through 13CD3-methionine labeling (heavy-methyl SILAC) of S. cerevisiae cells and in-depth manual data inspection, accurate lists of true positive methyl-PSMs were determined, allowing methyl-PSM FDRs to be compared to target-decoy approach-derived methyl-PSM FDR estimates. These results show that global FDR estimates produce extremely unreliable methyl-PSM filtering criteria; we demonstrate that this is an unavoidable consequence of the high number of amino acid combinations capable of producing peptide sequences that are isobaric to methylated peptides of a different sequence. Separate methyl-PSM FDR estimates were also found to be unreliable due to prevalent sources of false positive methyl-PSMs that produce high peptide identity score distributions. Incorrect methylation site localizations, peptides containing cysteinyl-S-β-propionamide, and methylated glutamic or aspartic acid residues can partially, but not wholly, account for these false positive methyl-PSMs. Together these results indicate that the target-decoy approach is an unreliable means of estimating methyl-PSM FDRs and methyl-PSM filtering criteria. We suggest that orthogonal methylpeptide validation (e.g. heavy-methyl SILAC or its offshoots) should be considered a prerequisite for obtaining high confidence methyl-PSMs in large-scale LC-MS/MS methylation site discovery experiments, and make recommendations on how to reduce methyl-PSM FDRs in samples not amenable to heavy isotope labeling.

Project description:In gas chromatography-mass spectrometry-based untargeted metabolomics, metabolites are identified by comparing mass spectra and chromatographic retention time with reference databases or standard materials. In that sense, machine learning has been used to predict the retention time of metabolites lacking reference data. However, the retention time prediction of trimethylsilyl derivatives of metabolites, typically analyzed in untargeted metabolomics using gas chromatography, has been poorly explored. Here, we provide a rationalized framework for machine learning-based retention time prediction of trimethylsilyl derivatives of metabolites in gas chromatography. We compared different machine learning paradigms, in addition to exploring the influence of the computational molecular structure representation to train the prediction models: fingerprint class and fingerprint calculation software. Our study challenged predicted retention time when using chemical ionization and electron impact ionization sources in simulated and real cases, demonstrating a good correct identity ranking capability by machine learning, despite observing a limited false identity filtering power in cases where a spectrum or a monoisotopic mass match to multiple candidates. Specifically, machine learning prediction yielded median absolute and relative retention index (relative retention time) errors of 37.1 retention index units and 2%, respectively. In addition, fingerprint class and fingerprint calculation software, as well as the molecular structural similarity between the training and test or real case sets, showed to be critical modulators of the prediction performance. Finally, we leveraged the structural similarity between the training and test or real case set to determine the probability that the prediction error is below a specific threshold. Overall, our study demonstrates that predicted retention time can provide insights into the true structure of unknown metabolites by ranking from the most to the least plausible molecular identity, and sets the guidelines to assess the confidence in metabolite identification using predicted retention time data.