Toward an Integrated Machine Learning Model of a Proteomics Experiment

2023/02/06 by Benjamin A. Neely, Viktoria Dorfer, Lennart Martens +15 · 1 voice · 3 citations
Chemistry · Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Proteomics Techniques and Applications #Cell Image Analysis Techniques #Machine Learning and Data Classification

paper · doi:10.1021/acs.jproteome.2c00711

openalex publication_date 2023/02/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In recent years machine learning has made extensive progress in modeling many aspects of mass spectrometry data. We brought together proteomics data generators, repository managers, and machine learning experts in a workshop with the goals to evaluate and explore machine learning applications for realistic modeling of data from multidimensional mass spectrometry-based proteomics analysis of any sample or organism. Following this sample-to-data roadmap helped identify knowledge gaps and define needs. Being able to generate bespoke and realistic synthetic data has legitimate and important uses in system suitability, method development, and algorithm benchmarking, while also posing critical ethical questions. The interdisciplinary nature of the workshop informed discussions of what is currently possible and future opportunities and challenges. In the following perspective we summarize these discussions in the hope of conveying our excitement about the potential of machine learning in proteomics and to inspire future research.

Citations

• An approach to correlate tandem mass spectral data of peptides with amino acid sequences in a protein database
• Global quantification of mammalian gene expression control
• DAMP Signaling is a Key Pathway Inducing Immune Modulation after Brain Injury
• Representation Learning: A Review and New Perspectives
• The Prevalence of Inappropriate Image Duplication in Biomedical Research Publications
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Denoising Diffusion Probabilistic Models
• Generative adversarial networks
• A review of uncertainty quantification in deep learning: Techniques, applications and challenges
• UniProt: the universal protein knowledgebase in 2021
• Highly accurate protein structure prediction with AlphaFold
• A single–cell type transcriptomics map of human tissues
• The PRIDE database resources in 2022: a hub for mass spectrometry-based proteomics evidences
• Detecting fabrication in large-scale molecular omics data
• Ensembl 2022
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• High-Resolution Image Synthesis with Latent Diffusion Models

Cited by

• The State of Peptide Detectability in Computational Proteomics and Guidelines for AI Applications
• Next-generation proteomics in medical laboratories: metrologically sound quantitative protein tests vs. innovative and personalized proteome patterns
• The PRIDE database at 20 years: 2025 update

Discussions

• See longer discussion in Neely et al. (doi.org/10.1021/acs....). [bsky, 1 points, 0 comments]

Related

• Discovery of Proteomics based on Machine learning
• Interpretation of the DOME Recommendations for Machine Learning in Proteomics and Metabolomics
• Foundation model for mass spectrometry proteomics
• ProteoBench: the community-curated platform for comparing proteomics data analysis workflows
• Instrumentation at the leading edge of proteomics