DelPi Learns Generalizable Peptide-Signal Correspondence for Mass Spectrometry-Based Proteomics
Park, J.; Kim, K.; Kang, U.-B.; Kim, S.
Show abstract
Peptide identification in mass spectrometry-based proteomics has traditionally relied on handcrafted features or simplified probabilistic approaches that limit the interpretation of structured peptide evidence. We present DelPi, an open-source peptide identification framework that learns generalizable peptide-signal correspondence from raw spectra through self-supervised pre-training followed by task-specific fine-tuning. With model distillation enabling practical deployment, DelPi expands the interpretation of peptide evidence across data-independent and data-dependent acquisition while maintaining robust false discovery control.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model 98%
- AlphaPeptDeep: A modular deep learning framework to predict peptide properties for proteomics 98%
- Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning 97%
Similar papers in this journal
- To fly, or not to fly, that is the question: A deep learning model for peptide detectability prediction in mass spectrometry 97%
- Inserting Pre-Analytical Chromatographic Priming Runs Significantly Improves Targeted Pathway Proteomics With Sample Multiplexing 96%
- Increasing the Throughput and Reproducibility of Activity-Based Proteome Profiling Studies with Hyperplexing and Intelligent Data Acquisition 96%
Similar papers in this journal
- Deep Learning Prediction of Glycopeptide Tandem Mass Spectra Powers Glycoproteomics 96%
- Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data 94%
- Deep Domain Adversarial Neural Network for the Deconvolution of Cell Type Mixtures in Tissue Proteome Profiling 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.