Bo Wen

The paper develops a deep learning-enhanced fragment ion indexing method to reduce memory usage in tandem mass spectrometry searches while maintaining search accuracy and speed.

This study identifies Abi-1-S323 phosphorylation as a biomarker for DNA repair states and treatment response in cancers, showing its role in regulating radiosensitivity through Rac1 and CHK1 signaling.

CasanovoGUI provides a user-friendly desktop interface for Casanovo, a deep learning model for de novo peptide sequencing, simplifying setup and result interpretation.

Bromo, a pairwise transformer, ranks a protein's peptide precursors by expected mass spectrometry response, beating XGBoost, PREGO and PeptideRanger on held-out yeast data, and can be fine-tuned per instrument.

The paper introduces a label-free quantification feature in the Crux toolkit, demonstrating improved efficiency and accuracy compared to existing methods.

This study revisits resonance-excitation collision-induced dissociation (reCID) for DIA proteomics, showing it can achieve performance comparable to HCD with optimized settings and libraries.

Carafe2 generates high-quality in silico spectral libraries for timsTOF DIA proteomics by fine-tuning deep learning models on DIA data, outperforming DDA-trained models in multiple applications.

The paper identifies three novel diagnostic biomarkers for osteoporosis in women using bioinformatics analysis of gene expression datasets.

The paper introduces TMT-Integrator, a tool for analyzing isobaric proteomic data, showing improved performance in protein and phosphorylation site quantification compared to existing tools.

The paper improves Casanovo, a deep learning de novo peptidesequencer, by enhancing interpretability, generalizing its use in database search, speeding up performance, and adding tools for adoption and result interpretation.

Puget predicts gene expression across cell types using sequence and Hi-C data, improving generalization to new biosamples and species.

Carafe generates high-quality in silico spectral libraries for DIA proteomics by training deep learning models directly on DIA data, improving fragment ion intensity prediction and peptide detection.

This paper evaluates FDR control in mass spectrometry proteomics tools, finding that none consistently control FDR at the peptide level in DIA data, especially for single-cell datasets.

This paper develops chemotherapy-specific predictors for triple-negative breast cancer using patient-derived xenografts and multi-omic data, achieving high AUROC scores for response prediction.

The paper re-purposes a machine learning model for de novo peptide sequencing as a score function for database search, improving detection power over existing methods.

This paper introduces a transformer-based model called Cascadia for de novo sequencing of data-independent acquisition mass spectrometry data, achieving state-of-the-art performance.

DeepRescore2 improves phosphopeptide identification using deep learning, leading to more phosphosites detected and new biological insights in liver cancer.

The paper investigates how common genetic haplotypes affect proteomic search results and identifies multi-variant peptides detectable by mass spectrometry.