Mathias Wilhelm

PepPr: De Novo peptide sequencing with peptide priors

PepPr improves peptide sequencing by integrating peptide priors, enhancing reference and variant peptide identification while maintaining discovery flexibility.

ChemIntelligence Enables Antibody-Free, Ultra-Low-Input Profiling of Lysine Lactylation and Diverse Acyl-Proteomes

ChemIntelligence enables antibody-free, ultra-low-input profiling of lysine lactylation and diverse acyl-proteomes using chemical derivatization and computational methods.

DORSSAA: Drug-target interactOmics Resource based on Stability/Solubility Alteration Assay

DORSSAA provides a platform for analyzing stability and solubility alteration data to identify drug-protein interactions and therapeutic targets.

GAP-MS: Automated validation of gene predictions using integrated mass spectrometry evidence

GAP-MS improves gene prediction accuracy in plant genomes by integrating mass spectrometry evidence, identifying hundreds of previously unannotated protein-coding loci.

Shifting Beyond Classical Drug Synergy in Combinatorial Therapy through Solubility Alterations

This paper introduces CoPISA, a proteomics workflow that identifies combination-specific protein targets in AML, revealing conjunctional targeting mechanisms beyond classical drug synergy.

High-throughput chemical proteomics workflow for profiling protein citrullination dynamics

The paper develops a chemical proteomics workflow to profile protein citrullination dynamics, achieving high sensitivity and throughput in detecting citrullinated peptides across biological systems.

Modanovo: A Unified Model for Post-Translational Modification-Aware de Novo Sequencing Using Experimental Spectra from In Vivo and Synthetic Peptides

Modanovo is a de novo peptide sequencing model that handles post-translational modifications, outperforming existing methods and complementing database searches in phosphoproteomics.

Decoding isozyme-specific substrate recognition in protein arginine deiminases by proteome-wide citrullination mapping

The paper maps isozyme-specific substrate recognition of PAD1-4 by identifying citrullination sites across the proteome, revealing distinct sequence preferences and key residues determining substrate specificity.

Systematic evaluation of peptide property predictors with explainable AI technique SHAP

The paper evaluates peptide property predictors using SHAP to explain model predictions and finds strong correlations with known amino acid indices.

Learning the Unseen: Data-Augmented Deep Learning for PTM Discovery with Prosit-PTM

This paper introduces Prosit-PTM, a deep learning model for PTM discovery that improves zero-shot prediction using a synthetic dataset and chemically-informed encoding.

Comparative Performance of Scribe and Database Search Engines in Metaproteomic Profiling of a Ground-Truth Microbiome Dataset

This study compares Scribe and database search engines in metaproteomic analysis of a ground-truth microbiome dataset, finding Scribe detects more proteins and quantifies microbial composition more accurately.

Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra

This paper introduces Pairwise Attention, a modified transformer encoder for de novo peptide sequencing from MS2 spectra, improving precision by 12.7% on a nine-species benchmark.

Integrating Alternative Fragmentation Techniques into Standard LC-MS Workflows Using a Single Deep Learning Model Enhances Proteome Coverage

The paper develops a deep learning model that integrates multiple fragmentation techniques into standard LC-MS workflows, improving proteome coverage and identification rates.

From Hype to Health Check: Critical Evaluation of Drug Response Prediction Models with DrEval

This paper evaluates drug response prediction models and finds that deep learning models perform similarly to simple baselines, highlighting issues in current model evaluation practices.

To fly, or not to fly, that is the question: A deep learning model for peptide detectability prediction in mass spectrometry

Pfly predicts peptide detectability in mass spectrometry using a deep learning model trained on synthetic and biological data, offering customizable classification for different experimental conditions.

Unifying the analysis of bottom-up proteomics data with CHIMERYS

CHIMERYS deconvolves chimeric spectra in proteomic data, enabling unified analysis across DDA, DIA, and PRM experiments by accurately identifying and quantifying multiple peptides per spectrum.

Deep Learning Enhances Precision of Citrullination Identification in Human and Plant Tissue Proteomes

The paper introduces a deep learning model to improve citrullination site identification in proteomes, achieving high precision and sensitivity in human and plant tissues.

PTMNavigator: Interactive Visualization of Differentially Regulated Post-Translational Modifications in Cellular Signaling Pathways

PTMNavigator visualizes differentially regulated PTMs in cellular pathways using phosphoproteomics data to enhance pathway enrichment analysis and drug response visualization.

Prosit-XL: enhanced cross-linked peptide identification by accurate fragment intensity prediction to study protein-protein interactions and protein structures

Prosit-XL improves cross-linked peptide identification by predicting fragment intensities, enhancing protein-protein interaction discovery and interactome mapping.

Network medicine-based epistasis detection in complex diseases: ready for quantum computing

The paper introduces NeEDL, a network medicine-based method for detecting higher-order epistatic interactions in complex diseases, showing improved statistical significance and applicability across eight diseases.

IS-PRM-based peptide targeting informed by long-read sequencing for alternative proteome detection

The paper introduces LRP-IS-PRM, a method using long-read RNAseq to inform targeted proteomics with IS-PRM, identifying five new protein isoforms in human stem cells.

Koina: Democratizing machine learning for proteomics research

Koina provides an open-source, accessible ML/DL prediction service for proteomics, improving integration with existing tools like FragPipe.

Fragment ion intensity prediction improves the identification rate of non-tryptic peptides in timsTOF

The paper trains a deep learning model to predict fragment ion intensities, improving immunopeptide identification rates using timsTOF instruments.

Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing

This paper introduces Spectralis, a deep learning method for de novo peptide sequencing that improves sensitivity and precision in tandem mass spectrometry.

A proteomics sample metadata representation for multiomics integration, and big data analysis.

The paper introduces a standardized metadata format for proteomics datasets to improve reusability and integration across public repositories.

Universal Spectrum Explorer: A standalone (web-)application for cross-resource spectrum comparison

The paper introduces a web-based tool for cross-resource peptide spectrum comparison and visualization, with a focus on integration and retrieval from spectral databases.

Generating high-quality libraries for DIA-MS with empirically-corrected peptide predictions

This paper introduces a method to generate high-quality DIA-MS libraries using peptide predictions and empirical refinement, demonstrating its effectiveness in non-model organisms and non-canonical databases.

A deep proteome and transcriptome abundance atlas of 29 healthy human tissues

The paper creates a proteome and transcriptome atlas of 29 human tissues, revealing differences in mRNA-protein abundance and challenges in proteogenomics.