Biology subjects

Claeys, T.

Publications and source records attributed to Claeys, T..

9 recordsLinked to original sources

bioRxiv2026

OmicsFM brings proteomics into the foundation model era

While foundation models have been shown to learn biological representations from large transcriptomic atlases, it remained unknown whether proteomics data allow the same. We here therefore introduce OmicsFM, a modality-agnostic transformer pretrained through masked abundance reconstruction on an unprecedented proteomics data corpus of 48,837 quality-filtered proteomics profiles from 1,397 reprocessed PRIDE projects. Interestingly, despite training on 14- to 93-fold fewer profiles than matched bulk- and single-cell transcriptomic models, respectively, our proteomics model rivals both. On held-out projects, OmicsFM attention networks recovered more molecular relationships than co-expression methods and existing single-cell foundation models across nine reference databases that reveal pathway-level organization. Sample-level embeddings preserved biological structure across independent studies, and its representations transferred successfully to cell-type classification, gene-essentiality prediction, and perturbation-response prediction, while consistently outperforming task-specific models. Moreover, our results show that proteomics and transcriptomics representations capture complementary biology. OmicsFM thus firmly establishes the possibility of training highly performant proteomics-based foundation models, and their importance in modelling and uncovering fundamental biology.

bioinformatics↗

bioRxiv2026

Discovery of non-canonical proteins through modification-aware proteogenomics

ShortThe SwissProt database contains a stable 20,418 human protein-coding genes and 42,541 human protein sequences. Ribo-Seq suggests about 7,000 additional, non-canonical Open Reading Frames (ORFs) are present in humans, though only a few of them are confirmed by Mass Spectrometry (MS). Detecting these proteins requires extensive database searches, increasing computational load and inflating False Discovery Rates (FDR). Using the ionbot search engine with the OpenProt database allows for reliable detection of non-canonical proteins while controlling FDR. Ionbot surpasses the Trans-Proteomics Pipeline (TPP) in reproducibility, identifying more peptides and proteins supported by multiple spectra. In addition, open modification searches yield better PSMs compared to closed searches. This work highlights the importance of employing cutting-edge search engines in non-canonical protein research, as well as the value of open modification search in correcting errors in non-canonical protein detection. LongO_ST_ABSBackgroundC_ST_ABSThe SwissProt database reports a quite stable 20,418 human protein-coding genes and 42,541 human protein sequences, figures that have remained stable. New techniques like Ribo-Seq indicate that approximately 7,000 additional, non-canonical Open Reading Frames (ORFs) are translated in humans, few of which have been confirmed by Mass Spectrometry (MS). Detecting these non-canonical proteins requires comprehensive database searches, which increase computational load and False Discovery Rate (FDR). Here, we use the open search engine ionbot in combination with the OpenProt proteogenomics database to reproducibly detect non-canonical proteins while maintaining a well-controlled FDR. ResultsCompared to the current gold standard, the Trans-Proteomics Pipeline (TPP), ionbot shows higher reproducibility, with a higher number of peptides and proteins supported by multiple spectra, and across multiple samples. We observe that PSMs from the open modification search against OpenProt have higher fragment ion intensity correlation compared to PSMs obtained from the closed search, or by only searching canonical proteins. ConclusionsIn this work, we show the potential for open modification searching to correct potential mistakes in non-canonical proteins detection by preventing modified canonical peptides or variants from being incorrectly identified as non-canonical peptides. We also highlight the importance of assessing the FDR of non-canonical identifications separately from canonical ones, as global FDR calculations are biased by the scarcity of non-canonical identifications in each dataset.

molecular biology↗

bioRxiv2026

Defining Quality Control Standards for Single-Cell Proteomics by Inter-Laboratory Benchmarking

Single-cell proteomics can quantify thousands of proteins from individual mammalian cells, yet the absence of community-wide quality control limits biological interpretability. Here, the HUPO Single Cell Initiative presents the first inter-laboratory single-cell proteomics benchmarking study across seven laboratories using standardized 384-well plates acquired on Orbitrap Astral and timsTOF Ultra2 instruments. Centralized analysis across six DIA software tools revealed that software choice impacts identification depth and quantitative accuracy more than instrument vendor. Multi-layered quality control enabled the detection of cell-leakage during sorting, LC misconfiguration, column degradation and site-specific pipetting failures. Inter-lab quantitative correlations were strongest between instruments of the same vendor relative to cross-platform comparisons. Sequential correction for plate identity and well position recovered clean cell-type separation for confident downstream differential expression analysis. This study provides a data-driven quality control framework spanning plate design to batch correction for reproducible single-cell proteomics across laboratories and platforms.

biochemistry↗

bioRxiv2025

ProteoBench: the community-curated platform for comparing proteomics data analysis workflows

Mass spectrometry (MS)-based proteomics is a well-established strategy for analyzing complex biological mixtures. Many MS instruments and data acquisition strategies are available, and the data they acquire differ substantially, thus requiring tailored analysis algorithms. Hence, many dedicated bioinformatics workflows are developed. These are in constant evolution, and the community lacks a centralized platform for comparing their performance. Here, we propose ProteoBench, a single platform that brings together software developers and software users to provide an ever-evolving comparison of state-of-the-art proteomics data processing tools. ProteoBench is an open-source resource that enables the community to evaluate data analysis workflows, develop benchmarking modules dedicated to specific comparisons, and discuss the best methods to compare software tools. The platform ensures that the benchmark evolves alongside advances in proteomics data analysis workflows. ProteoBench guides researchers towards the best-suited tool and parameters for their specific project and data according to their needs, and developers can test their newly developed tools or workflows privately, before adding them as public references. This community-driven effort will increase transparency and reproducibility between MS data analysis workflows, as well as facilitate the development and publication of software workflows in the field.

bioinformatics↗

bioRxiv2025

Limitations of de novo sequencing in resolving sequence ambiguity

De novo peptide sequencing enables peptide identification from fragmentation spectra without relying on sequence databases. However, incomplete spectra create ambiguity, making unambiguous identification challenging. Recent deep learning advances have produced numerous de novo models that predict sequences and refine peptide-spectrum matches under such conditions. Yet, their relative strengths, weaknesses, and ability to handle spectrum ambiguity remain unclear. Here, we benchmark eight state-of-the-art models on three publicly available proteomics datasets, comparing performance using established metrics and quantifying inter-model agreement. We assess post-processing approaches, including iterative refinement, rescoring, and reranking, for their ability to improve identification accuracy, and perform an error analysis to identify common mispredictions and their causes. Model performance varied, with considerable overlap of correct identifications. Post-processing yielded no or only modest improvements. Most sequencing errors were model-independent and driven by limited fragment ion coverage, a limitation also observed in database searches with large search spaces.

bioinformatics↗

bioRxiv2025

MLMarker: A machine learning framework for tissue inference and biomarker discovery

MLMarker is a machine learning tool that computes continuous tissue similarity scores for proteomics data, addressing the challenge of interpreting complex or sparse datasets. Trained on 34 healthy tissues, its Random Forest model generates probabilistic predictions with SHAP-based protein-level explanations. A penalty factor corrects for missing proteins, improving robustness for low-coverage samples. Across three public datasets, MLMarker revealed brain-like signatures in cerebral melanoma metastases, achieved high accuracy in a pan-cancer cohort, and identified brain and pituitary origins in biofluids. MLMarker provides an interpretable framework for tissue inference and hypothesis generation, available as a Python package and Streamlit app.

bioinformatics↗

bioRxiv2025

InstaNovo-P: A de novo peptide sequencing model for phosphoproteomics

Phosphorylation, a crucial post-translational modification (PTM), plays a central role in cellular signaling and disease mechanisms. Mass spectrometry-based phosphoproteomics is widely used for system-wide characterization of phosphorylation events. However, traditional methods struggle with accurate phosphorylated site localization, complex search spaces, and detecting sequences outside the reference database. Advances in de novo peptide sequencing offer opportunities to address these limitations, but have yet to become integrated and adapted for phosphoproteomics datasets. Here, we present InstaNovo-P, a phosphorylation specific version of our transformer-based InstaNovo model, fine-tuned on extensive phosphoproteomics datasets. InstaNovo-P significantly surpasses existing methods in phosphorylated peptide detection and phosphorylated site localization accuracy across multiple datasets, including complex experimental scenarios. Our model robustly identifies peptides with single and multiple phosphorylated sites, effectively localizing phosphorylation events on serine, threonine, and tyrosine residues. We experimentally validate our model predictions by studying FGFR2 signaling, further demonstrating that InstaNovo-P uncovers phosphorylated sites previously missed by traditional database searches. These predictions align with critical biological processes, confirming the models capacity to yield valuable biological insights. InstaNovo-P adds value to phosphoproteomics experiments by effectively identifying biologically relevant phosphorylation events without prior information, providing a powerful analytical tool for the dissection of signaling pathways.

bioinformatics↗

bioRxiv2022

Machine learning on large-scale proteomics data identifies tissue- and cell type-specific proteins

Using data from 183 public human data sets from PRIDE, a machine learning model was trained to identify tissue and cell-type specific protein patterns. PRIDE projects were searched with ionbot and tissue/cell type annotation was manually added. Data from physiological samples were used to train a Random Forest model on protein abundances to classify samples into tissues and cell types. Subsequently, a one-vs-all classification and feature importance were used to analyse the most discriminating protein abundances per class. Based on protein abundance alone, the model was able to predict tissues with 98% accuracy, and cell types with 99% accuracy. The F-scores describe a clear view on tissue-specific proteins and tissue-specific protein expression patterns. In-depth feature analysis shows slight confusion between physiologically similar tissues, demonstrating the capacity of the algorithm to detect biologically relevant patterns. These results can in turn inform downstream uses, from identification of the tissue of origin of proteins in complex samples such as liquid biopsies, to studying the proteome of tissue-like samples such as organoids and cell lines.

systems biology↗

bioRxiv2022

Trans-synaptic dwelling of SARS-CoV-2 particles perturbs neural synapse organization and function

SARS-CoV-2 infection is associated with short- and long-term neurological and psychiatric complications, referred to as neuroCOVID. These symptoms are relatively heterogenous and fluctuating, hampering the discovery of molecular mechanisms underlying viro-induced brain perturbations. Here, we show that the human cerebral cortex poorly supports SARS-CoV-2 dissemination using post-mortem COVID-19 patient samples, ex vivo organotypic cultures of human brain explants and stem cell-derived cortical organoids. Despite restricted infection, the sole exposure of neural cells to SARS-CoV-2 particles is sufficient to induce significant perturbations on neural synapse organization associated to electrical activity dysfunction. Single-organoid proteomics revealed that exposure to SARS-CoV-2 is associated to trans-synaptic proteins upregulation and unveiled that incoming virions dwell at LPHN3/FLRT3-containing synapses. Our study provides new mechanistic insights on the origin of SARS-CoV-2-induced neurological disorders. One-Sentence SummarySARS-CoV-2 modulates neural plasticity and electrical activity as viral particles lodge at the trans-synaptic interface.

microbiology↗