Mickaël Leclercq

Urinary tract infections are among the most common infections in humans, yet their diagnosis still depends on time-consuming workflows based on microbial culture, followed by MALDI-TOF mass spectrometry. Although LC-MS/MS offers the sensitivity and specificity needed to bypass culture, conventional pipelines depend on lengthy analyses and peptide/protein identification steps, limiting the throughput and hindering its adoption in clinical settings. Here, we introduce a direct, identification-free LC-MS/MS workflow that analyzes raw ion signal and produces species-level microbial identification in about 5 min after preparation, fast enough to meet clinical throughput requirements. Our machine learning-enabled raw-signal pipeline bypasses peptide identification entirely, preserving information and eliminating the traditional interpretation stack. Across 15 independent analytical batches covering 28 clinically relevant pathogens, the method achieved high-confidence classification (MCC = 0.86). Applied to 206 clinical urine specimens across three batches, the approach reached 91% accuracy at clinically actionable microbial loads (greater than 105 CFU/mL) and, critically, 0 false positives in control specimens. The performance was lower for specimens below this threshold. These results show that raw LC-MS/MS spectra contain sufficient biological information for direct microbial diagnosis, establishing an analytical framework for clinical mass spectrometry. This proof-of-concept demonstrates that rapid, culture-free, fast microbial identification is achievable and positions raw signal inference as a promising direction for next-generation diagnostic mass spectrometry.

The MSMP (MicroSeminoProtein, Prostate-associated) protein is overexpressed in several cancers, including prostate, ovarian, and breast cancers. Its overexpression is particularly prevalent in tumors resistant to hormonal therapy, as well as to antiangiogenic treatments (e.g., anti-VEGF therapies). In hypoxic tumor microenvironments, characteristic of solid tumors, MSMP expression increases and facilitates tumor growth. MSMP binds to the transmembrane receptor CCR2 (C-C chemokine receptor type 2), a GPCR present on monocytes and lymphocytes. This interaction stabilizes an active conformation of CCR2, enabling downstream MAP kinase signaling pathways to reactivate androgen synthesis and promote tumor progression. In this study, we employed molecular modeling, molecular dynamics simulations, and machine learning techniques to elucidate the structural basis of the MSMP-CCR2 interaction. High-resolution models of the MSMP-CCR2-G protein complex were generated using AlphaFold2 and refined with MD simulations. Comparative analyses with the CCL2-CCR2-G protein complex and the unbound CCR2-G protein complex revealed key conformational rearrangements that modulate and stabilize the active state of the receptor. Binding free energy calculations revealed similar energetic profiles for MSMP and CCL2, despite distinct binding modes. Residue-level energy decomposition identified critical residues at the MSMP-CCR2 interface, offering insights into the receptor's activation mechanism. Additionally, machine learning models classified molecular dynamics trajectories, highlighting key structural features associated with stable MSMP-CCR2-G protein states. This integrative approach identified residues essential for maintaining a stable conformation of the MSMP-CCR2-G protein complex, providing a basis for targeting MSMP-CCR2 interactions in therapeutic development.

Data-independent acquisition (DIA) mass spectrometry has become increasingly prevalent in proteomics as advances in instrumentation, chromatography, and computational analysis have enabled robust proteome identification across complex biological samples. However, analytical depth achieved with fast chromatographic gradients remains lower than that obtained using long-gradients, reflecting a throughput-depth trade-off. Here, we present PeptiDIA, a machine learning framework that enhances peptide identification in fast-gradient DIA data by leveraging paired fast and long-gradient acquisitions from identical samples. PeptiDIA processes DIA-NN outputs generated at relaxed false discovery rate thresholds to obtain expanded candidate peptide pools and trains gradient-boosted decision tree models using long-gradient identifications as reference labels. The model integrates DIA-NN features with engineered peptide descriptors and applies isotonic regression to calibrate probabilities, enabling controlled peptide recovery relative to the long-gradient reference. Applied to human and murine datasets spanning six tissues acquired on an Orbitrap Exploris 480, PeptiDIA increased peptide identifications by 25-34% at 1% target reference-discordance rate (RDR) and increased the number of protein groups containing at least one rescued peptide by 15-17%. Overall, PeptiDIA improves the identification depth of fast-gradient DIA-NN workflows without altering acquisition strategies. The framework is available as a web application and command-line tool at https://github.com/Jordano700/PeptiDIA .

Background: Rapid and accurate identification of urinary tract infection (UTI) pathogens is critical for effective treatment and combating antimicrobial resistance. Conventional culture-based diagnostics are slow, and standard tandem mass spectrometry workflows are resource-intensive. Methods: We present a proof-of-concept workflow that integrates high-resolution data-independent acquisition (DIA) MS/MS on the Thermo Scientific Orbitrap Astral with MS1-only spectra from the Orbitrap Exploris 480. DIA data establish a reference panel of pathogen-specific peptides, which are then identified in MS1 spectra from urine samples. Machine learning models trained on these matched MS1 features were used to classify eight common uropathogens and non-infected controls across synthetic inoculations, pure cultures, and clinical patient samples. Model development employed a one-vs-all Random Forest (Ranger) framework with nested cross-validation for feature selection and hyperparameter tuning, followed by evaluation on an independent held-out external patient cohort. Results: The approach accurately distinguished bacterial species in both controlled inoculated samples and clinical patient samples. Using repeated nested cross-validation, the model achieved a mean Matthews Correlation Coefficient (MCC) of 0.88, indicating robust classification performance across resampled training partitions. Performance generalized to an independent patient cohort, achieving an MCC of 0.822, confirming the model’s ability to maintain predictive accuracy under external validation. Conclusions: This proof-of-concept demonstrates that pairing DIA-derived peptide panels with MS1-only data acquired on a cost-effective instrument suitable for routine analysis, enables rapid, culture-free identification of UTI pathogens. The method provides a scalable, high-throughput platform suitable for clinical applications and establishes a foundation for broader biomarker discovery and potential quantitative workflows. Key Points: - DIA-derived peptide panels enable pathogen detection using MS1-only measurements. - Machine learning classifies eight common uropathogens covering 84% of infections. - MS1-only workflows enable culture-free pathogen identification of 300 samples/day.

Large language models (LLMs) originally developed for human text have been adapted to proteomics as protein language models (pLMs). These models treat amino acid sequences like sentences, and they learn patterns from millions of sequences. pLMs are used for several key tasks, including the prediction of protein structures, annotating protein functions, designing novel protein sequences with specific characteristics, and mapping the interactions between proteins and other molecules. Compared with traditional approaches, pLMs deliver insights more quickly but demand large computing resources and careful data management. Developers are focused on decreasing prediction inaccuracies and biases by exploring more efficient training techniques and smaller models to decrease the resources required. As sequence databases continue to grow, pLMs will improve to uncover links between proteins and disease pathways, speeding drug development and basic research while offering new proteome-scale insights that support experimental design and validation.

Human infection with the coronavirus disease 2019 (COVID-19) is mediated by the binding of the spike protein of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) to the human angiotensin-converting enzyme 2 (ACE2). The frequent mutations in the receptor-binding domain (RBD) of the spike protein induced the emergence of variants with increased contagion and can hinder vaccine efficiency. Hence, it is crucial to better understand the binding mechanisms of variant RBDs to human ACE2 and develop efficient methods to characterize this interaction. In this work, we present an approach that uses machine learning to analyze the molecular dynamics simulations of RBD variant trajectories bound to ACE2. Along with the binding free energy calculation, this method was used to characterize the major differences in ACE2-binding capacity of three SARS-CoV-2 RBD variants—namely the original Wuhan strain, Omicron BA.1, and the more recent Omicron BA.5 sublineages. Our analyses assessed the differences in binding free energy and shed light on how it affects the infectious rates of different variants. Furthermore, this approach successfully characterized key binding interactions and could be deployed as an efficient tool to predict different binding inhibitors to pave the way for new preventive and therapeutic strategies.

Urinary tract infections (UTIs) are a worldwide health problem. Fast and accurate detection of bacterial infection is essential to provide appropriate antibiotherapy to patients and to avoid the emergence of drug-resistant pathogens. While the gold standard requires 24h to 48h of bacteria culture prior MALDI-TOF species identification, we propose a culture-free workflow, enabling a bacterial identification and quantification in less than 4 hours using 1mL of urine. After a rapid and automatable sample preparation, a signature of 82 bacterial peptides, defined by machine learning, was monitored in LC-MS, to distinguish the 15 species causing 84% of the UTIs. The combination of the sensitivity of the SRM mode on a triple quadrupole TSQ Altis instrument and the robustness of capillary flow enabled us to analyze up to 75 samples per day, with 99.2% accuracy on bacterial inoculations of healthy urines. We have also shown our method can be used to quantify the spread of the infection, from 8×10 ⁴ to 3×10 ⁷ CFU/mL. Finally, the workflow was validated on 45 inoculated urines and on 84 UTI-positive urine from patients, with respectively 93.3% and 87.1% of agreement with the culture-MALDI procedure at a level above 1×10 ⁵ CFU/mL corresponding to an infection requiring antibiotherapy. HIGHLIGHTS: – LC-MS-SRM and machine learning to identify and quantify bacterial species of UTI – Fast sample preparation without bacterial culture and high-throughput MS analysis – Accurate quantification through calibration curves for 15 species of UTIs – Validation on inoculations (93% accuracy) and on patients specimens (87% accuracy)

Megakaryocytes (MKs), integral to platelet production, predominantly reside in the bone marrow (BM) and undergo regulated fragmentation within sinusoid vessels to release platelets into the bloodstream. Inflammatory states and infections influence MK transcription, potentially affecting platelet functionality. Notably, COVID-19 has been associated with altered platelet transcriptomes. In this study, we investigated the hypothesis that severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection could affect the transcriptome of BM MKs. Using spatial transcriptomics to discriminate subpopulations of MKs based on proximity to BM sinusoids, we identified ∼19 000 genes in MKs. Machine learning techniques revealed that the transcriptome of healthy murine BM MKs exhibited minimal differences based on proximity to sinusoid vessels. Furthermore, at peak SARS-CoV-2 viremia, when the disease primarily affected the lungs, MKs were not significantly different from those from healthy mice. Conversely, a significant divergence in the MK transcriptome was observed during systemic inflammation, although SARS-CoV-2 RNA was never detected in the BM, and it was no longer detectable in the lungs. Under these conditions, the MK transcriptional landscape was enriched in pathways associated with histone modifications, MK differentiation, NETosis, and autoimmunity, which could not be explained by cell proximity to sinusoid vessels. Notably, the type I interferon signature and calprotectin (S100A8/A9) were not induced in MKs under any condition. However, inflammatory cytokines induced in the blood and lungs of COVID-19 mice were different from those found in the BM, suggesting a discriminating impact of inflammation on this specific subset of cells. Collectively, our data indicate that a new population of BM MKs may emerge through COVID-19–related pathogenesis.