Biology subjects

Junet, V.

Publications and source records attributed to Junet, V..

3 recordsLinked to original sources

bioRxiv2025

Predicting TCR antigen specificity at proteome-scale with synthetic immune cells and machine learning

TCR specificity to peptide-HLA antigens is central to immunology, impacting responses in infection, autoimmunity and cancer. Achieving precise recognition while avoiding off-target reactivity is critical for effective immunity and safe therapeutic interventions. Comprehensive, proteome-wide specificity profiling of TCRs is challenging with current methods, which notably lack integrated machine learning for large-scale analysis. Here, we report a synthetic immune cell system coupled with machine learning to enable TCR functional and specificity mapping of peptide-HLA antigens at proteome-scale. Multi-step immunogenomic engineering of synthetic antigen-presenting cells (APCs) was performed to enable stable mono-allelic integration and precise display of peptide antigens and HLA class I from a defined genomic locus, ensuring genomically-encoded antigen presentation. Compatible with a synthetic TCR displaying T cell system, this platform incorporates a fluorescent reporter of cytokine-mediated signaling for real-time activation detection in both synthetic APCs and T cells. We combined this screening with diverse peptide antigen libraries and deep sequencing to train supervised machine learning models. These models were applied to predict TCR specificity to peptide-HLA antigens across the entire human proteome. Experimental validation confirmed novel off-targets for therapeutic TCR candidates, including for a clinically-approved TCR therapeutic. This integrated synthetic immune cell and machine learning approach provides unprecedented proteome-wide peptide-HLA specificity mapping to support the development of safer TCR-based therapies. One sentence summaryWe present a synthetic immune cell platform integrated with machine learning that enables prediction of TCR specificity to peptide-HLA antigens at proteome-scale.

immunology↗

bioRxiv2020

CuBlock: A cross-platform normalization method for gene-expression microarrays

MotivationCross-(multi)platform normalization of gene-expression microarray data remains an unresolved issue. Despite the existence of several algorithms, they are either constrained by the need to normalize all samples of all platforms together, compromising scalability and reuse, by adherence to the platforms of a specific provider, or simply by poor performance. In addition, many of the methods presented in the literature have not been specifically tested against multi-platform data and/or other methods applicable in this context. Thus, we set out to develop a normalization algorithm appropriate for gene-expression studies based on multiple, potentially large microarray sets collected along multiple platforms and at different times, applicable in systematic studies aimed at extracting knowledge from the wealth of microarray data available in public repositories; for example, for the extraction of Real-World Data to complement data from Randomized Controlled Trials. Our main focus or criterion for performance was on the capacity of the algorithm to properly separate samples from different biological groups. ResultsWe present CuBlock, an algorithm addressing this objective, together with a strategy to validate cross-platform normalization methods. To validate the algorithm and benchmark it against existing methods, we used two distinct data sets, one specifically generated for testing and standardization purposes and one from an actual experimental study. Using these data sets, we benchmarked CuBlock against ComBat (Johnson et al., 2007), YuGene (Le Cao et al., 2014), DBNorm (Meng et al., 2017), Shambhala (Borisov et al., 2019) and a simple log2 transform as reference. We note that many other popular normalization methods are not applicable in this context. CuBlock was the only algorithm in this group that could always and clearly differentiate the underlying biological groups after mixing the data, from up to six different platforms in this study. AvailabilityCuBlock can be downloaded from https://www.mathworks.com/matlabcentral/fileexchange/77882-cublock Contactxouse@anaxomics.com, xavier.daura@uab.cat Supplementary informationSupplementary data are available at bioRxiv online.

bioinformatics↗

bioRxiv2019

TPMS technology to infer biomarkers of macular degeneration prognosis in in silico simulated prototype-patients under the study of heart failure treatment with sacubitril and valsartan

Unveiling the mechanism of action of a drug is key to understand the benefits and adverse reactions of drug(s) in an organism. However, in complex diseases such as heart diseases there is not a unique mechanism of action but a wide range of different responses depending on the patient. Exploring this collection of mechanisms is one of the clues for a future personalised medicine. The Therapeutic Performance Mapping System (TPMS) is a Systems Biology approach that generates multiple models of the mechanism of action of a drug. This is achieved by (1) modelling the responses in human with an accurate description of the protein networks and (2) applying a Multilayer Perceptron-like and sampling method strategy to find all plausible solutions. In the present study, TPMS is applied to explore the diversity of mechanisms of action of the drug combination sacubitril/valsartan. We use TPMS to generate a range of mechanism of action models explaining the relationship between sacubitril/valsartan and heart failure (the indication), as well as evaluating their relationship with macular degeneration (a common/recurrent adverse effect). We found that a lower response in terms of heart failure treatment is more associated to macular degeneration development, although good response mechanisms can also associate to the adverse effect. A set of 30 potential biomarkers are proposed to identify mechanisms (or patients) more prone to suffering macular degeneration when presenting good heart failure response. As each molecular mechanism can be particular not only of cells but also individuals, we conclude that the study of the collection of models generated using TPMS technology can be used to detect adverse effects personalized to patients.

bioinformatics↗