Cyprien Mbogning

Cyprien Mbogning

Auto-generated profile, based on publicly available information

Cyprien Mbogning

CESP, Université Pa ris-Sud, UVSQ, INSERM, Université Paris-Saclay, Villejuif, France

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 November 2016 in PLOS ONE
Verified
Journal Article
Open access
PDF file
DBDelphine Bachelet
Delphine Bachelet
SHSigne Hässler
Signe Hässler
CMCyprien Mbogning
Cyprien Mbogning
JLJenny Link
Jenny Link
MRMalin Ryner
Malin Ryner
OCon behalf of the ABIRISK Consortium
on behalf of the ABIRISK Consortium
Immunogenicity of biopharmaceutical products in multiple sclerosis is a frequent side effect which has a multifactorial etiology. Here we study associations between anti-drug antibody (ADA) occurrence and demographic and clinical factors. Retrospective data from routine ADA test laboratories in Sweden, Denmark, Austria and Germany (Dusseldorf group) and from one research study in Germany (Munich group) were gathered to build a collaborative multi-cohort dataset within the framework of the ABIRISK project. A subset of 5638 interferon-beta (IFNβ)-treated and 3440 natalizumab-treated patients having data on at least the first two years of treatment were eligible for interval-censored time-to-event analysis. In multivariate Cox regression, IFNβ-1a subcutaneous and IFNβ-1b subcutaneous treated patients were at higher risk of ADA occurrence compared to IFNβ-1a intramuscular-treated patients (pooled HR = 6.4, 95% CI 4.9–8.4 and pooled HR = 8.7, 95% CI 6.6–11.4 respectively). Patients older than 50 years at start of IFNβ therapy developed ADA more frequently than adult patients younger than 30 (pooled HR = 1.8, 95% CI 1.4–2.3). Men developed ADA more frequently than women (pooled HR = 1.3, 95% CI 1.1–1.6). Interestingly we observed that in Sweden and Germany, patients who started IFNβ in April were at higher risk of developing ADA (HR = 1.6, 95% CI 1.1–2.4 and HR = 2.4, 95% CI 1.5–3.9 respectively). This result is not confirmed in the other cohorts and warrants further investigations. Concerning natalizumab, patients older than 45 years had a higher ADA rate (pooled HR = 1.4, 95% CI 1.0–1.8) and women developed ADA more frequently than men (pooled HR = 1.4, 95% CI 1.0–2.0). We confirmed previously reported differences in immunogenicity of the different types of IFNβ. Differences in ADA occurrence by sex and age are reported here for the first time. These findings should be further investigated taking into account other exposures and biomarkers.

11 April 2013 in Statistics and Computing
Verified
Journal Article
Closed access
PDF file
MLMarc Lavielle
Marc Lavielle
CMCyprien Mbogning
Cyprien Mbogning

31 January 2014 in Journal of Statistical Computation and Simulation
Verified
Journal Article
Closed access
CMCyprien Mbogning
Cyprien Mbogning
KBKevin Bleakley
Kevin Bleakley
MLMarc Lavielle
Marc Lavielle
We propose a nonlinear mixed-effects framework to jointly model longitudinal and repeated time-to-event data. A parametric nonlinear mixed-effects model is used for the longitudinal observations and a parametric mixed-effects hazard model for repeated event times. We show the importance for parameter estimation of properly calculating the conditional density of the observations (given the individual parameters) in the presence of interval and/or right censoring. Parameters are estimated by maximizing the exact joint likelihood with the stochastic approximation expectation–maximization algorithm. This workflow for joint models is now implemented in the Monolix software, and illustrated here on five simulated and two real datasets.

1 January 2014 in Journal of Clinical Bioinformatics
Verified
Journal Article
Open access
CMCyprien Mbogning
Cyprien Mbogning
HPHervé Perdry
Hervé Perdry
WTWilson Toussile
Wilson Toussile
PBPhilippe Broët
Philippe Broët
Dissecting the genomic spectrum of clinical disease entities is a challenging task. Recursive partitioning (or classification trees) methods provide powerful tools for exploring complex interplay among genomic factors, with respect to a main factor, that can reveal hidden genomic patterns. To take confounding variables into account, the partially linear tree-based regression (PLTR) model has been recently published. It combines regression models and tree-based methodology. It is however computationally burdensome and not well suited for situations for which a large number of exploratory variables is expected. We developed a novel procedure that represents an alternative to the original PLTR procedure, and considered different selection criteria. A simulation study with different scenarios has been performed to compare the performances of the proposed procedure to the original PLTR strategy. The proposed procedure with a Bayesian Information Criterion (BIC) achieved good performances to detect the hidden structure as compared to the original procedure. The novel procedure was used for analyzing patterns of copy-number alterations in lung adenocarcinomas, with respect to Kirsten Rat Sarcoma Viral Oncogene Homolog gene (KRAS) mutation status, while controlling for a cohort effect. Results highlight two subgroups of pure or nearly pure wild-type KRAS tumors with particular copy-number alteration patterns. The proposed procedure with a BIC criterion represents a powerful and practical alternative to the original procedure. Our procedure performs well in a general framework and is simple to implement.

1 July 2015 in Human Heredity
Verified
Journal Article
Closed access
CMCyprien Mbogning
Cyprien Mbogning
HPHervé Perdry
Hervé Perdry
PBPhilippe Broët
Philippe Broët
Objectives: In genomics, variable selection and prediction accounting for the complex interrelationships between explanatory variables represent major challenges. Tree-based methods are powerful alternatives to classical regression models. We have recently proposed the generalized, partially linear, tree-based regression (GPLTR) procedure that integrates the advantages of generalized linear regression (allowing the incorporation of confounding variables) and of tree-based models. In this work, we use bagging to address a classical concern of tree-based methods: their instability. Methods: We present a bagged GPLTR procedure and three scores for variable importance. The prediction accuracy and the performance of the scores are assessed by simulation. The use of this procedure is exemplified by the analysis of a lung cancer data set. The aim is to predict the epidermal growth factor receptor (EGFR) mutation based on gene expression measurements, taking into account the ethnicity (confounder variable) and perform variable selection. Results: The procedure performs well in terms of prediction accuracy. The scores differentiate predictive variables from noise variables. Based on a lung adenocarcinoma data set, the procedure achieves good predictive performance for EGFR mutation and selects relevant genes. Conclusion: The proposed bagged GPLTR procedure performs well for prediction and variable selection.

30 March 2026
Verified
Thesis
Closed access
CMCyprien Mbogning
Cyprien Mbogning
Cette thèse est consacrée au développement de nouvelles méthodologies pour l'analyse des modèles non-linéaires à effets mixtes, à leur implémentation dans un logiciel accessible et leur application à des problèmes réels. Nous considérons particulièrement des extensions des modèles non-linéaires à effets mixtes aux modèles de mélange et aux modèles conjoints. Dans la première partie, nous proposons, dans le but d'avoir une meilleure maîtrise de l'hétérogénéité liée aux données sur des patients issus de plusieurs clusters, des extensions des MNLEM aux modèles de mélange. Nous proposons ensuite de combiner l'algorithme EM, utilisé traditionnellement pour les modèles de mélanges lorsque les variables étudiées sont observées, et l'algorithme SAEM, utilisé pour l'estimation de paramètres par maximum de vraisemblance lorsque ces variables ne sont pas observées. La procédure résultante, dénommée MSAEM, permet ainsi d'éviter l'introduction d'une étape de simulation des covariables catégorielles latentes dans l'algorithme d'estimation. Cet algorithme est extrêmement rapide, très peu sensible à l'initialisation des paramètres, converge vers un maximum (local) de la vraisemblance et est implémenté dans le logiciel Monolix.La seconde partie de cette Thèse traite de la modélisation conjointe de l'évolution d'un marqueur biologique au cours du temps et les délais entre les apparitions successives censurées d'un évènement d'intérêt. Nous considérons entre autres, les censures à droite, les multiples censures par intervalle d'évènements répétés. Les paramètres du modèle conjoint résultant sont estimés en maximisant la vraisemblance jointe exacte par un algorithme de type MCMC-SAEM. Cette méthodologie est désormais disponible sous Monolix