Correction de Bonferroni | EPFL Graph Search

En statistiques, la correction de Bonferroni est une méthode pour corriger le seuil de significativité lors de comparaisons multiples. La correction de Bonferroni est la méthode de correction la plus simple, bien qu'elle soit conservatrice étant donné qu'elle présente un risque conséquent d'. En effet, cette méthode ne prend pas en compte quelques informations, comme la distribution des valeurs p des différentes comparaisons. La mathématicienne et statisticienne américaine Olive Jean Dunn (1915–2008) a travaillé sur la notion d'intervalle de confiance en biostatistique et développé une solution au , connue aujourd'hui sous le nom de correction de Bonferroni. Cette méthode de correction porte le nom du mathématicien italien Carlo Emilio Bonferroni (1892-1960), bien qu'il n'en soit pas l'auteur (ainsi, c'est un exemple de la loi de Stigler). Références Catégorie:Statistiques

Statistical inference in ensemble modeling of cellular metabolism

Marc-Olivier Boldi, Tuure Eelis Hameri, Vassily Hatzimanikatis

Kinetic models of metabolism can be constructed to predict cellular regulation and devise metabolic engineering strategies, and various promising computational workflows have been developed in recent years for this. Due to the uncertainty in the kinetic parameter values required to build kinetic models, these workflows rely on ensemble modeling (EM) principles for sampling and building populations of models describing observed physiologies. Sensitivity coefficients from metabolic control analysis (MCA) of kinetic models can provide important insight about cellular control around a given physiological steady state. However, despite considering populations of kinetic models and their model outputs, current approaches do not provide adequate tools for statistical inference. To derive conclusions from model outputs, such as MCA sensitivity coefficients, it is necessary to rank/compare populations of variables with each other. Currently existing workflows consider confidence intervals (CIs) that are derived independently for each comparable variable. Hence, it is important to derive simultaneous CIs for the variables that we wish to rank/compare. Herein, we used an existing large-scale kinetic model of Escherichia Coli metabolism to present how univariate CIs can lead to incorrect conclusions, and we present a new workflow that applies three different multivariate statistical approaches. We use the Bonferroni and the exact normal methods to build symmetric CIs using the normality assumptions. We then suggest how bootstrapping can compute asymmetric CIs whilst relaxing this normality assumption. We conclude that the Bonferroni and the exact normal methods can provide simple and efficient ways for constructing reliable CIs, with the exact normal method favored over the Bonferroni when the compared variables present dependencies. Bootstrapping, despite its significantly higher computational cost, is recommended when comparing non-normal distributions of variables. Additionally, we show how the Bonferroni method can readily be used to estimate required sample numbers to attain a certain CI size.

2019

Triplet State Imaging

Aurélie Formey de Saint Louvent, Boris Hinz, Theo Lasser, Iwan Märki, Thiemo Spielmann, Dimitri Nestor Alice Van De Ville

We present a functional imaging method based on triplet state kinetics. The triplet state of many known fluorophores shows a triplet lifetime typically in the order of ~10e-6 – 10e-3 s, 3-6 orders of magnitude longer than the associated fluorescence singlet lifetime. As a consequence triplet state sensing is more exposed to the microenvironment of fluorophores and can be used as a functional molecular antenna. By means of a modulated excitation scheme of pulses with varying duty cycles, the triplet state population can be controlled: large duty cycles lead to a highly populated triplet state and hence a lower populated excited singlet state. This singlet-triplet interation translates into a diminished fluorescence emission, which can be detected using any standard CCD detector technology. We realised an imaging setup allowing extraction of triplet lifetime maps based on a whole field illumination and detection. Effective correction of the competitive bleaching component is achieved by simultaneous monitoring of bleaching. The signal processing is based on a linear regressor analysis enabling rapid extraction of the triplet state lifetime. As a first proof of principle, we investigated oxygen as a triplet state quencher on a sample of tetramethylrhodamine (TMR) printed on a glass cover slide by soft lithography. These results demonstrate the robustness of the setup to extract triplet lifetimes against high concurrent bleaching components. First imaging of bioassays will be presented indicating the high potential for functional and metabolic imaging in life cell applications.

2009

Triplet Imaging by Modulated Excitation

Aurélie Formey de Saint Louvent, Boris Hinz, Kai Johnsson, Theo Lasser, Thiemo Spielmann, Dimitri Nestor Alice Van De Ville

We present a functional imaging method based on triplet state kinetics. The triplet state of many known fluorophores show a triplet lifetime typically in the order of ~10e-6 – 10e-3 s, 3-6 orders of magnitude longer than the associated fluorescence singlet lifetime. As a consequence triplet state sensing is more exposed to the microenvironment of fluorophores and can be used as a functional molecular antenna. Using an adaptive modulated excitation scheme, these long living triplet state dynamics are accessible by standard CCD detector technology. We built an imaging setup allowing extraction of triplet lifetime maps. Effective correction of the competitive bleaching component is achieved by simultaneous monitoring of bleaching. The signal processing is based on a linear regressor analysis enabling extraction of the triplet state lifetime. As a first proof of principle, we investigated oxygen as a triplet state quencher on a sample of Tetramethylrhodamine (TMR) printed on a glass cover slide by soft lithography. First bioassays will be presented indicating the high potential for functional and metabolic imaging in life cell applications.

2008

Statistical inference in ensemble modeling of cellular metabolism

Marc-Olivier Boldi, Tuure Eelis Hameri, Vassily Hatzimanikatis

2019