I am a biostatistician with a focus on the analysis of omics type of data and high dimensional data. My interest lies on the identification and modelling of correlation structures within the data. I have mostly developed mixed-model models in order to better estimate and interpret the variation present in the data, and methodology for prediction models utilizing the correlation within the data for improved accuracy and stability.
I recently have developed methods for estimating the effect of biomarkers on secondary phenotypes in ascertained family studies by correcting properly for the sampling process of these studies. Leading to a proper control of false positives as well as obtaining unbiased estimate of the heritability of such secondary phenotypes.
My current research are focusing on developing proper methodology for the analysis of CRISPR screens at the gene level while properly taking into account the correlation existing between guide RNAs targeting the same gene as well as the analysis of exon usage at the gene level.