A molecular genetics and computational biology researcher with over six years of post-Ph.D. experience and currently working as an assistant project scientist at the University of California - Davis, USA
I genotype large populations using next-gen sequencing, phenotype them using high-throughput phenotyping, and apply statistical modelling, machine and deep learning for the identification of causative mutations and candidate genes involved in differential phenotype expression
I write genomic and phenotype data analysis pipelines in BASH and Snakemake. I also build software packages, web-applications, and databases to process and visualize big omics data
I do significance testing, build custom classical and bayesian statistical models to treat the influence random effects and associate genetic variation, gene expression and phenotype expression
I use machine learning models for classification and regression. I build custom deep learning models for object detection, image segmentation, and instance segmentation for high-throughput phenotyping
I build classical statistical models and deep-learning models to extract phenotype data from large-scale image data
I build software packages, web-apps, and databases for high-throughput data processing and visualization.