Biography
I am a senior bioinformatician and research scientist with expertise in statistical methods, machine learning, modeling, and pipeline development. I have a proven track record of success in developing and applying bioinformatics to solve challenging problems in biology. My PhD thesis was selected as a case study for New Zealand eScience Infrastructure and published in eLife, receiving the Best Publication Award from my PhD institution. I have also developed various open-source bioinformatics software and workflows for biologists, downloaded by thousands. I am always eager to collaborate to solve challenging problems in biology, biostatistics, and bioinformatics.
The tools that I developed and published:
Tool | Download | Purpose |
---|---|---|
MirMachine | microRNA homology search tool using machine learning | |
Cellsnake | single-cell analysis tool for everyone |
Research Interests
- Modelling and early prediction models in the context of personalized medicine
- Molecular oncology and cancer
- RNA biology, especially non-coding RNAs such as microRNAs, tRNA-derived molecules
- RNA-RNA interactions
- Biostatistics and molecular epidemiology
- NGS (DNA and RNA sequencing), transcriptomics from bulk RNA sequencing to spatial transcriptomics
- Reproducible bioinformatics pipelines, mostly using Snakemake, shell scripts, Python and R programming
Skills
- R, I am quite capable in tidyverse syntax (ggplot, caret, mlr3, Rmarkdown, shiny apps, functional programming, parallelization)
- Machine learning and data analysis in R
- Python (especially in bioinformatics context)
- Snakemake (I develop pipelines and also teach Snakemake)
- Biostatistics (basic modeling, survival models, and some newer machine learning algorithms)
- Linux (shell scripting and high-performance computing systems)
- Data Science and Machine learning (for predictive models, especially in R and Python, h2o, caret, Keras)