Trained as a biomedical engineer, computational biologist and doctor.

Working as a data scientist at Open Targets, where we use machine learning and software engineering to help find new drugs, taking advantage of human genetics and other biological data.

Expertise

• Computational biology
• machine learning
• sequencing pipelines (16S, NGS)
• human microbiome
• medicine
• immunology
• drug development
• software project management

Computing stack

• Python - ipython,scikit-learn, numpy, matplotlib, seaborne, pandas, lxml, NLTK, requests, sqlite3.
• R - ML view: gbm, lasso, randomforest, etc.; ggplot2, knitr, shiny.
• Web development - working knowledge of HTML/CSS/JS, D3, dc.js, crossfilter.
• Strong experience with REST APIs.
• Linux - Git, bash/zsh, sge/torque/pbs, CI(travis/wercker), vagrant, ansible.
• Cloud - AWS, Google
• Containers - docker, kubernetes, ECS
• ETL - Luigi, Airflow
• Backends - Elasticsearch, sqlite
• Familiar with agile and test-driven development. CI/CD/DevOps

Contributor to open source projects:

• Open Targets
• kubernetes
• luigi