- Course overview
- Search within this course
- What is machine learning?
- ML in drug discovery: why now?
- ML in the drug discovery pipeline
- Getting started in ML using WEKA
- Hands-on with WEKA
- Identifying targets for cancer using gene expression profiles
- Summary
- Your feedback
- Learn more
- References
All materials are free cultural works licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license, except where further licensing details are provided.
Open Targets Genetics
Open Targets Genetics is an open source tool for exploring variant-gene-trait associations from the UK Biobank, FinnGen, and GWAS Catalog. It uses a novel machine learning model developed using a Gradient Boosting approach to predict Locus-to-gene (L2G) scores. The score is used for prioritising genes as potential targets. As an example, the figure below shows a list of independent loci (genetic variants) associated with Crohn’s disease and corresponding likely causal genes. Genes are assigned at each locus by three different pipelines, including the L2G pipeline, which is based on a ML framework. Prioritised genes could be good candidates for further analysis in drug target identification and prioritisation. Read more about the ML framework used by Open Targets Genetics elsewhere [20]. You can also read the deep-dive on the Open Targets blog.
