OncoCurate: Automating Cancer Genomics Biocuration


Screen Shot 2018-04-13 at 7.29.51 PM

Click here for the paper

Click here for a research presentation

Click here for a video description

OncoCurate is a cloud application that automates the process of cancer genomics biocuration. There’s three main things the system does:

  1. Isolates Research Abstracts that Relate to Cancer Genomics (I made a novel algorithm to do this by writing a search engine that uses the “Hallmarks of Cancer” to identify research abstracts that are relevant to curation)
  2. Predicts Whether Unknown Mutations are cancerous just by “reading” the relevant articles (Let’s say you didn’t know KRAS was oncogenic but there was a lot of research published about it recently; OncoCurate will find that research and then use LSTMs to figure out whether KRAS is oncogenic or not; this saves human curators A LOT of time)
  3. Improves its own performance by responding to human feedback (Human biocurators can annotate OncoCurate’s results and that feedback is used to improve all aspects of the algorithm)



Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s