ContentMine and DNAdigest Hackday
From the volunteers and organisers of ContentMine and DNAdigest comes a new hackday! #ContentMineHackday
ContentMine is an open-source project, funded by the Shuttleworth Foundation, that extracts facts from scientific literature in machine readable form.
We will use the tools of ContentMine to automatically extract references to genomic datasets from new journal publications. Then we can put them into a big machine-readable database that can be searched by interested humans and machines alike. We would love to have your expertise and help with this experiment!
But we also want to explore with you any other areas where automatic fact extraction could be useful.
Perhaps you work in a field where you have to manually transcribe data from graphs? Or perhaps you would like to scan open-access journals that are only available via the web for a particular word or phrase? ContentMine has tools to do all these things and more.
If you are interested in text-mining journals, whether that is for genomic dataset DOIs, your own research or just out of general interest, please come along and join us! In-depth programming knowledge is not essential – ContentMine is designed to make mining easy and we will have ContentMine mentors there on the day to help you get familiar with the system.
Tickets include lunch and catering during the day.
Students attend for free.
Register via Eventbrite
Map of EBML-EBL Wellcome Trist Genome Campus: (see below)
Information on how to get the EMBL-EBI – including travel by train, car, taxi or plane
EBI / Sanger Commuter Bus (see below)