Does anybody have suggestions for text mining tool / API web based / library that would allow me to use my curated keywords (phenotypes) to fetch associated genes from the Pubmed abstract and free articles. These keywords are from specific tissue so would want tissue specific hits only. Please advise me on available options.
Fwd: the isItOpen(Data) stats for the #lodd data: 2 use a closed ontology, 3 don't specify a license, 1 is unclear (seems closed), 5 with NC (via http://friendfeed.com/egonw...)
RDF graph visualization with domain knowledge... it recognizes predicates (SMILES in this case) and can visualize the chemical structure, instead of just the fields... (of course, in a pluggable Bioclipse way) It currently support sequences and chemical structures.
What would be v cool would be to have a large number for tomorrow. Peter is hoping to sign during his talk tomorrow and that is being widely webcast. Will be writing my blog post on the plane.
- Cameron Neylon
from Android
Yes, that would be great... Good to see the news spread so fast...
- Egon Willighagen
It is kind of a shame that the endorsement list is not made machine-readable... e.g. via RDFa... otherwise, Pierre would have created us a nice Google Map with endorsement origins ;)
- Egon Willighagen
Count votes per country (naive one liner): wget -O endorsed.html http://pantonprinciples.org/endorse...; xpath -q -e "//span[@class='signature']/text()" endorsed.html | cut -d',' -f3 | sort | uniq -c
- Egon Willighagen
@Neil... yes, the button is nice... but where's the poster we can put up at our universities?
- Egon Willighagen
Updated xpath: //span[@class='signature']/span[@class='Country']/text()
- Egon Willighagen
I haven't seen a list of papers... I did see that I was #15 to submit an abstract... and that was close before the deadline... unless there is a second track for papers...
- Egon Willighagen