Hopefully of use .... a large number of UMLS concepts are publicly availability to download without UMLS license for sources in MedGen, which represents 300k+ concepts, including many concepts and relationships in SNOMED-CT, MESH, NCI Metathausurus (MTH), etc.
You can download UMLS dictionaries for medgen here from NLM (no login) <ftp://ftp.ncbi.nlm.nih.gov/pub/medgen/> For custom dictionaries, you can use Bash to download and build many concepts in UMLS related dictionaries: https://bitbucket.org/invitae/medgen-mysql #concepts for each UMLS Semantic Type (STY) referenced by MedGen +-------------------------------------------+--------+ | STY | cnt | +-------------------------------------------+--------+ | Pharmacologic Substance | 102511 | | Finding | 90413 | | Organic Chemical | 81329 | | Disease or Syndrome | 47223 | | Neoplastic Process | 16151 | | Amino Acid, Peptide, or Protein | 9383 | | Congenital Abnormality | 6536 | | Pathologic Function | 5655 | | Steroid | 3919 | | Sign or Symptom | 2909 | | ... | ... | On Tue, Dec 8, 2015 at 2:19 PM, andy mcmurry <mcmurry.a...@gmail.com> wrote: > +1 I would be happy to write about the experience of creating the medgen > (medical genetics) database, especially useful for cancer and cardio > On Dec 8, 2015 2:04 PM, "David Kincaid" <kincaid.d...@gmail.com> wrote: > >> That is a great idea! I'd be happy to help provide some content as someone >> who has been trying to use cTAKES inside other projects. As I mentioned >> previously I am working in veterinary medicine which has just enough >> peculiarities to make cTAKES out of the box a challenge (although it is >> much better now than it was a couple years ago, so kudos to those of you >> who have been making it better). I also can't stand Eclipse, happily left >> Subversion behind years ago and prefer to work in Clojure as much as >> possible. >> >> - Dave >> >> On Tue, Dec 8, 2015 at 3:41 PM, Miller, Timothy < >> timothy.mil...@childrens.harvard.edu> wrote: >> >> > The recent discussion over dictionary building, and someone pointing out >> > it has come up several times, made me think that maybe we should use the >> > blog space that apache provides. It could be used for write-ups of >> > things that are not quite as formal as "documentation" but would benefit >> > from being written down somewhere that is easier to search and link to >> > than a mailing list. >> > Any thoughts? >> > Tim >> > >> > >> > -- Andy McMurry, PhD Chief Technical Officer http://GetMedal.com