Acromine: Overview

Acromine is an abbreviation dictionary built using MEDLINE https://www.nlm.nih.gov/bsd/pmresources.html, originally constructed by Okazaki, N., Ananiadou, S. and Tsujii, J. in (2010) as part of their work in the following published journal articles:

• Okazaki, N., Ananiadou, S. and Tsujii, J. (2010). Building a High Quality Sense Inventory for Improved Abbreviation Disambiguation. Bioinformatics, Oxford University Press.
• Okazaki, N., Ananiadou, S. (2006) Building an abbreviation dictionary using a term recognition approach. Bioinformatics, Volume 22, Number 24, pp. 3089-3095, Oxford University Press.

Data Collection and Publication

According to the Acromine site http://www.nactem.ac.uk/software/acromine/:

Acromine is an abbreviation dictionary automatically constructed from the whole MEDLINE as of April, 2009. Acromine identifies abbreviation definitions by assuming a word sequence co-occurring frequently with a parenthetical expression to be a potential expanded form. Applied to the whole MEDLINE (9,635,599 abstracts), the implemented system extracted 68,007 abbreviation candidates and recognized 467,402 expanded forms. The current Acromine achieves 99% precision and 82-95% recall on our evaluation corpus that roughly emulates the whole MEDLINE.

The information collected in this way has been made available as a RESTful service, written in Python, which can be queried publicly. This allows third-party applications to be written which can tap into this information using simple HTTPS requests and to receive a response represented as a JSON string.

Example call to Acromine REST service

library(jsonlite) # We will use jsonlite to parse the returned JSON string

acronym <- "BMI"
url <- paste0(
              "http://www.nactem.ac.uk/software/acromine/dictionary.py?sf="
              ,acronym
              ,"&#8217;"
              ,   sep = FALSE
       )

results <- fromJSON(url)

# The resultant data frame contains a column named lfs, which contains a list of data frames
# with the long-forms of the supplied acronym.  We will return the return the first 3 variables
# for the first 5 of these long forms
results$lfs[[1]][1:5,1:3]

##                                lf  freq since
## 1                 body mass index 15893  1978
## 2          bicuculline methiodide   113  1980
## 3         brain-machine interface    25  2002
## 4         bone marrow involvement    16  1989
## 5 brief motivational intervention     9  2003

Sample application

To see a simple example application which makes use of the Acromine REST service, please go to https://rory-gaddin.shinyapps.io/dataproducts-shiny-app/.

Thank you!