This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Text mining in PDFs

What tools are useful for text mining of pdf-based literature? For example, suppose I had a list of several genes and several phenotypes, and wanted to look for associations between those genes and phenotypes in literature for which a PDF is available, but HTML of the full text is not. Are there tools to efficiently do this type of search?

text mining
• 1,835 views • link
updated by h.mon h.mon • written by Matt LaFave Matt LaFave

not a direct answer to your request but perhaps this resource might be of use EVEX (not sure though how well maintained it still is)

• 1 views • link
written by lieven.sterck lieven.sterck

pdftotext is the best soln I have tried so far.

• 1 views • link
written by btsui btsui

2 answers

Something like https://github.com/kermitt2/grobid perhaps?

There are lots of PDF mining repos on github that I’d suggest having a mooch through.

I’ve definitely come across libraries for extracting data from graphs too but can’t for the life of me find the repos now...

• 1 views • link
written by Joe Joe

I have installed - but never used - Xapers, which can index pdf files and other sources. I don't know if you are looking for a fancy machine-learning kind of stuff, or simple indexing and searching are good enough for your purposes.

There is also pdfgrep, which could be nice for quickly searching a few pdfs.

• 1 views • link
written by h.mon h.mon

Log in to answer this question.

More posts like this