Question: Abstract with Mesh Tag

titipata / pubmed_parser

:clipboard: A Python Parser for PubMed Open-Access XML Subset and MEDLINE XML Dataset

http://titipata.github.io/pubmed_parser/

MIT License

559 stars 164 forks source link

Question: Abstract with Mesh Tag #122

Closed shrimonmuke0202 closed 1 month ago

shrimonmuke0202 commented 1 year ago

Hi Team,

I want to download the PubMed abstract which is annotated with MeSH tags. How can I do this?

titipata commented 1 year ago

Hi @shrimonmuke0202, so the simple way is to download the MEDLINE dump and then use the MEDLINE parser (parse_medline_xml) to parse MeSH tags. The tags are separated by ; which you can get Mesh IDs and terms to use later on.

shrimonmuke0202 commented 1 year ago

Thanks for your quick reply @titipata, Are the tokens of text contained in the abstract of any paper exactly matching the MeSH tags? From where can I download the MEDLINE dump?

titipata commented 1 year ago

Are the tokens of text contained in the abstract of any paper exactly matching the MeSH tags? I think MeSH tags are kinda high-level concepts of the given abstract. It may match or not match the abstract.
From where can I download the MEDLINE dump? https://www.nlm.nih.gov/databases/download/pubmed_medline.html (there are multiple ways to download API or bulk download)