PubMed_mining

##Script_pubmed_mining In this script, I used rentrez package for mining articles with terms of interest. The query to Pubmed is restricted by 200 entities, so I split the query by Chanks. The result is a dataframe with titles, IDs, authors names, and abstracts ##article_search_script the input data for this script is an output table from GePI http://gepi.coling.uni-jena.de/, which helps to find the gene and protein interactions for the gene of interest. I converted all article ids to pubmed ids. Next, I retrieved from PubMed abstracts for these articles, then I made the corpora based on these articles and tried to cluster them with adjutant packages based on the content ##script_references_analysis Sometimes I review the articles and it's crucial to quickly observe the references, that authors used in the manuscript