⚠️There's a newer version (1.0.21) of this package.Take me there.

pubmed.mineR (version 1.0.2.1)

Text mining of PubMed Abstracts

Description

Text mining of PubMed Abstracts (http://www.ncbi.nlm.nih.gov/pubmed). The algorithms are designed for two formats (text and XML) from PubMed

Copy Link

Version

Install

install.packages('pubmed.mineR')

Monthly Downloads

355

Version

1.0.2.1

License

GPL-3

Maintainer

S Ramachandran

Last Published

December 20th, 2014

Functions in pubmed.mineR (1.0.2.1)

common_words_new

R Data containing words which frequently in text

removeabs

To remove abstracts for the query term.

searchabsL

To Search the abstracts of term(s) in a combination mode.

cleanabs-methods

Methods for Function cleanabs

getabs

To get Abstracts for a given term.

getabsT-methods

To Get Abstracts

searchabsT-methods

searchabsT Searching abstracts

Yearwise-methods

Yearwise Year wise extraction of Abstracts

cluster_words

To Find the highest frequency of words within clusters

ready

To Initiate the Classes.

xmlreadabs

To read the abstracts from the PubMed saved in XML format.

R2S4

S4 Converter

whichcluster

To fetch the cluster for words

combineabs-methods

Abstracts Method to Combine Abstracts

get_original_term

To get the original terms from the corpus.

find_intro_conc_html

To find the introduction and conclusion from the abstracts.

combineabs

To combine the abstracts

getabs-methods

getabs To Get abstracts for a term

contextSearch

For Context Search

sendabs-methods

To send the Data into a File

subabs-methods

Getting subabstracts

Pathway_Info

To get the information of pathways for Genes

printabs

To prind the total number of abstracts in an S4 object of class Abstracts , its start and end

Find_conclusion

To find the conclusion from the abstract(s).

xmlgene_atomizations

Gene atomization of xml abstracts.

HGNCdata

R Data containing HGNC data.

HGNC-class

HGNC Class for package.

cos_sim_calc

To calculate the cosine similarity between terms.

getabsT

To get Abstracts for a given term.

tdm_for_lsa

create Term Document Matrix for lsa analysis

To Search abstracts Year wise

SentenceToken

To Tokenize the sentences

word_atomizations

Atomization of words

contextSearch-methods

Method for Context Search

xmlword_atomizations

Word atomizations of abstracts from xml format.

GeneToEntrez

Data containing Entrez Ids

Genewise

To Search the number of abstracts for Genes

gene_atomization

To Extract Genes from the Abstracts

Pathway_Link

To get the Links of the pathways for given genes

uniprotfun

To get information about gene from the UniProt.

wordsclusterview

To view the words in cluster

Abstracts-class

Class "Abstracts" Absract Class

subabs

To find sub-abstracts

cos_sim_calc_boot

cleanabs

To clean the result of searchabsL

R Data containing HGNC2UniprotID data mapping.

Genewise-methods

method to find the abstracts for the given gene.

removeabs-methods

removeabs To remove abstracts of a term from the data.

pubtator_function

function for text annotation uisng online PubTator

input_for_find_intro_conc_html

fetch the abstracts using E-utilities.