Package: LBDiscover 0.1.0

LBDiscover: Literature-Based Discovery Tools for Biomedical Research

A suite of tools for literature-based discovery in biomedical research. Provides functions for retrieving scientific articles from PubMed and other NCBI databases, extracting biomedical entities (diseases, drugs, genes, etc.), building co-occurrence networks, and applying various discovery models including ABC, AnC, LSI, and BITOLA. The package also includes visualization tools for exploring discovered connections.

Authors:Chao Liu [aut, cre]

LBDiscover_0.1.0.tar.gz
LBDiscover_0.1.0.zip(r-4.7-any)LBDiscover_0.1.0.zip(r-4.6-any)LBDiscover_0.1.0.zip(r-4.5-any)
LBDiscover_0.1.0.tgz(r-4.6-any)LBDiscover_0.1.0.tgz(r-4.5-any)
LBDiscover_0.1.0.tar.gz(r-4.7-any)LBDiscover_0.1.0.tar.gz(r-4.6-any)
LBDiscover_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
LBDiscover/json (API)

# Install 'LBDiscover' in R:
install.packages('LBDiscover', repos = c('https://chaoliu-cl.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/chaoliu-cl/lbdiscover/issues

Pkgdown/docs site:https://liu-chao.site

On CRAN:

Conda:

4.18 score 205 downloads 70 exports 22 dependencies

Last updated from:60e965ad1f. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develOK351
source / vignettesOK676
linux-releaseOK351
macos-releaseOK328
macos-oldrelOK302
windows-develOK281
windows-releaseOK308
windows-oldrelOK314
wasm-releaseOK143

Exports:abc_modelabc_model_optabc_model_sigabc_timesliceanc_modelbitola_modelcalc_bibliometricscalc_doc_simclear_pubmed_cachecluster_docscompare_termscreate_citation_netcreate_comatcreate_reportcreate_sparse_comatcreate_tdmcreate_term_document_matrixdetect_langdiversify_abcenhance_abc_kbeval_evidenceexport_chordexport_chord_diagramexport_networkextract_entitiesextract_entities_workflowextract_nerextract_ngramsextract_termsextract_topicsfilter_by_typefind_abc_allfind_similar_docsfind_termgen_reportget_dict_cacheget_pmc_fulltextget_term_varsget_type_distis_valid_biomedical_entityload_dictionaryload_resultslsi_modelmap_ontologymerge_entitiesmerge_resultsmin_resultsncbi_searchparallel_analysisperm_test_abcplot_heatmapplot_networkprep_articlespreprocess_textpubmed_searchquery_meshquery_umlsrun_lbdsafe_diversifysanitize_dictionarysave_resultssegment_sentencesvalid_entitiesvalidate_abcvalidate_umls_keyvec_preprocessvis_abc_heatmapvis_abc_networkvis_heatmapvis_network

Dependencies:askpassclicpp11curlgluehttrigraphjsonlitelatticelifecyclemagrittrMatrixmimeopensslpkgconfigR6rentrezrlangsysvctrsXMLxml2

Getting Started with Literature-Based Discovery
Introduction | Installation | Basic Workflow | Example: Exploring Migraine Research | 1. Load the package | 2. Define the primary term of interest | 3. Retrieve publications | 4. Extract variations of the primary term | 5. Preprocess text data | 6. Create a custom dictionary | 7. Extract biomedical entities | 8. Create co-occurrence matrix | 9. Apply the improved ABC model | 10. Apply statistical validation to the results | 11. Diversify and ensure minimum results | 12. Visualize the results | 13. Create interactive visualizations | 14. Evaluate literature support and generate report | Interactive Visualizations and Report | Embedding HTML Report in the Vignette | Direct Links to Interactive Visualizations | Advanced Features | Conclusion
Rendered fromIntro_to_Literature-Based_Discovery.Rmdusingknitr::rmarkdown

Last update: 2025-09-27
Started: 2025-05-14

Text Preprocessing and Entity Extraction
Introduction | Loading the Package | Data Retrieval | Basic Text Preprocessing | Optimized Preprocessing for Large Datasets | Advanced Text Analysis | N-gram Extraction | Sentence Segmentation | Language Detection | Entity Extraction | Loading Entity Dictionaries | Basic Entity Extraction | Complete Entity Extraction Workflow | Customizing Entity Extraction | Dictionary Sanitization | Mapping Terms to Biomedical Ontologies | Topic Modeling
Rendered fromText_Preprocessing.Rmdusingknitr::rmarkdown

Last update: 2025-05-14
Started: 2025-05-14

Working with Discovery Models
Discovery Models in Literature-Based Discovery | Overview of Discovery Models | Setup and Data Preparation | 1. Classic ABC Model | Statistical Validation of ABC Results | 2. AnC Model | 3. BITOLA Model | 4. LSI Model (Latent Semantic Indexing) | Comparing Results from Different Models
Rendered fromWork_with_Discovery_Models.Rmdusingknitr::rmarkdown

Last update: 2025-05-14
Started: 2025-05-14

Readme and manuals

Help Manual

Help pageTopics
Apply the ABC model for literature-based discovery with improved filteringabc_model
Optimize ABC model calculations for large matricesabc_model_opt
Apply the ABC model with statistical significance testingabc_model_sig
Apply time-sliced ABC model for validationabc_timeslice
ANC model for literature-based discovery with biomedical term filteringanc_model
Apply BITOLA-style discovery modelbitola_model
Calculate basic bibliometric statisticscalc_bibliometrics
Calculate document similarity using TF-IDF and cosine similaritycalc_doc_sim
Clear PubMed cacheclear_pubmed_cache
Cluster documents using K-meanscluster_docs
Compare term frequencies between two corporacompare_terms
Create a citation network from article datacreate_citation_net
Create co-occurrence matrix without explicit entity type constraintscreate_comat
Generate a comprehensive discovery reportcreate_report
Create a sparse co-occurrence matrixcreate_sparse_comat
Create a term-document matrix from preprocessed textcreate_tdm
Create a term-document matrix from preprocessed textcreate_term_document_matrix
Detect language of textdetect_lang
Enforce diversity in ABC model resultsdiversify_abc
Enhance ABC results with external knowledgeenhance_abc_kb
Evaluate literature support for discovery resultseval_evidence
Export interactive HTML chord diagram for ABC connectionsexport_chord
Export interactive HTML chord diagram for ABC connectionsexport_chord_diagram
Export ABC results to simple HTML networkexport_network
Extract and classify entities from text with multi-domain typesextract_entities
Extract entities from text with improved efficiency using only base Rextract_entities_workflow
Perform named entity recognition on textextract_ner
Extract n-grams from textextract_ngrams
Extract common terms from a corpusextract_terms
Apply topic modeling to a corpusextract_topics
Filter a co-occurrence matrix by entity typefilter_by_type
Find all potential ABC connectionsfind_abc_all
Find similar documents for a given documentfind_similar_docs
Find primary term in co-occurrence matrixfind_term
Generate comprehensive discovery reportgen_report
Get dictionary cache environmentget_dict_cache
Retrieve full text from PubMed Centralget_pmc_fulltext
Extract term variations from text corpusget_term_vars
Get entity type distribution from co-occurrence matrixget_type_dist
Determine if a term is likely a specific biomedical entity with improved accuracyis_valid_biomedical_entity
Load biomedical dictionaries with improved error handlingload_dictionary
Load saved results from a fileload_results
LSI model with enhanced biomedical term filtering and NLP verificationlsi_model
Map terms to biomedical ontologiesmap_ontology
Combine and deduplicate entity datasetsmerge_entities
Merge multiple search resultsmerge_results
Ensure minimum results for visualizationmin_results
Search NCBI databases for articles or datancbi_search
Apply parallel processing for document analysisparallel_analysis
Perform randomization test for ABC modelperm_test_abc
Create heatmap visualization from resultsplot_heatmap
Create network visualization from resultsplot_network
Prepare articles for report generationprep_articles
Preprocess article textpreprocess_text
Search PubMed for articles with optimized performancepubmed_search
Query external biomedical APIs to validate entity typesquery_external_api
Query for MeSH terms using E-utilitiesquery_mesh
Query UMLS for term informationquery_umls
Perform comprehensive literature-based discovery without type constraintsrun_lbd
Diversify ABC results with error handlingsafe_diversify
Enhanced sanitize dictionary functionsanitize_dictionary
Save search results to a filesave_results
Perform sentence segmentation on textsegment_sentences
Filter entities to include only valid biomedical termsvalid_entities
Apply statistical validation to ABC model results with support for large matricesvalidate_abc
Validate biomedical entities using BioBERT or other ML modelsvalidate_biomedical_entity
Comprehensive entity validation using multiple techniquesvalidate_entity_comprehensive
Validate entity types using NLP-based entity recognition with improved accuracyvalidate_entity_with_nlp
Validate a UMLS API keyvalidate_umls_key
Vectorized preprocessing of textvec_preprocess
Create a heatmap of ABC connectionsvis_abc_heatmap
Create an enhanced heatmap of ABC connectionsvis_heatmap
Create an enhanced network visualization of ABC connectionsvis_network
Visualize ABC model results as a networkvisualize_abc_network vis_abc_network