Package index • LBDiscover

All functions

abc_model(): Apply the ABC model for literature-based discovery with improved filtering

abc_model_opt(): Optimize ABC model calculations for large matrices

abc_model_sig(): Apply the ABC model with statistical significance testing

abc_timeslice(): Apply time-sliced ABC model for validation

anc_model(): ANC model for literature-based discovery with biomedical term filtering

bitola_model(): Apply BITOLA-style discovery model

calc_bibliometrics(): Calculate basic bibliometric statistics

calc_doc_sim(): Calculate document similarity using TF-IDF and cosine similarity

clear_pubmed_cache(): Clear PubMed cache

cluster_docs(): Cluster documents using K-means

compare_terms(): Compare term frequencies between two corpora

create_citation_net(): Create a citation network from article data

create_comat(): Create co-occurrence matrix without explicit entity type constraints

create_report(): Generate a comprehensive discovery report

create_sparse_comat(): Create a sparse co-occurrence matrix

create_tdm(): Create a term-document matrix from preprocessed text

create_term_document_matrix(): Create a term-document matrix from preprocessed text

detect_lang(): Detect language of text

diversify_abc(): Enforce diversity in ABC model results

enhance_abc_kb(): Enhance ABC results with external knowledge

eval_evidence(): Evaluate literature support for discovery results

export_chord(): Export interactive HTML chord diagram for ABC connections

export_chord_diagram(): Export interactive HTML chord diagram for ABC connections

export_network(): Export ABC results to simple HTML network

extract_entities(): Extract and classify entities from text with multi-domain types

extract_entities_workflow(): Extract entities from text with improved efficiency using only base R

extract_ner(): Perform named entity recognition on text

extract_ngrams(): Extract n-grams from text

extract_terms(): Extract common terms from a corpus

extract_topics(): Apply topic modeling to a corpus

filter_by_type(): Filter a co-occurrence matrix by entity type

find_abc_all(): Find all potential ABC connections

find_similar_docs(): Find similar documents for a given document

find_term(): Find primary term in co-occurrence matrix

gen_report(): Generate comprehensive discovery report

get_dict_cache(): Get dictionary cache environment

get_pmc_fulltext(): Retrieve full text from PubMed Central

get_term_vars(): Extract term variations from text corpus

get_type_dist(): Get entity type distribution from co-occurrence matrix

is_valid_biomedical_entity(): Determine if a term is likely a specific biomedical entity with improved accuracy

load_dictionary(): Load biomedical dictionaries with improved error handling

load_results(): Load saved results from a file

lsi_model(): LSI model with enhanced biomedical term filtering and NLP verification

map_ontology(): Map terms to biomedical ontologies

merge_entities(): Combine and deduplicate entity datasets

merge_results(): Merge multiple search results

min_results(): Ensure minimum results for visualization

ncbi_search(): Search NCBI databases for articles or data

parallel_analysis(): Apply parallel processing for document analysis

perm_test_abc(): Perform randomization test for ABC model

plot_heatmap(): Create heatmap visualization from results

plot_network(): Create network visualization from results

prep_articles(): Prepare articles for report generation

preprocess_text(): Preprocess article text

pubmed_search(): Search PubMed for articles with optimized performance

query_external_api(): Query external biomedical APIs to validate entity types

query_mesh(): Query for MeSH terms using E-utilities

query_umls(): Query UMLS for term information

run_lbd(): Perform comprehensive literature-based discovery without type constraints

safe_diversify(): Diversify ABC results with error handling

sanitize_dictionary(): Enhanced sanitize dictionary function

save_results(): Save search results to a file

segment_sentences(): Perform sentence segmentation on text

valid_entities(): Filter entities to include only valid biomedical terms

validate_abc(): Apply statistical validation to ABC model results with support for large matrices

validate_biomedical_entity(): Validate biomedical entities using BioBERT or other ML models

validate_entity_comprehensive(): Comprehensive entity validation using multiple techniques

validate_entity_with_nlp(): Validate entity types using NLP-based entity recognition with improved accuracy

validate_umls_key(): Validate a UMLS API key

vec_preprocess(): Vectorized preprocessing of text

vis_abc_heatmap(): Create a heatmap of ABC connections

vis_heatmap(): Create an enhanced heatmap of ABC connections

vis_network(): Create an enhanced network visualization of ABC connections

vis_abc_network(): Visualize ABC model results as a network