Submitting LBDiscover package

[chaoliu-cl]

Submitting Author Name: Chao Liu
Submitting Author Github Handle: @chaoliu-cl
Other Package Authors Github handles: (comma separated, delete if none)
Repository: https://github.com/chaoliu-cl/LBDiscover
Version submitted:
Submission type: Standard
Editor: TBD
Reviewers: TBD

Archive: TBD
Version accepted: TBD
Language: en

---

• Paste the full DESCRIPTION file inside a code block below:

Package: LBDiscover
Title: Literature-Based Discovery Tools for Biomedical Research
Version: 0.1.0
Date: 2025-05-14
Authors@R: 
    person("Chao Liu", email = "chaoliu@cedarville.edu", role = c("aut", "cre"),
           comment = c(ORCID = "0000-0002-9979-8272"))
Description: 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.
License: GPL-3
URL: https://github.com/chaoliu-cl/LBDiscover, http://liu-chao.site/LBDiscover/, https://liu-chao.site/LBDiscover/
BugReports: https://github.com/chaoliu-cl/LBDiscover/issues
Encoding: UTF-8
LazyData: true
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.2
Depends: 
    R (>= 4.0.0)
Imports: 
    httr (>= 1.4.0),
    xml2 (>= 1.3.0),
    igraph (>= 1.2.0),
    Matrix (>= 1.3.0),
    utils,
    stats,
    grDevices,
    graphics,
    tools,
    rentrez (>= 1.2.0),
    jsonlite (>= 1.7.0)
Suggests:
    openxlsx (>= 4.2.0),
    SnowballC (>= 0.7.0),
    visNetwork (>= 2.1.0),
    spacyr (>= 1.2.0),
    parallel,
    digest (>= 0.6.0),
    irlba (>= 2.3.0),
    knitr,
    rmarkdown,
    base64enc,
    reticulate,
    testthat (>= 3.0.0),
    mockery,
    covr,
    htmltools
VignetteBuilder: knitr
Config/testthat/edition: 3

Scope

• Please indicate which category or categories from our package fit policies this package falls under: (Please check an appropriate box below. If you are unsure, we suggest you make a pre-submission inquiry.):

  • data retrieval
  • data extraction
  • data munging
  • data deposition
  • data validation and testing
  • workflow automation
  • version control
  • citation management and bibliometrics
  • scientific software wrappers
  • field and lab reproducibility tools
  • database software bindings
  • geospatial data
  • translation

• Explain how and why the package falls under these categories (briefly, 1-2 sentences):
  Data retrieval: The package provides functions for retrieving scientific articles from PubMed and other NCBI databases. It is a tool for systematically accessing biomedical literature from major research repositories.
  Data extraction: It extracts biomedical entities (diseases, drugs, genes, etc.) from retrieved literature, performing information extraction from scientific texts.
  Citation management and bibliometrics: The package builds co-occurrence networks from literature and applies discovery models (ABC, AnC, LSI, BITOLA) to find hidden connections between concepts, which represents bibliometric analysis for literature-based discovery research.

• Who is the target audience and what are scientific applications of this package?
  Target Audience: LBDiscover is designed for biomedical researchers, bioinformaticians, and data scientists working in literature-based discovery (LBD). The primary users include:

• Biomedical researchers seeking hidden connections between diseases, drugs, and genes

• Pharmaceutical researchers exploring drug repurposing opportunities

• Bioinformaticians building knowledge networks from literature

• Graduate students and academics studying computational approaches to hypothesis generation

Scientific Applications:
The package supports several key research applications:

1. Drug Discovery and Repurposing: LBD has been used extensively in drug development and repurposing as well as predicting adverse drug reactions
2. Disease-Gene Association Discovery: Using literature-based discovery to identify disease candidate genes
3. Biomarker Identification: LBD has been explored as a tool to identify biomarkers for diagnostic and prognostic for diseases
4. Hypothesis Generation: Creating testable scientific hypotheses by connecting disparate pieces of literature
5. Knowledge Network Construction: Building co-occurrence networks to visualize research landscapes

• Are there other R packages that accomplish the same thing? If so, how does yours differ or meet our criteria for best-in-category?
  There are several R packages that overlap with LBDiscover's functionality, but none provide the same comprehensive approach to literature-based discovery:
  Similar Packages and Key Differences:

1. pubmed.mineR
   Overlap: PubMed text mining with functions for data visualization and biomedical entity extraction
   Difference: Focuses on general text mining and clustering rather than implementing specific LBD models like ABC, AnC, LSI, and BITOLA

2. bibliometrix
   Overlap: Comprehensive science mapping analysis with network analysis capabilities and bibliometric workflows
   Difference: Designed for general scientometric analysis across all disciplines, not specifically for biomedical literature-based discovery or implementing LBD-specific algorithms

3. Data Retrieval Packages (rentrez, easyPubMed, RISmed)
   Overlap: All provide interfaces to NCBI/PubMed for retrieving biomedical literature
   Difference: These focus solely on data retrieval and don't perform LBD analysis, entity extraction, or hypothesis generation

How LBDiscover Meets Best-in-Category Criteria:

1. Unique Functionality: LBDiscover is the first R package to specifically implement established LBD models:

• ABC Model: The most basic and widespread type of LBD centered around finding connections between concepts A, B, and C
• BITOLA: An interactive literature-based biomedical discovery support system using semantic prediction
• LSI (Latent Semantic Indexing): A statistical technique for improving information retrieval effectiveness used to assist in literature-based discoveries
• AnC Model: Advanced connection models for more sophisticated discovery patterns

2. Integrated Workflow: Unlike other packages that handle only one aspect (retrieval OR analysis OR visualization), LBDiscover provides a complete workflow from data retrieval through entity extraction to discovery model application and network visualization.
3. Biomedical Specialization: While bibliometrix serves general scientometrics and pubmed.mineR does general text mining, LBDiscover is specifically designed for biomedical literature-based discovery with domain-specific entity recognition (diseases, drugs, genes).
4. Modern Implementation: Recent work has focused on integrating Large Language Models for enhancing Literature-Based Discovery processes, and LBDiscover appears positioned to incorporate such advances while maintaining established methodological foundations.

• (If applicable) Does your package comply with our guidance around Ethics, Data Privacy and Human Subjects Research?
  NA

• If you made a pre-submission inquiry, please paste the link to the corresponding issue, forum post, or other discussion, or @tag the editor you contacted.

• Explain reasons for any pkgcheck items which your package is unable to pass.
  None

Technical checks

Confirm each of the following by checking the box.

• I have read the rOpenSci packaging guide.
• I have read the author guide and I expect to maintain this package for at least 2 years or to find a replacement.

This package:

• does not violate the Terms of Service of any service it interacts with.
• has a CRAN and OSI accepted license.
• contains a README with instructions for installing the development version.
• includes documentation with examples for all functions, created with roxygen2.
• contains a vignette with examples of its essential functions and uses.
• has a test suite.
• has continuous integration, including reporting of test coverage.

Publication options

• Do you intend for this package to go on CRAN?

• Do you intend for this package to go on Bioconductor?

• Do you wish to submit an Applications Article about your package to Methods in Ecology and Evolution? If so:

MEE Options

• The package is novel and will be of interest to the broad readership of the journal.
• The manuscript describing the package is no longer than 3000 words.
• You intend to archive the code for the package in a long-term repository which meets the requirements of the journal (see MEE's Policy on Publishing Code)
• (Scope: Do consider MEE's Aims and Scope for your manuscript. We make no guarantee that your manuscript will be within MEE scope.)
• (Although not required, we strongly recommend having a full manuscript prepared when you submit here.)
• (Please do not submit your package separately to Methods in Ecology and Evolution)

Code of conduct

• I agree to abide by rOpenSci's Code of Conduct during the review process and in maintaining my package should it be accepted.

[ropensci-review-bot]

Thanks for submitting to rOpenSci, our editors and @ropensci-review-bot will reply soon. Type @ropensci-review-bot help for help.

[ropensci-review-bot]

🚀

Editor check started

👋

[ropensci-review-bot]

Checks for LBDiscover (v0.1.0)

git hash: 02f4c075

• ✔️ Package is already on CRAN.
• ✖️ does not have a 'codemeta.json' file.
• ✖️ does not have a 'contributing' file.
• ✔️ uses 'roxygen2'.
• ✔️ 'DESCRIPTION' has a URL field.
• ✔️ 'DESCRIPTION' has a BugReports field.
• ✔️ Package has at least one HTML vignette
• ✖️ These functions do not have examples: [abc_model, anc_model, clear_pubmed_cache, create_report, eval_evidence, extract_entities_workflow, extract_entities, find_term, gen_report, get_dict_cache, get_term_vars, is_valid_biomedical_entity, load_dictionary, lsi_model, merge_entities, min_results, plot_heatmap, plot_network, prep_articles, query_external_api, query_mesh, query_umls, safe_diversify, sanitize_dictionary, valid_entities, validate_biomedical_entity, validate_entity_comprehensive, validate_entity_with_nlp].
• ✔️ Package has continuous integration checks.
• ✖️ Package coverage is 22.4% (should be at least 75%).
• ✖️ All examples use \dontrun{}.
• ✔️ R CMD check found no errors.
• ✔️ R CMD check found no warnings.
• 👀 Some goodpractice linters failed.
• 👀 Function names are duplicated in other packages

Important: All failing checks above must be addressed prior to proceeding

(Checks marked with 👀 may be optionally addressed.)

Package License: GPL-3

---

1. Package Dependencies

Details of Package Dependency Usage (click to open)

The table below tallies all function calls to all packages ('ncalls'), both internal (r-base + recommended, along with the package itself), and external (imported and suggested packages). 'NA' values indicate packages to which no identified calls to R functions could be found. Note that these results are generated by an automated code-tagging system which may not be entirely accurate.

type	package	ncalls
internal	base	2214
internal	LBDiscover	147
internal	methods	9
imports	stats	61
imports	graphics	58
imports	xml2	54
imports	utils	51
imports	httr	33
imports	igraph	19
imports	rentrez	9
imports	Matrix	8
imports	tools	3
imports	grDevices	2
imports	jsonlite	2
suggests	visNetwork	8
suggests	parallel	7
suggests	irlba	2
suggests	reticulate	2
suggests	SnowballC	1
suggests	spacyr	1
suggests	digest	1
suggests	openxlsx	NA
suggests	knitr	NA
suggests	rmarkdown	NA
suggests	base64enc	NA
suggests	testthat	NA
suggests	mockery	NA
suggests	covr	NA
suggests	htmltools	NA
linking_to	NA	NA

Click below for tallies of functions used in each package. Locations of each call within this package may be generated locally by running 's <- pkgstats::pkgstats(<path/to/repo>)', and examining the 'external_calls' table.

base

c (195), character (171), for (126), length (121), data.frame (115), nrow (112), sapply (111), min (83), list (73), max (72), grepl (55), any (54), unique (53), numeric (50), names (39), which (34), paste0 (31), sum (30), if (29), integer (25), rep (25), return (23), seq_along (22), unlist (22), attr (21), ncol (20), paste (19), tryCatch (19), rbind (18), tolower (18), is.na (17), is.null (16), matrix (16), ceiling (15), lapply (15), rownames (15), strsplit (15), table (15), colnames (14), nchar (13), as.numeric (12), seq_len (11), vector (11), match (9), order (9), round (9), regexpr (8), regmatches (8), setdiff (8), as.character (7), drop (7), gregexpr (7), ifelse (7), rowSums (7), sqrt (7), url (7), body (6), plot (6), range (6), sort (6), dim (5), gsub (5), substr (5), t (5), diff (4), grep (4), seq (4), sprintf (4), switch (4), col (3), diag (3), emptyenv (3), environment (3), file (3), log (3), logical (3), new.env (3), row (3), tapply (3), tempfile (3), all (2), apply (2), by (2), colSums (2), dimnames (2), do.call (2), mean (2), outer (2), row.names (2), sub (2), Sys.time (2), try (2), abs (1), as.data.frame (1), cat (1), colMeans (1), difftime (1), duplicated (1), expression (1), file.path (1), floor (1), format (1), interactive (1), match.arg (1), merge (1), mode (1), packageEvent (1), setHook (1), suppressMessages (1), system.file (1), units (1), unname (1), version (1), which.max (1)

LBDiscover

retry_api_call (16), create_comat (4), load_dictionary (4), pubmed_search (4), string_similarity (4), throttle_api (4), abc_model (3), authenticate_umls (3), cluster_docs (3), count_corpus_terms (3), extract_entities (3), get_pubmed_cache (3), tokenize_text (3), vec_preprocess (3), calc_doc_sim (2), calculate_score (2), create_cache_key (2), create_dummy_dictionary (2), create_term_document_matrix (2), diversify_abc (2), extract_text_ngrams (2), get_color_palette (2), get_dict_cache (2), get_service_ticket (2), is_valid_biomedical_entity (2), load_dict_single (2), load_from_mesh (2), load_from_umls (2), load_mesh_terms_from_pubmed (2), process_mesh_xml (2), abc_model_opt (1), abc_model_sig (1), abc_timeslice (1), add_statistical_significance (1), alternative_validation (1), anc_model (1), apply_bitola_flexible (1), apply_correction (1), b_term_type_filter (1), bitola_model (1), calc_bibliometrics (1), clear_pubmed_cache (1), compare_terms (1), create_citation_net (1), create_report (1), create_single_heatmap (1), create_sparse_comat (1), create_tdm (1), create_vis_heatmap (1), detect_lang (1), diversify_b_terms (1), diversify_c_paths (1), enhance_abc_kb (1), eval_evidence (1), export_chord (1), export_chord_diagram (1), export_network (1), extract_entities_workflow (1), extract_mesh_from_text (1), extract_ner (1), extract_ngrams (1), extract_terms (1), extract_topics (1), fetch_and_parse_gene (1), fetch_and_parse_pmc (1), fetch_and_parse_protein (1), fetch_and_parse_pubmed (1), filter_by_type (1), filter_terms_for_abc_model (1), find_abc_all (1), find_similar_docs (1), find_term (1), gen_report (1), get_pmc_fulltext (1), get_term_vars (1), get_type_dist (1), get_umls_semantic_types (1), is_valid_type (1), list_to_df (1), load_results (1), parse_pubmed_xml (1), preprocess_text (1), process_batch (1), split_into_sentences (1), split_text (1)

stats

df (19), terms (16), p.adjust (5), phyper (4), kmeans (3), profile (3), aggregate (2), runif (2), setNames (2), smooth (2), complete.cases (1), dist (1), pt (1)

graphics

text (29), par (13), title (8), layout (6), arrows (2)

xml2

xml_find_first (19), xml_text (19), xml_find_all (10), read_xml (4), xml_attr (1), xml_name (1)

utils

txtProgressBar (40), read.csv (4), adist (2), write.csv (2), de (1), head (1), URLencode (1)

httr

content (18), GET (8), POST (5), headers (2)

igraph

graph_from_data_frame (12), layout_with_fr (6), degree (1)

methods

new (9)

rentrez

entrez_link (3), entrez_search (3), entrez_fetch (2), entrez_summary (1)

Matrix

t (4), diag (2), sparseMatrix (2)

visNetwork

visEdges (2), visGroups (2), visNetwork (2), visLayout (1), visSave (1)

parallel

clusterExport (3), parLapply (2), detectCores (1), makeCluster (1)

tools

file_ext (3)

grDevices

colorRampPalette (1), rainbow (1)

irlba

irlba (2)

jsonlite

fromJSON (2)

reticulate

import (2)

digest

digest (1)

SnowballC

wordStem (1)

spacyr

spacy_parse (1)

---

2. Statistical Properties

This package features some noteworthy statistical properties which may need to be clarified by a handling editor prior to progressing.

Details of statistical properties (click to open)

The package has:

• code in R (100% in 13 files) and
• 1 authors
• 3 vignettes
• no internal data file
• 11 imported packages
• 105 exported functions (median 47 lines of code)
• 146 non-exported functions in R (median 48 lines of code)

---

Statistical properties of package structure as distributional percentiles in relation to all current CRAN packages
The following terminology is used:

• loc = "Lines of Code"
• fn = "function"
• exp/not_exp = exported / not exported

All parameters are explained as tooltips in the locally-rendered HTML version of this report generated by the checks_to_markdown() function

The final measure (fn_call_network_size) is the total number of calls between functions (in R), or more abstract relationships between code objects in other languages. Values are flagged as "noteworthy" when they lie in the upper or lower 5th percentile.

measure	value	percentile	noteworthy
files_R	13	65.8
files_inst	4	97.1
files_vignettes	3	89.3
files_tests	9	84.9
loc_R	8759	97.6	TRUE
loc_inst	991	77.5
loc_vignettes	925	88.8
loc_tests	1294	86.6
num_vignettes	3	91.0
n_fns_r	251	91.3
n_fns_r_exported	105	95.3	TRUE
n_fns_r_not_exported	146	88.0
n_fns_per_file_r	9	87.6
num_params_per_fn	4	51.1
loc_per_fn_r	48	88.7
loc_per_fn_r_exp	47	77.7
loc_per_fn_r_not_exp	48	89.6
rel_whitespace_R	24	98.5	TRUE
rel_whitespace_inst	23	81.5
rel_whitespace_vignettes	25	85.1
rel_whitespace_tests	31	91.6
doclines_per_fn_exp	20	15.3
doclines_per_fn_not_exp	0	0.0	TRUE
fn_call_network_size	157	84.3

---

2a. Network visualisation

Click to see the interactive network visualisation of calls between objects in package

---

3. goodpractice and other checks

Details of goodpractice checks (click to open)

3a. Continuous Integration Badges

GitHub Workflow Results

id	name	conclusion	sha	run_number	date
17965843714	pages build and deployment	success	04c683	7	2025-09-24
17965695551	pkgdown.yaml	success	a008bc	4	2025-09-24
17965695558	R-CMD-check.yaml	success	a008bc	4	2025-09-24

---

3b. goodpractice results

R CMD check with rcmdcheck

R CMD check generated the following check_fails:

1. cyclocomp
2. no_description_date

Test coverage with covr

Package coverage: 22.42

The following files are not completely covered by tests:

file	coverage
R/abc_model.R	22.9%
R/comprehensive_summary.R	0%
R/heatmap_visualization.R	6.86%
R/performance_optimalization.R	19.75%
R/pubmed_search.R	0%
R/queries.R	15.5%
R/text_preprocessing.R	0%
R/utils.R	1.93%
R/visualization.R	49.63%
R/zzz.R	10%

Cyclocomplexity with cyclocomp

The following functions have cyclocomplexity >= 15:

function	cyclocomplexity
is_valid_biomedical_entity	161
extract_entities_workflow	145
abc_model	129
sanitize_dictionary	100
vis_heatmap	99
vis_network	77
load_from_umls	71
validate_entity_with_nlp	57
extract_entities	54
pubmed_search	46
load_from_mesh	45
parse_pubmed_xml	45
create_comat	43
create_report	43
run_lbd	41
anc_model	38
load_dictionary	37
extract_ner	35
vis_abc_heatmap	35
export_chord_diagram	33
process_mesh_xml	32
validate_abc	29
abc_model_sig	27
lsi_model	27
abc_timeslice	26
map_ontology	26
shadowtext	26
abc_model_opt	24
eval_evidence	24
process_mesh_chunks	24
export_network	23
query_umls	23
apply_bitola_flexible	22
merge_entities	21
vis_abc_network	21
get_pmc_fulltext	20
validate_entity_comprehensive	20
vec_preprocess	20
bitola_model	19
create_sparse_comat	19
fetch_and_parse_pmc	19
find_abc_all	19
ncbi_search	19
cluster_docs	18
create_citation_net	17
load_mesh_terms_from_pubmed	17
create_tdm	16
create_term_document_matrix	16
extract_topics	16
preprocess_text	16
compare_terms	15
min_results	15

Static code analyses with lintr

lintr found no issues with this package!

---

4. Other Checks

Details of other checks (click to open)

✖️ The following 10 function names are duplicated in other packages:

• • create_report from DataExplorer, prodigenr, reporter
• • extract_entities from medExtractR
• • load_dictionary from ricu
• • merge_results from climwin
• • ncbi_search from taxize
• • parallel_analysis from kim
• • plot_heatmap from dendroTools, dynplot, greatR, MitoHEAR, omu, Plasmidprofiler, RolWinMulCor, romic
• • plot_network from cape, dbnR, HeteroGGM, immcp, imsig, LSVAR, SeqNet, SubgrPlots
• • save_results from data.validator
• • vis_heatmap from immunarch

---

Package Versions

package	version
pkgstats	0.2.0.66
pkgcheck	0.1.2.230

---

Editor-in-Chief Instructions:

Processing may not proceed until the items marked with ✖️ have been resolved.

[ldecicco-USGS]

Thanks for the submission @chaoliu-cl ! The package sounds really neat. Let me know when you've been able to address the✖️ found in the check.

I'd be a little concerned about those high complexity values found in the goodpractices checks. Those files and functions are huge and look like there are logical places you could split up the code. One example might be to put all of the static lists in a sysdata.rda file.