LIDR-TB: large language model-integrated platform for traceable drug repurposing in tuberculosis

{"Tuberculosis":[0],"(TB)":[1],"remains":[2],"a":[3,18,53,69,81,97,113,149,189,203,218,228],"global":[4],"challenge":[5],"exacerbated":[6],"by":[7,29],"the":[8,30,106,155,186],"ongoing":[9],"emergence":[10],"of":[11,32,188,235],"drug-resistant":[12],"strains.":[13],"Although":[14],"drug":[15,60,214,268],"repurposing":[16,61,269],"offers":[17],"cost-effective":[19],"strategy":[20],"to":[21,123,128,161,174,241],"expedite":[22],"therapeutic":[23],"discovery,":[24,256],"its":[25],"application":[26],"is":[27],"impeded":[28],"lack":[31,187],"unified,":[33,190],"disease-specific":[34],"frameworks":[35],"that":[36,73,101,116],"integrate":[37],"fragmented":[38],"chemical":[39,76,197],"and":[40,77,93,96,143,198,210,227,253,263],"biological":[41,78,94,199],"data":[42,251],"from":[43],"heterogeneous":[44,75,196],"sources.":[45],"Herein,":[46],"we":[47,147],"developed":[48],"LIDR-TB":[49,201],"(":[50],"http://lidrtb.sysbio.org.cn":[51],"),":[52],"TB-focused,":[54],"LLM-integrated":[55],"informatics":[56,192],"platform":[57,64,205,248],"for":[58,89,194,206,261],"traceable":[59],"research.":[62],"The":[63],"integrates":[65,217],"three":[66],"core":[67],"components:":[68],"curated":[70,107],"knowledge":[71,108,207,220,255],"base":[72],"consolidates":[74],"evidence":[79,259],"into":[80],"graph-structured":[82,219],"representation;":[83],"an":[84,222],"interactive":[85,223],"network":[86,224],"visualization":[87,225],"module":[88],"exploring":[90],"multi-layered":[91],"molecular":[92],"relationships;":[95],"RAG-based":[98,229],"question-answering":[99,230],"model":[100],"anchors":[102],"LLM":[103,156],"outputs":[104],"within":[105],"base.":[109],"These":[110],"components":[111],"form":[112],"unified":[114],"workflow":[115],"supports":[117],"cross-module":[118],"verification,":[119],"allowing":[120],"generative":[121],"responses":[122,237],"be":[124],"directly":[125],"traced":[126],"back":[127],"raw":[129],"experimental":[130,243],"records.":[131],"Benchmarking":[132],"on":[133],"expert-curated":[134],"evaluation":[135],"suites":[136],"showed":[137],"promising":[138],"results":[139],"in":[140,167,178,213,267],"semantic":[141,159],"understanding":[142],"answer":[144,176],"fidelity.":[145],"Notably,":[146],"observed":[148],"potential":[150],"\\"semantic":[151],"compensatory":[152],"effect\\",":[153],"wherein":[154],"leverages":[157],"latent":[158],"context":[160],"partially":[162],"offset":[163],"structural":[164],"parsing":[165],"misalignments":[166],"some":[168],"cases.":[169],"This":[170,245],"observation":[171],"may":[172],"contribute":[173],"maintaining":[175],"quality":[177],"complex":[179],"biomedical":[180],"queries.":[181],"Scientific":[182],"contribution":[183],"To":[184],"address":[185],"domain-specific":[191],"framework":[193],"integrating":[195],"data,":[200],"provides":[202],"tuberculosis-focused":[204],"exploration,":[208],"visualization,":[209],"evidence-grounded":[211],"retrieval":[212],"repurposing.":[215],"It":[216],"base,":[221],"module,":[226],"model,":[231],"enabling":[232],"multi-level":[233],"verification":[234],"generated":[236],"through":[238],"direct":[239],"linkage":[240],"underlying":[242],"evidence.":[244],"openly":[246],"accessible":[247],"advances":[249],"chemical-biological":[250],"integration":[252],"cheminformatics-driven":[254],"facilitating":[257],"systematic":[258],"exploration":[260],"TB":[262],"related":[264],"infectious":[265],"diseases":[266],"studies.":[270]}

Authors

Institutions

Publication Details

Journal
Journal of Cheminformatics
Published
2026-09-18
DOI
https://doi.org/10.1186/s13321-026-01305-3
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

LIDR-TB: large language model-integrated platform for traceable drug repurposing in tuberculosis

Bairong Shen, Jie Song, Xingyun Liu, Jiajia Dong et al.
Journal of Cheminformatics
Computational Drug Discovery Methods
article

LIDR-TB: large language model-integrated platform for traceable drug repurposing in tuberculosis

Bairong Shen, Jie Song, Xingyun Liu, Jiajia Dong, Hui Zong, Xin Zheng, Jiao Wang, Amin Ullah, Xiaoyu Li, ShanShan Hu
article en

Abstract

Tuberculosis (TB) remains a global challenge exacerbated by the ongoing emergence of drug-resistant strains. Although drug repurposing offers a cost-effective strategy to expedite therapeutic discovery, its application is impeded by the lack of unified, disease-specific frameworks that integrate fragmented chemical and biological data from heterogeneous sources. Herein, we developed LIDR-TB ( http://lidrtb.sysbio.org.cn ), a TB-focused, LLM-integrated informatics platform for traceable drug repurposing research. The platform integrates three core components: a curated knowledge base that consolidates heterogeneous chemical and biological evidence into a graph-structured representation; an interactive network visualization module for exploring multi-layered molecular and biological relationships; and a RAG-based question-answering model that anchors LLM outputs within the curated knowledge base. These components form a unified workflow that supports cross-module verification, allowing generative responses to be directly traced back to raw experimental records. Benchmarking on expert-curated evaluation suites showed promising results in semantic understanding and answer fidelity. Notably, we observed a potential "semantic compensatory effect", wherein the LLM leverages latent semantic context to partially offset structural parsing misalignments in some cases. This observation may contribute to maintaining answer quality in complex biomedical queries. Scientific contribution To address the lack of a unified, domain-specific informatics framework for integrating heterogeneous chemical and biological data, LIDR-TB provides a tuberculosis-focused platform for knowledge exploration, visualization, and evidence-grounded retrieval in drug repurposing. It integrates a graph-structured knowledge base, an interactive network visualization module, and a RAG-based question-answering model, enabling multi-level verification of generated responses through direct linkage to underlying experimental evidence. This openly accessible platform advances chemical-biological data integration and cheminformatics-driven knowledge discovery, facilitating systematic evidence exploration for TB and related infectious diseases in drug repurposing studies.

Journal of Cheminformatics
Army Medical University (CN), Sichuan University (CN), West China Hospital of Sichuan University (CN), Southwest Hospital (CN)
National Natural Science Foundation of China
Good health and well-being
Openalex Percentile: Top 9%
Computational Drug Discovery Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.