Leihong Wu Data-verified

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

High Impact

Staff Fellow

NCTR

Last publication 2025 Last refreshed 2026-05-23

staff

25 h-index 109 pubs 2,393 cited

Research Areas

Links

ORCID Research Group

OverviewAI-generated summary

Leihong Wu, a Staff Fellow at the National Center for Toxicological Research, focuses on the application of artificial intelligence (AI) within regulatory science. Wu's research interests encompass general bioinformatics, genomics and sequencing analysis, deep learning, predictive toxicology, and the analysis of drug labeling documents for adverse event identification.

Wu has investigated the analytical validity of circulating tumor DNA sequencing assays for precision oncology and contributed to establishing best practices for cancer mutation detection using whole-genome and whole-exome sequencing. Further work has explored the balance between predictivity and explainability in machine-learning models for predictive toxicology, utilizing data from the Tox21 initiative. Wu has also examined bias in AI for regulatory science through a narrative literature review and applied BERT-based natural language processing to drug labeling documents to classify risks such as drug-induced liver injury. Recent work includes the use of ChatGPT for text summarization of drug labeling documents.

Wu is designated as a highly cited researcher, with a h-index of 25 and over 2,300 citations across 109 publications. Key collaborators include Joshua Xu, Magnus Gray, and Weida Tong, all from the National Center for Toxicological Research, with whom Wu has multiple shared publications.

Metrics

h-index: 25
Publications: 109
Citations: 2,393

Selected Publications

Comparative Study of Molecular Descriptors and AI-Based Embeddings for Toxicity Prediction (2025)

DOI OpenAlex
Assessing the developmental effects of fentanyl and impacts on lipidomic profiling using neural stem cell models (2025)

2 citations DOI OpenAlex
Biomarkers of Neurotoxicity and Disease (2025)

1 citation DOI OpenAlex
Leveraging FDA Labeling Documents and Large Language Model to Enhance Annotation, Profiling, and Classification of Drug Adverse Events with AskFDALabel (2025)

9 citations DOI OpenAlex
Is ChatGPT Ready for Public Use in Organ-Specific Drug Toxicity Research? (2025)

2 citations DOI OpenAlex
Enhancing pharmacogenomic data accessibility and drug safety with large language models: a case study with Llama3.1 (2024)

4 citations DOI OpenAlex
Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods (2024)

2 citations DOI OpenAlex
Description and Validation of a Novel AI Tool, LabelComp, for the Identification of Adverse Event Changes in FDA Labeling (2024)

5 citations DOI OpenAlex
Assessing the performance of large language models in literature screening for pharmacovigilance: a comparative study (2024)

8 citations DOI OpenAlex
SD-WEAT: Towards Robustly Measuring Bias in Input Embeddings (2024)

DOI OpenAlex
Text summarization with ChatGPT for drug labeling documents (2024)

13 citations DOI OpenAlex
PERform: assessing model performance with predictivity and explainability readiness formula (2024)

2 citations DOI OpenAlex
A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document (2024)

11 citations DOI OpenAlex
RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling (2023)

12 citations DOI OpenAlex
Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science (2023)

26 citations DOI OpenAlex