Leihong Wu
This is a likely match — the affiliation was inferred from OpenAlex, ORCID, and web sources but has not been fully confirmed. Treat with appropriate caution.
Staff Fellow
Also affiliated: Qingdao University (2020); Zhejiang Chinese Medical University (2011); United States Food and Drug Administration (2015–2025); Center for Devices and Radiological Health (2021); Zhejiang University of Science and Technology (2011); Government of the United States of America (2021); Cancer Research And Biostatistics (2024); Food and Drug Administration (2016–2020); Zhejiang University (2010–2014)
Staff Researcher
Research Areas
Biomedical Subjects
Links
Biography and Research Information
OverviewAI-generated summary
Leihong Wu's research focuses on the application of artificial intelligence and machine learning in regulatory science, particularly within the fields of toxicology and bioinformatics. Wu investigates the use of deep learning models for predictive toxicology, analyzing large datasets such as those from the Tox21 initiative to understand the trade-offs between prediction accuracy and model explainability. This work aims to advance the development of more reliable computational methods for assessing chemical and drug safety.
Further research involves the application of natural language processing (NLP) techniques to analyze complex biomedical documents, such as drug labeling information. Wu has explored BERT-based NLP models for classifying drug-induced liver injury risks and has investigated text summarization using advanced models like ChatGPT for drug labeling documents. These efforts contribute to improving the efficiency and accuracy of information extraction from regulatory texts.
Wu's work also extends to genomics and sequencing analysis, with publications evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology and assessing cancer mutation detection methods. Wu leads a research group and has a significant publication record, with 110 total publications and an h-index of 25, indicating a highly cited researcher. Key collaborators include Joshua Xu, Magnus Gray, and Weida Tong, all from the National Center for Toxicological Research.
Metrics
- h-index: 25
- Publications: 110
- Citations: 2,505
Selected Publications
-
GANomics: bridging legacy and modern transcriptomic platforms for clinical applications (2026)
-
Comparative Study of Molecular Descriptors and AI-Based Embeddings for Toxicity Prediction (2025)
-
Benchmarking bias in embeddings of healthcare AI models: using SD-WEAT for detection and measurement across sensitive populations (2025)
-
Assessing the developmental effects of fentanyl and impacts on lipidomic profiling using neural stem cell models (2025)
-
Biomarkers of Neurotoxicity and Disease (2025)
-
Leveraging FDA Labeling Documents and Large Language Model to Enhance Annotation, Profiling, and Classification of Drug Adverse Events with AskFDALabel (2025)
-
Is ChatGPT Ready for Public Use in Organ-Specific Drug Toxicity Research? (2025)
-
Enhancing pharmacogenomic data accessibility and drug safety with large language models: a case study with Llama3.1 (2024)
-
Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods (2024)
-
Description and Validation of a Novel AI Tool, LabelComp, for the Identification of Adverse Event Changes in FDA Labeling (2024)
-
Assessing the performance of large language models in literature screening for pharmacovigilance: a comparative study (2024)
-
SD-WEAT: Towards Robustly Measuring Bias in Input Embeddings (2024)
-
Text summarization with ChatGPT for drug labeling documents (2024)
-
PERform: assessing model performance with predictivity and explainability readiness formula (2024)
-
A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document (2024)
Collaboration Network
Top Collaborators
- Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets
- Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- A Weakly Supervised Deep Learning Framework for Whole Slide Classification to Facilitate Digital Pathology in Animal Study
- RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling
Showing 5 of 18 shared publications
- Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets
- Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science
- BERT-Based Natural Language Processing of Drug Labeling Documents: A Case Study for Classifying Drug-Induced Liver Injury Risk
- Text summarization with ChatGPT for drug labeling documents
- A Weakly Supervised Deep Learning Framework for Whole Slide Classification to Facilitate Digital Pathology in Animal Study
Showing 5 of 15 shared publications
- Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science
- RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling
- A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document
- Classifying Free Texts Into Predefined Sections Using AI in Regulatory Documents: A Case Study with Drug Labeling Documents
- Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods
Showing 5 of 7 shared publications
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- Toward best practice in cancer mutation detection with whole-genome and whole-exome sequencing
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- Text summarization with ChatGPT for drug labeling documents
- Text summarization with ChatGPT for drug labeling documents
- RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling
- Leveraging FDA Labeling Documents and Large Language Model to Enhance Annotation, Profiling, and Classification of Drug Adverse Events with AskFDALabel
- Description and Validation of a Novel AI Tool, LabelComp, for the Identification of Adverse Event Changes in FDA Labeling
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Advancing NGS quality control to enable measurement of actionable mutations in circulating tumor DNA
- BERT-Based Natural Language Processing of Drug Labeling Documents: A Case Study for Classifying Drug-Induced Liver Injury Risk
- Transcriptome analysis reveals lung-specific miRNAs associated with impaired mucociliary clearance induced by cigarette smoke in an in vitro human airway tissue model
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
- Transcriptome analysis reveals lung-specific miRNAs associated with impaired mucociliary clearance induced by cigarette smoke in an in vitro human airway tissue model
- Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning
- Optimized imaging methods for species-level identification of food-contaminating beetles
- Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning
- Optimized imaging methods for species-level identification of food-contaminating beetles
- Accurate species identification of food-contaminating beetles with quality-improved elytral images and deep learning
- Optimized imaging methods for species-level identification of food-contaminating beetles
- Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology
- A verified genomic reference sample for assessing performance of cancer panels detecting small variants of low allele frequency
Similar Researchers
Based on overlapping research topics