Joshua Xu Ph.D.
R2R Branch Chief, SBRBPAS Expert — Division of Bioinformatics and Biostatistics
Joshua Xu, Ph.D.
(870) 543-7121
NCTRResearch@fda.hhs.gov
Back to NCTR Principal Investigators page
About | Publications | Lab Members
Background
Dr. Joshua Xu obtained a Ph.D. in electrical engineering from Texas A&M University in 1999, specializing in medical image analysis. He worked as a senior software engineer for a congressionally funded mobile telemedicine program at the Texas Center for Applied Technology, an R&D center of the Texas A&M University System. In 2007, he joined ICF International as an onsite contractor for FDA's National Center for Toxicological Research (NCTR). He led the development of SNPTrack, an integrated solution for managing, analyzing, and interpreting genetic association study data and used it to support the FDA’s Voluntary Exploratory Data Submission program. In 2012, Dr. Xu joined the newly formed NCTR Division of Bioinformatics and Biostatistics and became the branch chief for Research-to-Review and Return (R2R) in 2018. His research focused on benchmarking emerging genomics technologies for precision medicine, image analysis for food contamination detection, and adapting Natural Language Processing (NLP) techniques for regulatory documents review. He oversees the R2R program to translate regulatory science research findings and integrate advanced AI technologies into regulatory applications. Below is a list of selected awards and recognitions Dr. Xu has received:
- 2022 FDA Chief Scientist Publication Award for "Basic, Translational or Applied Science for the liquid biopsy evaluation paper in Nature Biotechnology"
- 2022 FDA Excellence in Analytical Science Award (group) for "Sequencing Quality Control Phase 2 (SEQC2) project"
- 2016 FDA Commissioner’s Special Citation for "Cross-Center Bioinformatics Projects Benefiting Regulatory Business Processes"
- 2016 FDA Outstanding Inter-Center Scientific Collaboration Award (group) for "Developed a bioinformatics tool and relational database for FDA drug labeling to aid regulatory decision making and drug review in advancing translational and regulatory sciences"
- 2016 FDA Chief Scientist Publication Award (group) for "Data Methods, Analysis, and Study Design"
- 2015 FDA Chief Scientist Publication Award (group) for "Basic, Translational or Applied Science"
Research Interests
Dr. Xu is an expert in next-generation sequencing (NGS) data analysis, image analysis, artificial intelligence, and informatics system development. His recent focus has been with the FDA-led Sequencing Quality Control Phase 2 (SEQC2) project to evaluate the technical reliabilities and scientific applications of NGS technologies. He led the SEQC2 Oncopanel Sequencing Working Group to assess the reproducibility and detection sensitivity of oncology panel sequencing including liquid biopsy tests that analyze circulating tumor DNA in blood to advance precision medicine. The working group consisted of over 200 participants from academia, government agencies, and industry including 8 companies providing oncopanels and 30 testing laboratories. Post-SEQC2 research is centered around indel calling from oncopanel sequencing data and evaluation of targeted RNA-sequencing for the detection of fusion genes and small variants.
Besides continued research of assessing NGS and related bioinformatics methods to support FDA’s oversight of NGS-based diagnostic tests, Dr. Xu has been developing and adopting NLP methods for regulatory document review and developing image analysis algorithms for digital pathology and food contamination detection. More specifically, he oversees two initiatives under the NCTR-led AI4TOX programs: BERTox and PathologAI. The BERTox initiative consists of multiple projects that apply the large language models (LLMs) such as BERT and GPT to facilitate analysis of FDA documents and public literature for improved efficiency and accuracy of information retrieval and toxicity assessment. The PathologAI project aims to develop an effective and accurate framework for the analysis of histopathological data from animal studies to advance digital pathology in preclinical application.
Professional Societies/National and International Groups
Arkansas Bioinformatics Consortium
Member
2015 – Present
Annual Conference Organizing Committee, 2023 – 2024
Society of Toxicology
Member
2023 – Present
The MidSouth Computational Biology and Bioinformatics Society
Member
2009 – Present
Conference Program Chair, 2022
Massive Analysis and Quality Control (MAQC) Society
Member
2017 – present
Executive Secretary, 2021 – present
Conference Program Co-chair, 2022
Select Publications
Publication titles are linked to text abstracts on PubMed.
Towards Accurate Indel Calling for Oncopanel Sequencing Through an International Pipeline Competition at precisionFDA.
Gong B., Lababidi S., Kusko R., et al.
Sci Rep. 2024, 14, 8165. https://doi.org/10.1038/s41598-024-58573-y.
A Framework Enabling LLMs into Regulatory Environment for Transparency and Trustworthiness and its Application to Drug Labeling Document.
Wu L., Xu J., Thakkar S., Gray M., Qu Y., Li D., and Tong W.
Regulatory Toxicology and Pharmacology. 2024, 149, 105613. doi:10.1016/j.yrtph.2024.105613.
Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science.
Gray M., Samala R., Liu Q., Skiles D., Xu J., Tong W., and Wu L.
Clinical Pharmacology and Therapeutics. 2024. doi:10.1002/cpt.3117. PMID: 38018360.
Quartet RNA Reference Materials Improve the Quality of Transcriptomic Data Through Ratio-Based Profiling.
Yu Y., Hou W., Liu Y. et al.
Nat Biotechnol. 2024. doi:10.1038/s41587-023-01867-9.
RxBERT: Enhancing Drug Labeling Text Mining and Analysis with AI Language Modeling.
Wu L., Gray M., Dang O., Xu J., Fang H., and Tong W.
Experimental Biology and Medicine. 2023, 248(21):1937-1943. doi:10.1177/15353702231220669.
Classifying Free Texts Into Predefined Sections Using AI in Regulatory Documents: A Case Study with Drug Labeling Documents.
Gray M., Xu J., Tong W., and Wu L.
Chem Res Toxicol. 2023, 36(8):1290-1299. doi:10.1021/acs.chemrestox.3c00028. Epub 2023 Jul 24.
A Weakly Supervised Deep Learning Framework for Whole Slide Classification to Facilitate Digital Pathology in Animal Study.
Bussola N., Xu J., Wu L., Gorini L., Zhang Y., Furlanello C., and Tong W.
Chem Res Toxicol. 2023, 36(8):1321-1331. doi:10.1021/acs.chemrestox.3c00058. Epub 2023 Aug 4.
Towards Accurate and Reliable Resolution of Structural Variants for Clinical Diagnosis.
Liu Z., Roberts R., Mercer T.R., Xu J., Sedlazeck F.J., and Tong W.
Genome Biology. 2022, 23 (1), 68.
Cross-Oncopanel Study Reveals High Sensitivity and Accuracy with Overall Analytical Performance Depending on Genomic Regions.
Gong B., Li D., Kusko R., et al.
Genome Biol. 2021, 22, 109. doi:10.1186/s13059-021-02315-0.
A Verified Genomic Reference Sample for Assessing Performance of Cancer Panels Detecting Small Variants of Low Allele Frequency.
Jones W., Gong B., Novoradovskaya N., et al.
Genome Biol. 2021, 22, 111. doi:10.1186/s13059-021-02316-z.
Evaluating the Analytical Validity of Circulating Tumor DNA Sequencing Assays for Precision Oncology.
Deveson I.W., Gong B., Lai K., et al.
Nat Biotechnol. 2021, 39, 1115–1128. doi:10.1038/s41587-021-00857-z.
Accurate Species Identification of Food-Contaminating Beetles with Quality-Improved Elytral Images and Deep Learning.
Bisgin H., Bera T., Wu L., et al.
Frontiers in Artificial Intelligence. 2022, 5.
Trade-Off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An In-Depth Investigation with Tox21 Data Sets.
Wu L., Huang R., Tetko I.V., Xia Z., Xu J., and Tong W.
Chemical Research in Toxicology. 2021, 34 (2), 541-549.
Linking Pharmacogenomic Information on Drug Safety and Efficacy with Ethnic Minority Populations.
Li D., Xie A.H., Liu Z., Li D., Ning B., Thakkar S., Tong W., and Xu J.
Pharmaceutics. 2020, 12 (11), 1021.
DLI-IT: A Deep Learning Approach to Drug Label Identification Through Image and Text Embedding.
Liu X., Meehan J., Tong W., Wu L., Xu X., and Xu J.
BMC Medical Inform Decis Mak. 2020, 20:68.
A Deep Learning Model to Recognize Food Contaminating Beetle Species Based on Elytra Fragments.
Wu L., Liu Z., Bera T., Ding H., Langley D.A., Jenkins-Barnes A., Furlanello C., Maggio V., Tong W., and Xu J.
Comput Electron Agric. 2019, 166, 105002; doi:10.1016/j.compag.2019.105002.
Comparing SVM and ANN Based Machine Learning Methods for Species Identification of Food Contaminating Beetles.
Bisgin H., Bera T., Ding H., Semey H.G., Wu L., Liu Z., Barnes A.E., Langley D.A., Pava-Ripoll M., Vyas H.J., Tong W., and Xu J.
Sci Rep 8. 2018, 6532.
The FDA’s Experience with Emerging Genomics Technologies—Past, Present, and Future.
Xu J., Thakkar S., Gong B., and Tong W.
AAPS Journal. 2016, 18(4): 814–818.
Comparison Of RNA-Seq And Microarray-Based Models For Clinical Endpoint Prediction.
Zhang W., Yu Y., Hertwig F., et al.
Genome Biol. 2015, 16(6):133.
The Concordance Between RNA-Seq And Microarray Data Depends On Chemical Treatment And Transcript Abundance.
Wang C., Gong B., Bushel P.R., et al.
Nat Biotechnol. 2014, 32: 926-932.
Lab Members
Contact information for all lab members:
(870) 543-7121
NCTRResearch@fda.hhs.gov
Spurthi Buchireddy, M.S.
Computer Scientist
Ebony Cotton, PharmD
Postdoc Fellow
Binsheng Gong, Ph.D.
Bioinformatician
Wenxue Jiang, M.S.
Data Scientist
Jae Hyun Kim, Ph.D.
Computer Scientist
Dan Li, Ph.D.
Research Computer Scientist
Feng Qian, M.S.
Data Scientist
Leihong Wu, Ph.D.
Research Computational Biologist
Junshuang Yang, M.S.
Computer Scientist
Yifan Zhang, Ph.D.
Computer Scientist
- Contact Information
- Joshua Xu
- (870) 543-7121
- Expertise
-
ExpertiseApproachDomainTechnology & DisciplineToxicology