Magnus Gray Source Confirmed

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

Researcher

National Center for Toxicological Research

faculty

6 h-index 14 pubs 77 cited

Research Areas

Natural Language Processing Techniques Advanced Neural Network Applications Pharmacological Effects and Toxicity Studies Health Literacy and Information Accessibility Meta-analysis and systematic reviews Topic Modeling

Links

ORCID Lab Website

Is this your profile? Verify and claim your profile

OverviewAI-generated summary

Magnus Gray's research focuses on the application of artificial intelligence and natural language processing techniques to regulatory science, particularly within the pharmaceutical domain. His work investigates methods for measuring and mitigating bias in AI models, aiming to enhance transparency and trustworthiness in regulatory environments. Gray has explored the use of language embedding models for analyzing and classifying regulatory documents, such as drug labeling information. He has also studied the comparative performance of molecular descriptors and AI-based embeddings for toxicity prediction.

Gray collaborates with researchers at the National Center for Toxicological Research, including Leihong Wu and Joshua Xu, and has published multiple papers with them. His scholarship metrics include an h-index of 6, with a total of 14 publications and 77 citations.

Metrics

  • h-index: 6
  • Publications: 14
  • Citations: 77

Selected Publications

  • Comparative Study of Molecular Descriptors and AI-Based Embeddings for Toxicity Prediction (2025) DOI
  • Benchmarking bias in embeddings of healthcare AI models: using SD-WEAT for detection and measurement across sensitive populations (2025) DOI
  • SD-WEAT: Towards Robustly Measuring Bias in Input Embeddings (2024) DOI
  • A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document (2024) DOI
  • RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling (2023) DOI
  • Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science (2023) DOI
  • Classifying Free Texts Into Predefined Sections Using AI in Regulatory Documents: A Case Study with Drug Labeling Documents (2023) DOI

Collaborators

Researchers in the database who share publications

Leihong Wu National Center for Toxicological Research 8 shared publications Joshua Xu National Center for Toxicological Research 4 shared publications Mariofanna Milanova University of Arkansas at Little Rock 1 shared publication Weida Tong National Center for Toxicological Research 1 shared publication Denny Skiles National Center for Toxicological Research 1 shared publication Hong Fang National Center for Toxicological Research 1 shared publication

Similar Researchers

Based on overlapping research topics

Svitlana Shpyleva National Center for Toxicological Research
Natural Language Processing Techniques Advanced Neural Network Applications Pharmacological Effects and Toxicity Studies
Good match 4 shared topics
Paul Rogers National Center for Toxicological Research
Natural Language Processing Techniques Advanced Neural Network Applications Pharmacological Effects and Toxicity Studies
Good match 4 shared topics
Fan Dong National Center for Toxicological Research
Natural Language Processing Techniques Advanced Neural Network Applications Pharmacological Effects and Toxicity Studies
Good match 4 shared topics
Minjun Chen National Center for Toxicological Research
Natural Language Processing Techniques Advanced Neural Network Applications Pharmacological Effects and Toxicity Studies
Good match 4 shared topics
M. Eduard Tudoreanu University of Arkansas at Little Rock
Natural Language Processing Techniques Advanced Neural Network Applications Topic Modeling
Good match 3 shared topics
Tolgahan Çakaloğlu University of Arkansas at Little Rock
Natural Language Processing Techniques Advanced Neural Network Applications Topic Modeling
Good match 3 shared topics