Weigong Ge Data-verified

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

High Impact

Researcher

NCTR

Last publication 2025 Last refreshed 2026-05-16

faculty

25 h-index 73 pubs 6,733 cited

Research Areas

OverviewAI-generated summary

Weigong Ge's research focuses on the application of computational methods, including machine learning and deep learning, to address challenges in toxicology, pharmacology, and health sciences. His work has involved developing predictive models for drug properties, such as the prediction of gas adsorption capacity in nanomaterials and the prediction of hERG blockade, a critical factor in drug safety. Ge has also investigated the use of AI for analyzing large datasets, such as comparing topic modeling techniques for understanding opioid-related cardiovascular risks in women and analyzing adverse event reports submitted to the FDA.

His research extends to drug discovery and repurposing, with studies on predicting binding patterns in estrogen receptors and developing models for predicting SARS-CoV-2 main protease binding for potential COVID-19 treatments. Ge has also worked on data normalization techniques, specifically using RxNorm for drug name standardization in studies of prescription opioids. His scholarly contributions are reflected in a h-index of 25, with over 73 publications and 6,666 citations, designating him as a highly cited researcher.

Ge collaborates with several colleagues at the National Center for Toxicological Research, including Joe Meehan and Bohu Pan, with whom he shares a significant number of publications. Other key collaborators include Wen Zou and Tucker A. Patterson. His recent activity indicates ongoing engagement in research, with publications as recent as 2025.

Metrics

h-index: 25
Publications: 73
Citations: 6,733

Selected Publications

Developing predictive models for µ opioid receptor binding using machine learning and deep learning techniques (2025)

2 citations DOI OpenAlex
AI-powered topic modeling: comparing LDA and BERTopic in analyzing opioid-related cardiovascular risks in women (2025)

31 citations DOI OpenAlex
Machine learning and deep learning approaches for enhanced prediction of hERG blockade: a comprehensive QSAR modeling study (2024)

20 citations DOI OpenAlex
A systematic analysis and data mining of opioid-related adverse events submitted to the FAERS database (2023)

7 citations DOI OpenAlex
Developing a SARS-CoV-2 main protease binding prediction random forest model for drug repurposing for COVID-19 treatment (2023)

10 citations DOI OpenAlex
Mold2 Descriptors Facilitate Development of Machine Learning and Deep Learning Models for Predicting Toxicity of Chemicals (2023)

2 citations DOI OpenAlex
Additional file 3 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 13 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 5 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 15 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 10 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 9 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 11 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 1 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex
Additional file 6 of Assessing reproducibility of inherited variants detected with short-read whole genome sequencing (2022)

DOI OpenAlex