The Data2AI4LifeSciences Laboratory @ TWU

What we do

Data Quality in AI

We focus on ensuring the reliability and integrity of data used in artificial intelligence systems.

AI in Life Sciences

Applying cutting-edge AI techniques to solve complex problems in biology and medicine.

Human Factors in AI

Investigating the ethical implications and societal impact of AI technologies.

Lab Narrative

Our research ecosystem is dedicated to AI for Life Sciences, grounded in foundational theoretical computer science and applied data science. Our domains include Computer Vision, Language Modeling, Information Science, Network Science, and Human Factors. We advance traditional analyses by pioneering Graph Representation Learning and Multimodal Data Integration. These tools help us decode biological and cognitive systems, from the cell to the brain. Through rigorous Data Quality assessment and advanced Big Data mining, we transform unstructured information into dynamic Knowledge Graphs that support modern AI models. This integrated approach bridges the gap between data validity and model accuracy. These elements form the essential foundation of computational life sciences.

Mission

Our mission is to accelerate progress in Biomedical Informatics, Biomedical Literature Mining, Biomedical Imaging, and Computational Drug Discovery. We achieve this by developing novel Graph Neural Networks, integrating large foundation models, and Automating Knowledge-Extraction pipelines that transform raw data into actionable insights. To address structural challenges in Data Science, we establish rigorous standards for Data Quality, Entity Resolution, and Entity Recognition. This approach ensures our models are grounded in reliable data. We also enhance Human Factors in AI by integrating Biometrics and Non-Linear Analysis to model operator attention during system interaction. This aims at bridging the gap between machine logic and human cognition. Through this dual focus, we are committed to ethical, sustainable end-to-end AI systems that generate valid, interpretable, reliable, and safe scientific hypotheses.

Vision

We envision a future in which Data Mining, Network Biology, and Information Retrieval merge into an intelligent system that advances scientific discovery. In this world, Language Modeling and Graph Theory work together to automatically curate biological knowledge and reduce the time needed for discoveries. Here, AI is a transparent partner, always grounded in Ethics, Law, and Data Quality, and serves to enhance, never replace, human intelligence. Ultimately, we strive to define the next generation of Biomedical Intelligence, where structured networks clarify the underlying logic of life.

Topics

Biomedical & Life Sciences

Biomedical informatics Computational drug discovery Protein interaction prediction Computational biomedical imaging Network biology Hypothesis generation

Graph Theory & Network Intelligence

Graph theory Knowledge graphs Network science Graph representation learning Graph neural networks Deep learning Generative AI Foundation models

Data Science & Information Engineering

Data quality Multimodal data integration Data science Big data Data mining Information retrieval Entity resolution Entity recognition Information science Automated knowledge extraction

Human Factors & Responsible AI

Human-computer interaction Eye tracking Ethics and sustainability in AI

Members

PI

Islam Akef Ebeid

iebeid@twu.edu

Students

  • Meagan Stephens

Affiliated Faculty

  • Dr. Wen Xu

Publications

Ebeid IA, Tang H, and Gu P (2025). Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks. Front. Bioinform. 5:1651623. doi: 10.3389/fbinf.2025.1651623

[View Publication]

Gu, P., Tang, H., Ebeid, I. A., Nunez, J. A., Vazquez, F., Adame, D., ... & Chen, D. Z. (2025, June). Adapting a Segmentation Foundation Model for Medical Image Classification. In 2025, IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS) (pp. 167-172). IEEE.

Courses

  • CSCI 4623: Big Data and High-Performance Computing

Funding Sources

National Science Foundation (NSF)
Award Number: 2523786