Quantitative Learning Impact Modelling of AI-Integrated Module-Level Project-Based Learning in a Multimodal Data Omics Course: A Case Study

Authors

  • Mahadevaswamy Associate Professor, Dept. of ECE, Vidyavardhaka College of Engineering, Mysuru, Gokulam 3rd Stage, Mysuru
  • Pavithra G. Associate Professor, Department of ECE, Dayananda Sagar College of Engineering, Bengaluru
  • B. P. Pradeep Kumar Professor, Dept. of CSD, Atria Institute of Technology, Bengaluru
  • Shivashankar R. Assistant Professor, Dept. of ME, Vidyavardhaka College of Engineering, Mysuru
  • Shivaraju H. P. Associate Professor, Dept. of Environmental Sciences, JSS Academy of Higher Education and Research, Mysuru

DOI:

https://doi.org/10.16920/jeet/2026/v39is2/26003

Keywords:

Assessment; Explainable AI; Multimodal Data; Project-based learning; Reproducibility; Student engagement.

Abstract

Multimodal omics courses require students to work with diverse biological data and construct reproducible analytical workflows, yet little is known about how AI-enabled tools influence learning in these settings. Prior work highlights the value of project-based learning but offers limited evidence on module-level outcomes that shape student performance. This study examines an undergraduate omics course in which six short projects-spanning genomics, transcriptomics, proteomics, metabolomics, imaging, and clinical data-were taught using a counterbalanced Latin-square design. Each project was delivered either with and without AI-integrated scaffolds, including automated baselines, experiment tracking, containerised execution, calibration measures, and interpretability tools. Performance, concept-inventory gains, behavioural traces, and affective measures were analysed using mixed-effects modelling and mediation analysis.

Students in the AI-integrated condition showed higher technical performance, better calibration, stronger reproducibility, and good concept-learning gains. Qualitative feedback indicated that workflow tools supported iteration and clearer reasoning, though challenges with environment setup and over-reliance on automated outputs remained. The findings suggest that AI-enabled scaffolds can strengthen learning in data-intensive omics courses when paired with structured, module-level projects. The study offers a methodological template for evaluating instructional designs that combine PBL with modern analytical workflows.

Downloads

Download data is not yet available.

References

Goller, C. C., Srougi, M. C., Chen, S. H., Schenkman, L. R., & Kelly, R. M. (2021). Integrating bioinformatics tools into inquiry-based molecular biology laboratory education modules. Frontiers in Education, 6, 711403.

He, X., Zhao, K., & Chu, X. (2021). AutoML: A survey of state-of-the-art. ACM Computing Surveys, 54(8), 1-36.

Lanubile, F., Martínez-Fernández, S., & Quaranta, L. (2023). Teaching MLOps in higher education through project-based learning. In 2023 IEEE/ACM ICSE-Software Engineering Education and Training (SEET) (pp. 1–8).

Luo, Y., Zhang, Q., Hu, R., Yin, H., Zhang, R., & Xie, L. (2024). Multiomics research: Principles and challenges in integrative analysis. BioDesign Research, 4, 0059.

Merkle, E. C., Fitzsimmons, E., Uanhoro, J., & Goodrich, B. (2021). Efficient Bayesian structural equation modelling in Stan. Journal of Statistical Software, 100(6), 1–22.

Paulsen, L., & Lindsay, E. (2024). Learning analytics dashboards are increasingly becoming about learning and not just analytics: A systematic review. Education and Information Technologies, 29(11), 14279–14308.

Poličar, P. G., Kokošar, J., Rotovnik, T., & Zupan, B. (2024). Teaching bioinformatics through the analysis of SARS-CoV-2: Project-based training for computer science students. Bioinformatics, 40(Suppl. 1), i398-i405.

Saint, J., Fan, Y., Gašević, D., & Pardo, A. (2022). Temporally-focused analytics of self-regulated learning: A systematic review. Computers and Education: Artificial Intelligence, 3, 100060.

Sauter, T., Bintener, T., Kishk, A., Presta, L., Prohaska, T., Guignard, D., Zeng, N., Cipriani, C., Arshad, S., & Pfau, T. (2022). Project-based learning course on metabolic network modelling in computational systems biology. PLOS Computational Biology, 18(1), e1009711.

Scott, I. C., Hepworth, S., Chisnall, C., & Routledge, P. (2024). Evaluating automated machine learning platforms for use in healthcare. JAMIA Open, 7(3), ooae031.

Sun, J. C.-Y., Yeh, R. C., Yu, S.-W., & Lin, C. (2023). Temporal learning analytics to explore traces of self-regulated learning in an online course. Computers & Education, 194, 104656.

Luo, Y., Zhang, Q., Hu, R., Yin, H., Zhang, R., & Xie, L. (2024). Multiomics research: Principles and challenges in integrative analysis. BioDesign Research, 4, 0059.

Downloads

Published

2026-02-17

How to Cite

Mahadevaswamy, G., P., Pradeep Kumar, B. P., R., S., & H. P., S. (2026). Quantitative Learning Impact Modelling of AI-Integrated Module-Level Project-Based Learning in a Multimodal Data Omics Course: A Case Study. Journal of Engineering Education Transformations, 39(Special Issue 2), 21–29. https://doi.org/10.16920/jeet/2026/v39is2/26003

Issue

Volume 39, Special Issue 2, January 2026

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

Most read articles by the same author(s)