I am an assistant professor in the Department of Computer Science at Saint Louis University, with a secondary appointment in Department of Health and Clinical Outcomes Research (HCOR) in School of Medicine. I received my M.A. in Statistics in 2014, and a Ph.D. in Computer Science in 2019 from the University of Missouri-Columbia.
The research in my lab focuses on developing data-driven computational methods (particularly machine learning, deep learning, and computational optimization methods) to address the fundamental problems in biological sciences, including protein/RNA structure prediction, molecular interactions (i.e., protein-protein complex, protein-RNA contacts) and quality assessment of molecular structure predictions. In addition, we are also interested in omics data analysis (i.e., RNA-seq/scRNA-seq transcriptomics and genomics). @Google Scholar / @Curriculum Vitae
I am also dedicated to advancing AI in education (AI4Ed) by integrating innovative technologies such as ProcessFeedback and AI-driven tools (LLMs) into computational learning. Through funded research and hands-on tutorials at education conference (see Full Paper | Workshop Materials for ACM-SIGCSE), I develop self-reflective teaching approaches that enhance student engagement and promote interactive learning in both classrooms and research training. My work spans undergraduate AI research initiatives, innovative teaching methodologies, and contributions to major AI and CS education conferences.
Protein/RNA Structure Prediction
Read MoreProtein Quality Assessment
Read MoreOmics data analysis & Deep Learning
Privacy-Preserving Machine Learning
Read More1. Tutorial on AI in Education (AI4Ed) on ACM-SIGCSE 2025
Adhikari, Badri, and Jie Hou. "Teaching Coding in the Age of AI: A Hands-on Tutorial on Process Feedback." Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 2. 2025.
see Full Paper | Workshop Materials
|
|
2. Student Engagement Strategies Panel: SLU representative at Focus on Teaching and Technology Conference (FTTC) 2024
Topic: "Enhance Engagement and Learning: Integrating ProcessFeedback in Classroom"
![]() |
1. 2024, School of Science & Engineering Faculty and Staff Excellence in Teaching Award, Saint Louis University |
2. 2019, Outstanding PhD Student Award in the College of Engineering, University of Missouri |
1. NIH/NIGMS, R15 (Active, Principal-Investigator), “Improving Artificial Intelligence Readiness of RNA Motif Data for Structure Analysis and Modeling,” 09/2024 – 08/2027. Project Number: 1R15GM155891-01
Major Goals: Our goal is to enhance computational RNA structural analysis by integrating artificial intelligence (AI) and developing a comprehensive RNA data generation framework tailored for AI applications. |
![]() |
2. NIH/NHLBI, R01 (Active, co-Investigator, site co-PI), “Pharmacogenetic Refinement of the Warfarin Dose Using Machine Learning,” 07/2024 – 06/2028. (PI: Dr. Gage Brian at School of Medicine, WUSTL). Project Number: 1R01HL173734-01
Major Goals: Our goal is to improve the safety and effectiveness of anticoagulant therapy. We will use penalized regression and machine learning to develop algorithms to guide warfarin dosing. To facilitate use of the algorithms, we will integrate them into a popular electronic health record (Epic) and make them publicly available at our non-profit web application, www.WarfarinDosing.orgScope of work: Major role in developing advanced machine learning framework to quantify the warfarin dose-response relationship in long-term period; Algorithm validation and deployment via their electronic medical record, Epic. |
![]() |
3. NSF (Active, co-PI), “CC* Compute-Campus: Modernizing Campus Cyberinfrastructure for AI-Enhanced Research and Education (ModernCARE),” 11/2024 – 10/2026. (PI: Ted Ahn at SLU-CS). Project Number: 2430236
Major Goals: This project aims to enhance SLU's campus computing infrastructure equipment (a brand-new, small-scale, university-wide, GPU-based cluster) to support advanced AI-driven research and educational activities that will benefit our faculty, students, and broader scientific community.Scope of work: Dr. Hou will support HPC training workshops and seminars, lead the sub-session for the bioinformatics and AI, and validate the new system on the AI-driven molecular structure prediction. Dr. Hou will also incorporate this environment in the development of new machine learning and bioinformatics courses. |
![]() |
4. SLU Scholarly Undergraduate Research Grants and Experiences (SURGE) Program
a. (PI, Active) “AI agent for automated RNA motif analysis using open-source large language models (LLMs)s,” 08/2025 – 06/2026. Job Details: https://slu.joinhandshake.com/jobs/9741688/share_previewb. (PI, Completed) “Automated RNA Motif Structure Parsing Framework for AI/ML applications,” 08/2024 – 12/2024c. (PI, Completed) “Computational algorithms for binding affinity between antibodies and antigens,” 05/2023 – 09/2023 |
![]() |
5. SLU Foundational Interdisciplinary Research Experience (FIRE) grant
a. (PI, active) “Advancing RNA Motif Structural Analysis with a Fully Automated AI Agent,” 01/2025 – 12/2026![]() |
![]() |
Data-restrained structural modeling based on experimental information has attracted new attention. Solutions to such problems are still under development. The use of experimental restraints, such as cross-linking/mass spectrometry, small-angle x-ray scattering (SAXS) and single-particle cryo-electron microscopy (cryo-EM) have emerged and are considered a promising direction in structural modeling improvement.
My research interest focuses on developing computational methods (i.e. deep learning, machine learning, optimization techniques) to determine the optimal ways to fully leverage the experimental information from SAXS/Cryo-EM in protein/RNA structure modeling.
Protein quality assessment (QA) plays an important role in protein structure prediction, which evaluates the quality of a protein model without knowing its true structure. My research interest focuses on developing deep-learning based model QA methods to explore potential solutions for improving the accuracy of model quality assessment, incuding integrating multiple QA methods and residue-residue contact/distance predictions.