Computer Science: RNA Motif Structural Analysis

This research assistantship is hybrid, and lasts across Fall 2025 and Spring 2026. The lead faculty is Dr. Jie Hou.

All SURGE positions are part-time with a maximum of 8-10  hours per week.

Please review the project description and qualifications below, and submit your resume and a brief written statement (cover letter) explaining your interest in this area and your qualifications.

Project description

RNA motifs are crucial in gene expression, protein synthesis, and molecular interactions, yet their analysis remains complex and resource-intensive, requiring advanced computational skills. This complexity is limiting undergraduate engagement, particularly for chemistry students at Saint Louis University (SLU). 
To address these challenges, we are partnering with SLU's Chemistry group to develop an automated framework leveraging large language models (LLMs) for code generation and automated error handling, aiming to streamline motif detection, clustering, and structure prediction. Unlike existing methods, this modular, user-friendly system will allow students with minimal programming experience to focus on hypothesis formulation and results interpretation rather than technical implementation. This initiative fosters interdisciplinary collaboration between computer science and chemistry, enhances research efficiency, and serves as a scalable model for AI-driven data analysis in STEM. 

Day-to-day

Undergraduate students will assist graduate students in developing an open-source
computational framework for RNA motif structural analysis, including:
1. reading relevant literature for RNA motif analysis and artificial intelligence (AI) agent;
2. writing python scripts to deploy AI agent;
3. the integration of the AI agent for RNA motif analysis;
4. performing evaluation of the experimental results;
5. writing the summary of experiments for manuscript
 

Students are also required to discuss the project progress with the advisor weekly.
 

Qualifications

A qualified candidate should:
1. Have programming experience with python;
2. Have interest in learning biological data analysis;
3. Comfortable with scientific literature reading;
4. Have basic knowledge of machine learning is preferred