Related Experiment Video
Updated: Jul 15, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Evaluating a large language model's ability to solve programming exercises from an introductory bioinformatics course
Stephen R Piccolo1, Paul Denny2, Andrew Luxton-Reilly2
1Department of Biology, Brigham Young University, Provo, Utah, United States of America.
Artificial intelligence tools like ChatGPT can successfully complete most introductory bioinformatics programming exercises. This suggests a need for updated teaching methods and potential collaboration between researchers and AI for coding tasks.
Area of Science:
- Life Sciences
- Bioinformatics
- Computer Science Education
Background:
- Computer programming is essential for life scientists but challenging to learn.
- Artificial intelligence (AI) advancements enable code generation from natural language prompts.
- The potential of AI to assist or replace human coding efforts in life sciences is under investigation.
Purpose of the Study:
- To evaluate the effectiveness of OpenAI's ChatGPT in solving programming tasks for life scientists.
- To assess the performance of ChatGPT on introductory bioinformatics course exercises.
Main Methods:
- 184 programming exercises from an introductory bioinformatics course were used.
- ChatGPT's ability to solve exercises was tested.
- Natural language feedback was provided for exercises ChatGPT did not solve initially.
Main Results:
- ChatGPT successfully solved 75.5% of exercises on the first attempt.
- Within seven or fewer attempts, ChatGPT solved 97.3% of all exercises.
- The AI model demonstrated significant capability in completing programming tasks.
Conclusions:
- AI tools like ChatGPT show high proficiency in solving common life science programming problems.
- Educational strategies and assessment methods in life sciences may require adaptation due to AI.
- AI models offer potential as collaborative tools for life science researchers in coding.
More Related Videos
07:09A Bioinformatics Pipeline for Investigating Molecular Evolution and Gene Expression using RNA-seq
Published on: May 28, 2021
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Related Concept Videos
Machines: Problem Solving II
Improving Translational Accuracy
Machines: Problem Solving I
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
Evolutionary Relationships through Genome Comparisons
Modern Molecular Taxonomy
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...