This two-day workshop focuses on the applications of large language models (LLMs) in bioinformatics. Participants will first be introduced to foundational machine learning (ML) concepts, followed by an in-depth exploration of LLMs and their growing role in bioinformatics. The proposed program will include lectures and hands-on labs covering LLM applications in genomics, proteomics, metabolomics, with a major focus on both bioinformatics cheminformatics. Participants will learn how to use LLMs and which LLMs to use for coding in bioinformatics, gene prediction/annotation, protein structure/function analysis, and small molecule property prediction in their research.
By the end of the workshop, participants will be able to:
1. Explain the key concepts of large language models and their applications in bioinformatics, including genomics, proteomics, metabolomics and general informatics.
2. Apply LLMs to perform bioinformatics coding tasks.
3. Utilize LLM-based tools for analyzing bioinformatics data in genomics, including gene prediction/annotation, protein structure/function prediction, and small molecule function analysis.
4. Integrate LLMs into bioinformatics workflows for research and analysis
Post-doctoral fellows, graduate students, bioinformaticians, computational biologists, and researchers in the life sciences domain; Focused on individuals involved in bioinformatics projects, with an interest in applying large language models and artificial intelligence to genomics, proteomics, and cheminformatics research.
Participants should have a basic understanding of bioinformatics and molecular biology. Familiarity with Python programming and command-line tools is required. Some prior exposure to LLMs concepts and tools would be beneficial, though not mandatory.
Introduction to Machine Learning
• Overview of machine learning concepts and applications in bioinformatics.
• Introduction to key algorithms used in machine learning for bioinformatics, including neural networks, decision trees, graphical neural networks and transformers
Introduction to Large Language Models (LLMs)
• Basics of LLMs: what they are and how they differ from traditional machine learning models.
• Evolution of LLMs: BERT, GPT, and their relevance to bioinformatics.
• Fine tuning and prompt engineering for improving LLM performance.
LLMs for Bioinformatics Coding (Lecture)
• Introduction to how LLMs can be used for coding in bioinformatics.
• Overview of bioinformatics tools and coding examples.
LLMs for Bioinformatics Coding (Lab)
• Students performing bioinformatics coding using LLMs (selected examples, performance comparisons)
LLM Applications in Genomics (Lecture)
• Overview of LLMs applications in genomics.
LLM Applications in Genomics (Lab)
• Hands-on: Running LLMs for genomic analysis, including gene prediction, gene annotation and variant identification
• Hands-on: Fine-tuning an LLMs for genomic analysis, including gene prediction, gene annotation and variant identification.
LLM Applications in Proteomics (Lecture)
• Lecture: How LLMs are used in proteomics for tasks like protein structure prediction and protein functional annotation.
LLM Applications in Proteomics (Lab)
• Hands-on: Using LLMs for structure prediction and functional analysis of proteins.
Chemical Language Models for Metabolomics and Exposomics (Lecture & Lab)
• Introduction to chemical language models for small molecule prediction and chemical property
analysis.
• Hands-on: Applying LLMs to predict chemical properties and molecular functions in
metabolomics and exposomics.
LLMs Applications for Bioinformatics Data Analysis
• Lecture: Using LLMs for bioinformatics data analysis, focusing on tools like OpenAI Code
Interpreter and Julius AI.
• Hands-on: Practical examples of data analysis using these tools in bioinformatics.
Future Directions and Wrap-Up
• Discussion on the future of LLMs in bioinformatics.
• Wrap-up discussion and Q&A session.
Duration: 2 days
Start: Nov 14, 2026
End: Nov 15, 2026
Status: Application Open
Apply
Canadian Bioinformatics Workshops promotes open access. Past workshop content is available under a Creative Commons License.
Posted on: