The purpose of this workshop is to provide an overview of Machine learning concepts and tooling useful to Biologists.

• Starting from ground up with no assumed pre-requisite know how
• Understand the academic underpinnings of how Machine Learning works
• Covering key Machine Learning concepts and not exhaustive coverage of topics

Helping in clinical experimentation and academic research.

• The material covered will help in skilling up participants to confidently utilise Machine Learning within academic work and research.
• Appraise participants with cutting edge utilisation of Machine Learning within Biology

Presentation Slides

Morning Session

• Introduction
• AI/ML Unpacked
• Canonical Structure of AI Systems
• AI: History and Current Rise
• AI Classification & Taxonomy
• Building Robust AI Models
• Datasets in AI: Unstructured vs Structured Data
• Introduction to Jupyter Notebooks
• Overview of Key Python Libraries for Machine Learning in Bioscience
• LAB 1 - Protein Structure Prediction using ESMFold
• LAB 2 - Physicochemical Properties Analysis of Protein Sequence Data

Afternoon Session

• Machine Learning Algorithms: Linear & Logistic Regression
• Clustering Methods in ML
• Ensemble Learning Techniques
• Boosting Algorithms
• Mathematical Underpinnings of ML
• Introduction to Large Language Models (LLMs)
• LLM Experimentation
• LAB 3 - Modelling Protein Detectability on Mass Spectrometry with MLP Algorithm

1. LAB 1 - Protein Structure Prediction using ESMFold

   • First Notebook - Simple protein fold inference

   • Second Notebook - Advanced protein fold inference

2. LAB 2 - Physicochemical Properties Analysis of Protein Sequence Data

3. LAB 3 - Modelling Protein Detectability on Mass Spectrometry with MLP Algorithm

Linear Regression

Logistic Regression

Clustering

Ensembles

XGBoost

Principle Component Analysis (PCA)