Machine learning
purlPURL: https://gxy.io/GTN:P00030Comment: What is a Learning Pathway?
We recommend you follow the tutorials in the order presented on this page. They have been selected to fit together and build up your knowledge step by step. If a lesson has both slides and a tutorial, we recommend you start with the slides, then proceed with the tutorial.
This learning path teaches machine learning from simple concepts to complex ones. You start with a basic introduction to Machine learning. Then you move to different aspects of supervised machine learning such as classification and regression. Further topics introduce you to deep learning concepts such as convolutional and recurrent neural networks and conclue with fine-tuning a large language like model trained on protein sequences.
New to Machine Learning? Follow this learning path to get familiar with the basics as well as complex machine learning topics!
Module 1: Introduction to Machine learning
This is an introductory section explaining basic concepts in machine learning such as its types and data splitting techniques.
Time estimation: 30 minutes
Learning Objectives
- Provide the basics of machine learning and its variants.
- Learn how to do classification using the training and test data.
- Learn how to use Galaxy's machine learning tools.
Lesson | Slides | Hands-on | Recordings |
---|---|---|---|
Basics of machine learning
|
Module 2: Classification and Regression
Regression and classification
Time estimation: 4 hours
Learning Objectives
- Learn classification background
- Learn what a quantitative structure-analysis relationship (QSAR) model is and how it can be constructed in Galaxy
- Learn to apply logistic regression, k-nearest neighbors, support verctor machines, random forests and bagging algorithms
- Learn how visualizations can be used to analyze the classification results
- Learn regression background
- Apply regression based machine learning algorithms
- Learn ageing biomarkers and predict age from DNA methylation datasets
- Learn how visualizations can be used to analyze predictions
Lesson | Slides | Hands-on | Recordings |
---|---|---|---|
Classification in Machine Learning
|
|||
Regression in Machine Learning
|
Module 3: Deep learning
Deep learning
Time estimation: 4 hours
Learning Objectives
- Understand the inspiration behind CNN and learn the CNN architecture
- Learn the convolution operation and its parameters
- Learn how to create a CNN using Galaxy's deep learning tools
- Solve an image classification problem on MNIST digit classification dataset using CNN in Galaxy
- Understand the difference between feedforward neural networks (FNN) and RNN
- Learn various RNN types and architectures
- Learn how to create a neural network using Galaxy's deep learning tools
- Solve a sentiment analysis problem on IMDB movie review dataset using RNN in Galaxy
Lesson | Slides | Hands-on | Recordings |
---|---|---|---|
Deep Learning (Part 3) - Convolutional neural networks (CNN)
|
|||
Deep Learning (Part 2) - Recurrent neural networks (RNN)
|
Module 4: Fine tuning protein language model
Fine tuning protein language models
Time estimation: 1 hour
Learning Objectives
- Learn to load and use large protein models from HuggingFace
- Learn to fine-tune them on specific tasks such as predicting dephosphorylation sites
Lesson | Slides | Hands-on | Recordings |
---|---|---|---|
Fine tune large protein model (ProtTrans) using HuggingFace |
Editorial Board
This material is reviewed by our Editorial Board: