Next-Generation Sequencing (NGS) technologies have given rise to vast amounts of biological and biomedical Big Data. The rapidly growing volume and diversity of data present unique opportunities as well as significant challenges for analysis. Biological Big Data from different sources (Multi-Omics data) are a promising resource due to their synergistic effects, which can potentially model the behavior of biological cells. Omics integration can thus identify novel biological pathways that may not be distinguishable from individual Omics datasets alone. In this course, through a mix of lectures and hands-on sessions, we will cover machine learning methodologies for integrating large amounts of biological data.

We assume some basic awareness of UNIX environment, as well as at least beginner level of R and / or Python programming.

By completing this course, you will:

• Understand the basics of machine learning approaches to biological data analysis
• Gain an overview of bioinformatic tools and best practices for integrative Omics analysis
• Be able to design an integrative project and implement appropriate analysis methodologies
• Be able to choose the right tools and approaches to answer your specific research question
• Gain confidence in learning new methods needed to answer your research question

Day 1: Introduction & Supervised Integration

14:00–19:00 (Berlin time)

• 14:00–14:45 | Course overview and introductions

• 15:00–16:00 | Intro to multi-omics ML integration: key concepts

• 16:15–17:15 | Feature selection & supervised Omics integration

• 17:30–18:20 | Feature selection methods: LASSO, PLS, LDA (Lab)

• 18:30–19:00 | Supervised integration using mixOmics and DIABLO (Lab)

Day 2: Unsupervised & Deep Learning Approaches

 14:00–19:00 (Berlin time)

• 14:00–15:00 | Unsupervised integration: theory & methods

• 15:15–16:45 | MOFA1 & MOFA2 for unsupervised integration (Lab)

• 17:00–18:00 | Deep Learning for biological data integration

• 18:15–19:00 | Autoencoders for Omics integration (Lab)

Day 3: Single-cell Omics Integration

14:00–19:00 (Berlin time)

• 14:00–15:00 | UMAP and dimensionality reduction for single-cell data

• 15:15–15:45 | PCA, tSNE, UMAP comparison (Lab)

• 15:45–16:45 | UMAP and graph intersection (Lab)

• 17:00–18:00 | Batch correction & feature integration

• 18:15–19:00 | Seurat CCA + DTW, WNN for single-cell integration (Lab) | Final discussion and Q&A

1 -  Machine Learning with R - ONLINE, 16-20 February

2 -  Multimodal AI for Systems Biology - ONLINE, 2-6 March

3 - Machine Learning for Bio-imaging - ONLINE, 9-11 March

4 - AI for Genomics - ONLINE, 7-9 April

Should you have any further questions, please send an email to [email protected]