MIT Deep Learning Genomics - Lecture 11 - RNA, PCA, t-SNE, Embeddings (Spring20)

MIT 6.874 Lecture 11. Spring 2020
Course website: https://mit6874.github.io/
Lecture slides: https://mit6874.github.io/assets/sp2020/slides/L11_PCA_tSNE_Autoencoders.pdf

Outline:
1. Gene expression analysis: The Biology of RNA-seq
2. Supervised (Classification) vs. unsupervised (Clustering)
3. Supervised: Differential expression analysis
4. Unsupervised: Embedding into lower dimensional space
5. Linear reduction of dimensionality
- Principle Component Analysis
- Singular Value Decomposition
6. Non-linear dimensionality reduction: embeddings
- t-distributed Stochastic Network Embedding (t-SNE)
- Building intuition: Playing with t-SNE parameters
7. Deep Learning embeddings
- Autoencoders