There is no required reading until Week 3. Lecture slides are on Canvas.
Lecture Week Date Theme
0. Introduction - course introduction, ML principles, and pitfalls
1 1 9/26 Course introduction; ML challenges in biological problems
Please see lecture slides on Canvas
2 2 10/1 Probabilistic modeling & learning; mathematical foundations
3 2 10/3 Deep learning (autoencoders, MLPs, CNNs, RNNs, and transformers)
Optional readings
4 3 10/8 Model interpretation techniques from the explainable AI field
Optional readings
https://christophm.github.io/interpretable-ml-book/shap.html
Molnar: Interpretable ML Book Chapter 5.10 (Shapley values)
Molnar: Interpretable ML Book Chapter 5.10 (SHAP)
5 3 10/10 Model interpretation techniques from the explainable AI field & Gene expression basics
Optional readings
https://christophm.github.io/interpretable-ml-book/shap.html
Molnar: Interpretable ML Book Chapter 5.10 (Shapley values)
Molnar: Interpretable ML Book Chapter 5.10 (SHAP)
6 4 10/15 Guest Lecture - Armita Nourmohammad (UW Physics)
1. Bulk Transcriptomics
7 4 10/17 D - Linear models
L - Unsupervised learning of gene expression data
Required reading
Optional reading
Basic data interpretation techniques
8 5 10/22 Guest Lecture - Manu Setty (Fred Hutch)
9 5 10/24 Project Proposal Workshopping
L - Cancer biology
10 6 10/29 D - Supervised transcriptome (Alzheimer's)
L - Single-cell genomics
Required reading
“Unified AI framework to uncover deep interrelationships between gene expression and Alzheimer’s disease neuropathologies”
Optional readings
ML pitfalls
Schreiber et al. “A pitfall for ML methods aiming to predict across cell types”
DeGrave*, Janizek* and Lee. “AI for radiographic COVID-19 detection selects shortcuts over signal”
GSEA (classic: “On testing the significance of sets of genes”; recent: https://www.nature.com/articles/s41467-021-22862-1)
11 6 10/31 D - Supervised transcriptome (cancer)
L - Gene regulatory network
Required readings
“Uncovering expression signatures of synergistic drug responses via ensembles of explainable machine-learning models”
Optional readings
“Biologically informed deep neural network for prostate cancer discovery”
“Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer Cells”
2. Single-cell Transcriptomics
12 7 11/5 D - Single-cell transcriptome (unsupervised)
L - Large Language Models
Required readings
13 7 11/7 D - Single-cell transcriptomics & gene regulatory network
L - Sequence-to-function models
14 8 11/12 D - Single-cell foundation models
L - Genome interpretation
Required readings:
Optional readings:
3. Genetics/genomics
15 8 11/14 D - Genomic profile prediction
Project Checkpoint Workshopping
Required readings
Optional readings:
16 9 11/19 D - Genomic Interpretability
L - Cell Painting
Required reading
Optional reading
4. Emerging areas (cell painting & mRNA molecule design)
17 9 11/21 D - Cell painting
L - ML pitfalls
5. Medicine & healthcare
18 10 11/26 D - Real-world clinical AI
L - Biological age
Required reading
Optional reading
19 11 12/3 D - Impact of aging on disease
D - Trustworthy & transparent medical AI
Final
20 11 12/5 Final project presentation