Reading list

(The list below will be completed soon)

• Week 1:

  • How to give good research talks (read here and watch here)

  • How to read research papers (here)

  • How to choose research problems (here and here)

• Week 2:

  • Intro to VAE: here

  • Unsupervised representation of gene expression: here

  • Need for batch effect adjustments? here

• Week 3:

  • Review: Computational prediction of protein interactions: here

  • ML for protein interactions and functions from sequence: here

• Week 4:

  • Review on ML guided protein design: here

  • Autofocused oracles for model-based design: here

  • Conditioning by adaptive sampling for robust design: here

• Week 5:

  • Integrating gene expression an imaging: here and here

• Week 6:

  • Challenges in 'omics studies of human disease: here

  • Causal Inference from gene expression data: here

  • Other related papers:

    • Clustering on the Unit Hypersphere using von Mises-Fisher Distributions: here

    • Single-cell experimental design: here

• Week 7:

  • single-cell RNA-seq data modelling & challenges: here and here

• Week 8:

  • Topics in Cancer Genomics: here and here

• Week 9:

  • Phenome-scale causal discovery and mendelian randomization: here

• Week 10:

Preparatory reading for the class:

ML

• A Course in Machine Learning by Hal Daumé III: http://ciml.info/.

• Pattern Recognition and Machine Learning by Chris Bishop. (pdf)

Biology

• Introduction to Molecular Biology (pdf).

• A lengthy, general resource: Molecular Biology of the Cell v5 (pdf)

Suggested review articles:

• Opportunities and obstacles for deep learning in biology and medicine (here)