• Instructor: Yunan Luo
• Email: [email protected]

This graduate-level course focuses on the exciting intersection between machine learning and computational biology. We will cover modern machine learning techniques, including supervised and unsupervised learning, feature selection, probabilistic modeling, graphical models, deep learning, and more. Students will learn the fundamental principles, underlying mathematics, and implementation details of these methods. Through reading and critiquing published research papers, students will learn the applications of machine learning methods to a variety of biological problems in genomics, single-cell analyses, structural biology, and system biology. Students will also learn to implement deep learning models using PyTorch, a popular deep learning library, through in-depth programming assignments. In the final project, students will apply what they have learned to real-world data by exploring these concepts with a biological problem that they are passionate about.

This course is appropriate for graduate students or advanced undergraduate students in computer science, bioinformatics, biomedical engineering, mathematics, and statistics. Familiarity with basic linear algebra, statistics, probability, and algorithms is expected. Background knowledge in data analytics and machine learning will be helpful for this course. Students are also expected to have programming experience in Python.

The repository contains the following directories and files:

• HW-1

  • hw1_reg.ipynb: Jupyter notebook for HW1 regression task.
  • hw1_torch_intro.ipynb: Jupyter notebook for HW1 PyTorch introduction.
  • HW1-PDF-Solution.pdf: PDF solution for HW1.

• HW-2

  • cnn.pth: PyTorch model weights for CNN.
  • hw2_clf.ipynb: Jupyter notebook for HW2 classification task.
  • hw2_nn.ipynb: Jupyter notebook for HW2 neural network task.
  • mlp.pth: PyTorch model weights for MLP.
  • weights.txt: Weights file.
  • HW2-PDF-Solution.pdf: PDF solution for HW2.
  • HW2-PDF.pdf: Additional PDF for HW2.

• HW-3

  • graph_gcn.pth: PyTorch model weights for GCN.
  • graph_gnn.pth: PyTorch model weights for GNN.
  • hw3_VAE.ipynb: Jupyter notebook for HW3 VAE task.
  • hw3_gnn.ipynb: Jupyter notebook for HW3 GNN task.
  • node_gcn.pth: PyTorch model weights for node GCN.
  • HW3-PDF-Solution.pdf: PDF solution for HW3.
  • HW3-PDF.pdf: Additional PDF for HW3.

• MLCB Course Syllabus S24.pdf: Course syllabus for Spring 2024.
• MLCB Schedule S24.pdf: Course schedule for Spring 2024.

• Lec01-Introduction.pdf
• Lec02-Molecular biology.pdf
• Lec03-Sequence alignment I.pdf
• Lec04-Sequence alignment II.pdf
• Lec05-Regression.pdf
• Lec06-Classification+Applied ML toolbox.pdf
• Lec07-Neural networks.pdf
• Lec08-Deep learning.pdf
• Lec09-Deep learning for sequence data.pdf
• Lec10-Large language models (LLMs).pdf
• Lec11-Unsupervised learning.pdf
• Lec12_Generative AI.pdf
• Lec13-Learning from network data.pdf
• Lec14-Graph neural networks.pdf
• Lec15-Learning from structure data.pdf
• Lec16-Protein language models.pdf
• Lec17-Variant effect prediction.pdf
• Lec18-Protein function prediction.pdf
• Lec19-Protein structure prediction.pdf
• Lec20-GNN for molecular structure.pdf
• Lec21-Programmable protein design.pdf
• Lec22-ML for bioimaging.pdf
• Lec23-ML for network biology.pdf

To get started with this repository:

1. Clone the repository:

   git clone https://github.com/sarth-diskalkar/CSE7850-Machine-Learning-in-Computational-Biology.git
   
   

Feel free to copy this updated README and modify it as necessary for your repository. Let me know if any adjustments should be made. Feel free to check out my other repos as well!