| Week | Date | Major Topic | Computational concepts | Biological application | Slides | Reading | Lecturer |
|---|
| 1 | 5-Sep | Class overview | | What is Network Biology | pptx pdf | 1. Molecules of life 2. Topology of molecular networks 3. Current and Future Directions in Network Biology | Profs. Roy/Gitter |
| 2 | 10-Sep | Representing and learning networks from data | Introductory concepts of graphs and PGMs | Representing gene regulatory networks | pptx pdf | (1) Friedman et al (2) Sparse candidate (3) Markowetz and Spang (optional) | Prof. Roy |
| 12-Sep | | Learning directed PGMs from data | | Continue from Sep 10th | | Prof. Roy |
| 3 | 17-Sep | | Extensions to directed PGMs | Modeling time and prior knowledge | pdf pptx | DBN and Cancer signaling | Prof. Roy |
| 19-Sep | | Dependency networks | Predictive relationships and cycles | pdf pptx | GENIE3 | Prof. Roy |
| 4 | 24-Sep | | Continue with dependency networks | | | | Prof. Roy |
| 26-Sep | | Causal graph learning | Causal GRNs | pdf pptx | Review article | Prof. Roy |
| 5 | 1-Oct | Deep learning in network biology | Graph neural networks | Predicting protein interfaces | pptx pdf | (1)Distill intros (2)Wu et al | Prof. Gitter |
| 3-Oct | | Graph neural networks | Predicting protein function | pptx pdf | Graph attention networks | Prof. Gitter |
| 6 | 8-Oct | | Graph transformers | Predicting chemical properties | pptx pdf | GraphGPS | Prof. Gitter |
| 10-Oct | | Graph transformers | | Continued | Attention examples (pdf) (ipynb) | Prof. Gitter |
| 7 | 15-Oct | | Graph transformers | | Continued | Transformer | Prof. Gitter |
| 17-Oct | Analysis of graphs | Degree distribution; clusters/modules | Design principles of biological networks | pdf pptx | (1) Barabasi and Oltvai review (2) Girvan-Newman algorithm (notebook) | Spencer Halberg & Erika Lee |
| 8 | 22-Oct | | Graph clustering and motifs; evaluation | | pdf pptx | Module detection benchmark | Prof. Roy |
| 24-Oct | | Unsupervised Representation learning | Task agnostic graph analysis | pdf pptx | (1)node2vec (2) OhmNet | Prof. Roy |
| 9 | 29-Oct | | Continue unsupervised representation learning (RL) | | see oct24 slides | | Prof. Roy |
| 31-Oct | Graph comparison and alignment | Wrap up deep RL for features;MF for alignment | Aligning protein-protein interactions | (1) RLpdf pptx; (2)Alignment: pdf pptx | (1) Variational GraphAutoEncoder; (2) FUSE | Prof. Roy |
| 10 | 5-Nov | | Alignment continued | Aligning single cell omic datasets | pdf pptx | (1) MNN correct; (2) LIGER | Prof. Roy |
| 7-Nov | Network-based integration and interpretation | Graph kernels for node prioritization | Finding important genes of a process/disease | pptx pdf | GeneWanderer | Prof. Gitter |
| 11 | 12-Nov | | Graph diffusion | Finding patient/disease pathways associated with cancer | pptx pdf | HotNet | Prof. Gitter |
| 14-Nov | | Graph diffusion | Finding patient/disease pathways associated with cancer | See 12-Nov | | Prof. Gitter |
| 12 | 19-Nov | | Data integration with few samples | Integrating data from small samples | pptx pdf | PCSF | Prof. Gitter |
| 21-Nov | | Data integration with many samples | Integrating data from large samples | pptx pdf | SNF | Prof. Gitter |
| 13 | 26-Nov | | Integrating complementary networks | Protein function prediction and module learning | pptx pdf | BIONIC | Prof. Gitter |
| 28-Nov | Thanksgiving | | | | | |
| 14 | 3-Dec | Projects | | | | | |
| 5-Dec | Projects | | | | | |
| 15 | 10-Dec | Projects | |