1. **Graph Construction:**
  - Given the molecular strings (under SMILES format), We have to construct graphs for each SMILES string. 
  - Then, you can represent as a graph for each object, which means that 2500 molecules object will have 2500 graphs.

2. **Graph Similarity**
  - Given a few molecular strings (test dataset), finding the similar graphs.
  - Students can use some similarity measurements, i.e., Graph Edit Distance, average_shortest_path_length, diameter, etc.)

3. **Graph Classification**
  1. Using some conventional models, i.e., SVM classifier to classify the molecules.
    - You need to split the dataset into train/test set or train/validation/test set based on ratio. Or you can use the train/test dataset, which is already prepared.
    - Note: Graph-based features could be degree distribution, clustering coefficient, or centrality measures.
  2. Graph visualization 
    - Students can use T-Sne/PCA.

4. **Write a report about what you found, and explain the idea, method, and result.**

- Suggestion library for AI:
  - Sklearn for Machine Learning model.
  - Deep Learning model: Pytorch.