Growing Phylogenetic-like Trees
Preprocess:
- Describe compounds with keys
Process:
- Cluster active compounds with SOM
- Detect “hotspots” in the SOM
- Extract/learn filter-keys from hotspots
- Determine set of “useful” learned filter-keys
- Subset compounds with each useful filter-key
- Subset active compounds with each useful filter-key
- Filter compounds is a smarts query
- Repeat on each subset, i.e. grow tree
Structural Family Identification