liveBook · Manning

Self-organizing map

As explained in Build AI Drug Discovery Pipelines

A self-organizing map is an unsupervised neural-network technique that maps high-dimensional data onto a lower-dimensional grid while preserving neighborhood relationships.

A self-organizing map (SOM) projects high-dimensional data onto a low-dimensional grid while preserving neighborhood relationships. For chemical screening, it turns 2,048-dimensional Morgan fingerprints into a two-dimensional map that helps visualize similar compounds and potential clusters. section 7.1.2

A SOM training workflow:

  • Initialize a rectangular or hexagonal grid whose nodes contain randomly initialized vectors matching the input dimensionality. section 7.1.2
  • Select an input vector and compare it with every node using a distance metric such as Euclidean distance. section 7.1.2
  • Choose the closest node as the best matching unit (BMU), then update the BMU and neighboring nodes toward the input. section 7.1.2

From colored beads to drug repurposing

The intuition uses colored beads encoded as RGB vectors: nearby colors map to nearby nodes. The same process maps molecular fingerprints. In drug repurposing, nodes receive the plurality activity label of their training compounds; unseen compounds assigned to active nodes become candidate hits for further study. section 7.1.2 section 7.1.3

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains grid initialization, BMU selection, neighborhood updates, topology visualization, and hyperparameter search without detailing full implementation.
Examples
Uses RGB-colored beads, 2,048-dimensional molecular fingerprints, activity-enriched nodes, U-MAT maps, and Drug Repurposing Hub compounds.
What it assumes
Assumes vector representations and distance comparisons while introducing BMUs, grids, neighborhood updates, and node labeling.
What you can do after
Apply it via MiniSom to map fingerprints, label nodes by activity, and prioritize unseen compounds near active regions.
How it connects
Connects unsupervised learning with PCA, Morgan fingerprints, distance metrics, U-MAT visualization, and drug repurposing.

Also explained in

Compare how 2 books explain self-organizing map →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.