Dataset Similarity and Clustering – DBSCAN¶
This Floe clusters datasets based on pre-generated fingerprints using Tanimoto similarity calculation and sklearn DBSCAN clustering. The Floe can generate the following datasets:
Members dataset that will contain each molecule from the input dataset with cluster id, cluster size, and cluster member id data fields.
Cores dataset that contains one representative from each cluster with the cluster id and cluster size data fields.
Singletons dataset that contains clusters with only one member.
When writing the singletons dataset, neither the members nor the cores output datasets will contain the singleton records.
If two molecules have a fingerprint Tanimoto similarity score less than the Minimum Similarity Score Cutoff parameter, they can be clustered together.
Increasing the default cutoff value will result in more clusters with fewer members and more singletons.
Decreasing the default cutoff value will result in less clusters with more members and less singletons.
This Floe has to cache records and generate an NxN similarity matrix, therefore, it is not suitable for handling a very large dataset (more than 100K).
The fingerprint can be pre-generated using the following two Floes in this package:
Fingerprint Generation
Fingerprint Generation (User Defined) Floe
Extra Required Parameters