Variability of x-fold cross validation results
Should multiple splits be run?
Binary molecules and the cartridge
With a diversion into using PostgreSQL like a document store
Colliding bits III, expanded
Looking at numbers of collisions and their impact on similarity
Colliding bits II, revisited
The impact of bit collisions on machine-learning performance
Timing methods for serializing molecules
Quickly saving/restoring molecules from text formats
Dealing with multiconformer SD files
If only we could reliably use better file formats
Optimizing conformer generation parameters
Improving the speed of the RDKit’s conformer generator
A Ternary GHOST
Extending the threshold-shifting algorithm to three-class problems
R-Group Decomposition and Highlighting
Making pretty pictures for SAR analysis
Looking at the number of bits set by different fingerprints
How many features do we find?
Simulating count fingerprints
An approximation to make working with count vectors more efficient
Fingerprint similarity thresholds for database searches
FOMO and similarity search
Thresholds for “random” in fingerprints the RDKit supports
When is it just noise?
Looking at random-coordinate embedding
An alternative starting point for conformer generation
Sphere exclusion clustering with the RDKit
Very fast clustering for larger datasets
