Tanimoto Similarity
A method for measuring the similarity between two molecular fingerprint vectors, defined as the size of the intersection divided by the size of the union, taking values from 0 to 1. It is regarded in the field of cheminformatics as one of the gold standards for structural similarity.
Timeline (last 90 days)
SAGA (Structure-Aware Guided Alignment) is a training-only regularization method that aligns neural molecular representations with fingerprint-based Tanimoto similarity via centered kernel alignment (CKA).
In molecular optimization, commonly used similarity measures include Tanimoto similarity (based on Morgan fingerprints) and MACCS fingerprint similarity, with values ranging from 0 to 1.
A Tanimoto similarity of ≥0.85 is generally considered highly similar, while ≥0.7 indicates that the structural scaffold is largely preserved.
All Facts (3)
SAGA (Structure-Aware Guided Alignment) is a training-only regularization method that aligns neural molecular representations with fingerprint-based Tanimoto similarity via centered kernel alignment (CKA).
50%UnverifiedIn molecular optimization, commonly used similarity measures include Tanimoto similarity (based on Morgan fingerprints) and MACCS fingerprint similarity, with values ranging from 0 to 1.
50%UnverifiedA Tanimoto similarity of ≥0.85 is generally considered highly similar, while ≥0.7 indicates that the structural scaffold is largely preserved.
50%