Figure 6.

Structural and scaffold similarity between each query and its functionally similar search results

The functionally similar molecules, as determined from the LLM-assisted patent search, from the alternate canonicalization search results contain significantly more dissimilar structures and scaffolds compared to when the canonicalization is the same as the database. Structural similarity measured by whole-molecule fingerprint Tanimoto similarity; scaffold similarity measured by scaffold fingerprint Tanimoto similarity. Asterisks indicate the level of statistical significance for two-sided independent t tests (ns, p < 1.0; ∗p < 0.05; ∗∗p < 0.01; ∗∗∗p < 0.001; ∗∗∗∗p < 0.0001).