Mining the chemical quarry with joint chemical probes: An application of latent semantic structure indexing (LaSSI) and TOPOSIM (dice) to chemical database mining

In this study we use a novel similarity search technique called latent sema ntic structure indexing (LaSSI) with joint chemical probes as queries to mi ne the MDL drug data report database. LaSSI is based on latent semantic ind exing developed for searching textual databases. We use atom pair and topol ogical torsion descriptors in our calculations. The results obtained with L aSSI are compared with another in-house similarity search technique TOPOSIM . The results from the similarity searches using joint chemical probes are significantly better than searches using single chemical probes for both La SSI and TOPOSIM. The selected molecules are closely related in activity to their queries and are ranked among the top 300 scoring molecules of the 82 860 entries in the database. Our implementation of LaSSI is very fast and e fficient in finding active compounds. The results also show that LaSSI cons istently retrieves more diverse chemical structures representative of the j oint chemical probes in comparison to TOPOSIM. The use of multimolecule top ological probes to identify compounds complements the use of searching data bases with 3D pharmacophore hypotheses.