Abstract
Generative topographic mapping was used to investigate the possibility to diversify the in-house compounds collection of Boehringer Ingelheim (BI). For this purpose, a 2D map covering the relevant chemical space was trained, and the BI compound library was compared to the Aldrich-Market Select (AMS) database of more than 8M purchasable compounds. In order to discover new (sub)structures, the "AutoZoom" tool was developed and applied in order to analyze chemotypes of molecules residing in heavily populated zones of a map and to extract the corresponding maximum common substructures. A set of 401K new structures from the AMS database was retrieved and checked for drug-likeness and biological activity.
Highlights
Structural library enrichment is an important task for pharmaceutical industry
In order to train the GTM manifold, a Frame set (FS) of 25K compounds needed for the manifold construction was diversity-picked from the Aldrich-Market Select (AMS) library with the dissimilarity threshold equal to 0.4
Some 94.1% of the Boehringer Ingelheim (BI) Pool and 95.8% of the AMS collections passed the LLh threshold which means that the frame set extracted from AMS is diverse enough to describe both databases
Summary
Structural library enrichment is an important task for pharmaceutical industry. To be efficient in drug-discovery, One can suggest two different scenarios of the screening pool enrichment with new chemical matter: computer-aided enumeration of virtual structures under some constraints (e.g. molecular weight, LogP, etc.), or selection of existing structures from an external database. Several attempts were made to create a workflow for an efficient molecular de novo design [1,2,3,4,5]. The second scenario is more practical because new structures selected as a result of comparison of two data sets (a reference set and an external set) do exist and can be purchased or synthesized following the reported in the literature procedure
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
