Searching Chemical Space with the Bayesian Idea Generator

Abstract

The Pfizer Global Virtual Library (PGVL) is defined as a set compounds that could be synthesized using validated protocols and monomers. However, it is too large (10(12) compounds) to search by brute-force methods for close analogues of a given input structure. In this paper the Bayesian Idea Generator is described which is based on a novel application of Bayesian statistics to narrow down the search space to a prioritized set of existing library arrays (the default is 16). For each of these libraries the 6 closest neighbors are retrieved from the existing compound file, resulting in a screenable hypothesis of 96 compounds. Using the Bayesian models for library space, the Pfizer file of singleton compounds has been mapped to library space and is optionally searched as well. The method is >99% accurate in retrieving known library provenance from an independent test set. The compounds retrieved strike a balance between similarity and diversity resulting in frequent scaffold hops. Four examples of how the Bayesian Idea Generator has been successfully used in drug discovery are provided. The methodology of the Bayesian Idea Generator can be used for any collection of compounds containing distinct clusters, and an example using compound vendor catalogues has been included.

New Modalities, Technologies, and Partnerships in Probe and Lead Generation: Enabling a Mode-of-Action Centric Paradigm

“…With computing limitations progressively vanishing and the rise of machine learning algorithms, in addition to novel scoring methodologies, , the question of library size and composition is becoming central. Since the size of small molecule chemical space is vast at over 10 63 drug-like small molecules, rational selection approaches have to be considered, in particular since hits have to be synthesized to confirm their predicted activity. One approach consists in selecting commercially available compounds.…”

e-LEA3D: a computational-aided drug design web server

“…In this case, synthetic chemistry experts may help in defining a synthetic route and in selecting possible reactants to create a combinatorial library (13). For example, van Hoorn and Bell designed a Bayesian Idea Generator to identify the likely chemistry protocols associated with a given compound (14). …”

Recent Advances in the Medicinal Chemistry of the Metabotropic Glutamate Receptor 1 (mGlu1)

“…This opportunity was identified using a computational tool known as a Bayesian Idea Generator, BIG (devised and now published upon by Van Hoorn of Pfizer) . BIG is a method that applies Bayesian staistics to identify the nearest validated parallel synthesis-enabled chemical space related to your single input molecule.…”