Chemical Library Space: Definition and DNA-Encoded Library Comparison Study Case

Abstract

The development of DNA-encoded library (DEL) technology introduced new challenges for the analysis of chemical libraries. It is often useful to consider a chemical library as a standalone chemoinformatic object�represented both as a collection of independent molecules, and yet an individual entity�in particular, when they are inseparable mixtures, like DELs. Herein, we introduce the concept of chemical library space (CLS), in which resident items are individual chemical libraries. We define and compare four vectorial library representations obtained using generative topographic mapping. These allow for an effective comparison of libraries, with the ability to tune and chemically interpret the similarity relationships. In particular, property-tuned CLS encodings enable to simultaneously compare libraries with respect to both property and chemotype distributions. We apply the various CLS encodings for the selection problem of DELs that optimally "match" a reference collection (here ChEMBL28), showing how the choice of the CLS descriptors may help to fine-tune the "matching" (overlap) criteria. Hence, the proposed CLS may represent a new efficient way for polyvalent analysis of thousands of chemical libraries. Selection of an easily accessible compound collection for drug discovery, as a substitute for a difficult to produce reference library, can be tuned for either primary or target-focused screening, also considering property distributions of compounds. Alternatively, selection of libraries covering novel regions of the chemical space with respect to a reference compound subspace may serve for library portfolio enrichment.

Meta-GTM: Visualization and Analysis of the Chemical Library Space

“…19 It was then filtered according to the rules of DEL-likeness derived in our previous work. 5 Hence, until otherwise stated, in the text, we always refer to the filtered ChEMBL28 containing 1,605,370 molecules. After standardization and filtering, ISIDA fragment descriptors of type IA-FF-FC-AP-2-3 (ISIDA fragment sequences of 2 and 3 atoms labeled by their CVFF force field types and formal charge using all paths) were calculated.…”

“…The GTM that was used in our previous study 5 for visualization of each library space and further for the generation of library-representative vectors is the "universal" GTM #1, which was developed by Casciuc et al 21 This map was trained to be able to robustly separate active from inactive compounds over a vast set of diverse biological targets. μGTM tuning followed a similar procedure, except that the specific fitness criteria (measuring the preservation on the μGTM of interlibrary neighborhood relationships in observed CLS) needed to be introduced.…”

“…2 Since the latter allows for simple and fast combinatorial synthesis and screening of an entire library of DNA-encoded compounds (one DEL can contain up to trillions of compounds 3 ), it enables the exploration of new areas of the chemical space in just a single screen, allowing for the identification of ligands for novel target classes or intractable target families. 4 However, it raises the problem of the appropriate library selection from a possible enormous chemical library space (CLS) 5 of thousands of DELs.…”

“…In our recent study, 5 we introduced CLS vectors encoding its structural or/and property information, derived from a generative topographic map of the corresponding compound collections. Herewith, the standard chemoinformatics of molecules can be seamlessly generalized to libraries.…”

“…In our previous work, 5 CLS defined as a high-dimensional vectorial space was based on the three types of belowmentioned GTM-based library descriptor vectors:…”