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

Abstract

In chemical library analysis, it may be useful to describe libraries as individual items rather than collections of compounds. This is particularly true for ultra-large noncherry-pickable compound mixtures, such as DNA-encoded libraries (DELs). In this sense, the chemical library space (CLS) is useful for the management of a portfolio of libraries, just like chemical space (CS) helps manage a portfolio of molecules. Several possible CLSs were previously defined using vectorial library representations obtained from generative topographic mapping (GTM). Given the steadily growing number of DEL designs, the CLS becomes "crowded" and requires analysis tools beyond pairwise library comparison. Therefore, herein, we investigate the cartography of CLS on meta-(μ)GTMs� "meta" to remind that these are maps of the CLS, itself based on responsibility vectors issued by regular CS GTMs. 2,5 K DELs and ChEMBL (reference) were projected on the μGTM, producing landscapes of library-specific properties. These describe both interlibrary similarity and intrinsic library characteristics in the same view, herewith facilitating the selection of the best projectspecific libraries.

PredictingS. aureusantimicrobial resistance with interpretable genomic space maps

“…In the context of this study, the conventional GTM model has been employed for AMR prediction. Nevertheless, it is worth noting that various GTM-specific techniques, including meta-GTM [54] and s-GTM [55], may hold promise for further in-depth investigation of genotype-phenotype relationships and validating model accuracy with respect to population structure [11]. The thorough exploration of these techniques, their integration with feature selection methodologies [8], their applicability to diverse bacterial species as well as systematic GTM performance comparison with other models available to date constitute topics for the future research.…”