MOTIVATION: Metabolism occurs in a cell type-specific manner, but which cells regulate metabolite levels remains unclear. RESULTS: Here, we integrate some of the largest metabolite quantitative trait loci datasets, TOPMed and UK Biobank, with one of the most extensive single-cell RNA sequencing resources, Tabula Sapiens. This integration allows us to identify cell types that regulate metabolites body-wide. We find hepatocytes are the primary regulatory cell type for most metabolites, associating with 385/410 (94%) metabolites for whom an association is found. Additionally, our multi-gene approach reveals more metabolite associations with beta cells compared to those identified using a single-gene approach. For example, we identify novel metabolite-cell type associations, such as the association between phenylpropanoic acid and beta cells, this metabolite that was previously thought to be regulated by the microbiome. AVAILABILITY: Code used in this work is available via Github at https://github.com/haimkru/Metabolite-Cell-Type-Associations.

MOTIVATION: Proteins are known to share similarities in local regions of three-dimensional (3D) structure even across disparate global folds. Such correspondences can help to shed light on functional relationships between proteins and identify conserved local structural features that lead to function. Self-supervised deep learning on large protein structure datasets has produced high-fidelity representations of local structural microenvironments, providing the opportunity to characterize the landscape of local structure and function at scale. RESULTS: In this work, we leverage these representations to cluster over 15 million environments in the Protein Data Bank, resulting in the creation of a "lexicon" of local 3D motifs which form the building blocks of all known protein structures. We characterize these motifs and demonstrate that they provide valuable information for modeling structure and function at all scales of protein analysis, from full protein chains to binding pockets to individual amino acids. We devise a new protein representation based solely on its constituent local motifs and show that this representation enables state-of-the-art performance on protein structure search and model quality assessment. We then show that this approach enables accurate prediction of drug off-target interactions by modeling the similarity between local binding pockets. Finally, we identify structural motifs associated with pathogenic variants in the human proteome by leveraging the predicted structures in the AlphaFold structure database. AVAILABILITY AND IMPLEMENTATION: All code and cluster data are available at https://github.com/awfderry/collapse-motifs.