Contact

All Publications

  • Unsupervised learning reveals landscape of local structural motifs across protein classes. Bioinformatics (Oxford, England) Derry, A., Krupkin, H., Tartici, A., Altman, R. B. 2025

    Abstract

    Proteins are known to share similarities in local regions of 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.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.All code and cluster data are available at https://github.com/awfderry/collapse-motifs  .Supplementary data are available at Bioinformatics online.

    View details for DOI 10.1093/bioinformatics/btaf377

    View details for PubMedID 40569048

  • Sarcopenia and Cognitive Decline in Hospitalized Older Adults from a Prospective Study. Aging and disease Kon-Kfir, S., Cukierman-Yaffe, T., Krupkin, H., Belkin, A., Shlomai, G., Bleier, J., Weinstein, S., Bruckmayer, L., Prinz, E., Kaplan, A., Shraga, M. G., Lev, D., Dekel, S., Shalmon, N., Tsarfaty, N., Reiss, N., Bischof, E., Leibowitz, A. 2025

    Abstract

    As populations age, sarcopenia increasingly impacts healthcare due to its associations with morbidity, mortality, and cognitive decline. This study is a cross-sectional analysis of prospectively collected data from 140 older adults hospitalized in an internal medicine department. Sarcopenia was measured by handgrip strength, and cognitive function by the Digit Symbol Substitution Test (DSST). Sarcopenic patients (n=78) had lower DSST scores (p=0.003) and Norton scores (p&;lt0.001) compared to non-sarcopenic patients. Handgrip strength showed a significant positive correlation with DSST scores (R=0.26, p=0.0019), persisting after adjustments for age and sex (R=0.42, p=1.7e-07). This study underscores a significant association between sarcopenia and cognitive decline in hospitalized older adults, advocating for routine sarcopenia and cognitive assessments upon admission. These findings emphasize the importance of identifying at-risk patients early and developing targeted interventions. Future research should further explore underlying mechanisms and validate findings in broader cohorts.

    View details for DOI 10.14336/AD.2024.1676

    View details for PubMedID 40153579