Convolutional networks for supervised mining of molecular patterns within cellular context (Nature Methods)

2 Jan

CLEM-Reg: An automated point cloud based registration algorithm for correlative light and volume electron microscopy

Correlative light and volume electron microscopy (vCLEM) is a powerful imaging technique that enables the visualisation of fluorescently labelled proteins within their ultrastructural context on a subcellular level. Currently, expert microscopists align vCLEM acquisitions using time-consuming and subjective manual methods. This paper presents CLEM-Reg, an algorithm that automates the 3D alignment of vCLEM datasets by leveraging probabilistic point cloud registration techniques. These point clouds are derived from segmentations of common structures in each modality, created by state-of-the-art open-source methods, with the option to leverage alternative tools from other plugins or platforms. CLEM-Reg drastically reduces the time required to register vCLEM datasets to a few minutes and achieves correlation of fluorescent signal to sub-micron target structures in EM on three newly acquired vCLEM benchmark datasets (fluorescence microscopy combined with FIB-SEM or SBF-SEM). CLEM-Reg was then used to automatically obtain vCLEM overlays to unambiguously identify TGN46-positive transport carriers involved in the trafficking of proteins between the trans-Golgi network and plasma membrane. The datasets are available in the EMPIAR and BioStudies public image archives for reuse in testing and developing multimodal registration algorithms by the wider community. A napari plugin integrating the algorithm is also provided to aid end-user adoption. DOI: 10.1101/2023.05.11.540445

2 Jan

Boltz-1: Democratizing Biomolecular Interaction Modeling

Understanding biomolecular interactions is fundamental to advancing fields like drug discovery and protein design. In this paper, we introduce Boltz-1, an open-source deep learning model incorporating innovations in model architecture, speed optimization, and data processing achieving AlphaFold3-level accuracy in predicting the 3D structures of biomolecular complexes. Boltz-1 demonstrates a performance on-par with state-of-the-art commercial models on a range of diverse benchmarks, setting a new benchmark for commercially accessible tools in structural biology. By releasing the training and inference code, model weights, datasets, and benchmarks under the MIT open license, we aim to foster global collaboration, accelerate discoveries, and provide a robust platform for advancing biomolecular modeling. DOI: 10.1101/2024.11.19.624167

2 Jan

Fast protein structure searching using structure graph embeddings

Comparing and searching protein structures independent of primary sequence has proved useful for remote homology detection, function annotation and protein classification. Fast and accurate methods to search with structures will be essential to make use of the vast databases that have recently become available, in the same way that fast protein sequence searching underpins much of bioinformatics. We train a simple graph neural network using supervised contrastive learning to learn a low-dimensional embedding of protein structure. The method, called Progres, is available as software at https://github.com/greener-group/progres and as a web server at https://progres.mrc-lmb.cam.ac.uk. It has accuracy comparable to the best current methods and can search the AlphaFold database TED domains in a tenth of a second per query on CPU. DOI: 10.1101/2022.11.28.518224

26 Nov 2024

Structural ubiquitin contributes to K48 linkage-specificity of the HECT ligase Tom1

Homologous to E6AP C-Terminus (HECT) ubiquitin ligases play key roles in essential pathways such as DNA repair, cell cycle control or protein quality control. Tom1 is one of five HECT ubiquitin E3 ligases encoded in the S. cerevisiae genome and prototypical for a ligase with pleiotropic functions such as ubiquitin chain amplification, orphan quality control and DNA damage response. Structures of full-length HECT ligases, including the Tom1 ortholog HUWE1, have been reported, but how domains beyond the conserved catalytic module contribute to catalysis remains largely elusive. Here, through cryogenic electron microscopy (cryo-EM) of Tom1 during an active ubiquitylation cycle, we demonstrate that the extended domain architecture directly contributes to activity. We identify a Tom1-ubiquitin architecture during ubiquitylation involving a non-canonical ubiquitin binding site in the solenoid shape of Tom1. We demonstrate that this ubiquitin binding site coordinates a structural ubiquitin contributing to the fidelity of K48 poly-ubiquitin chain assembly.

Convolutional networks for supervised mining of molecular patterns within cellular context (Nature Methods)

More articles

CLEM-Reg: An automated point cloud based registration algorithm for correlative light and volume electron microscopy

Boltz-1: Democratizing Biomolecular Interaction Modeling

Fast protein structure searching using structure graph embeddings

Structural ubiquitin contributes to K48 linkage-specificity of the HECT ligase Tom1