Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
This Perspective discusses the potential of protein structure-prediction models for exploring the structural landscape and specificity of TCR–pMHC interactions.
We created DELiVR, a deep-learning pipeline for 3D brain-cell mapping that is trained with virtual reality-generated reference annotations. It can be deployed via the user-friendly interface of the open-source software Fiji, which makes the analysis of large-scale 3D brain images widely accessible to scientists without computational expertise.
Several research groups are making it easier for other neuroscientists to analyze large datasets by providing tools that can be accessed and used from anywhere in the world.
Cell segmentation currently involves the use of various bespoke algorithms designed for specific cell types, tissues, staining methods and microscopy technologies. We present a universal algorithm that can segment all kinds of microscopy images and cell types across diverse imaging protocols.
RoboEM, an artificial intelligence (AI)-based flight agent, automatically steers through three-dimensional electron microscopy (3D-EM) images of brain tissue to follow neurites. RoboEM substantially improves state-of-the-art automated reconstructions, eliminating manual proofreading needs in complex connectomic analysis problems and paving the way for high-throughput, cost-effective, large-scale mapping of neuronal networks — connectomes.
The exceptionally photostable green fluorescent protein StayGold has been monomerized in different laboratories, which has generated three unique monomeric variants that will enable new imaging applications.
New condenser aperture designs form square or rectangular beams that match the camera dimensions, which efficiently expands the data acquisition area in cryogenic electron microscopy.
Diploid assembly is a difficult task that requires several types of genomic sequencing data, including — but not limited to — HiFi reads and parental sequences. Hypo-assembler, an assembly algorithm, uses high quality solid k-mers extracted from Illumina data alongside Nanopore reads to produce a high-quality diploid assembly using only Nanopore and Illumina data.
We developed a high-content profiling method named vibrational painting (VIBRANT) for single-cell drug response measurements, combining vibrational imaging, multiplexed vibrational probes and machine learning. VIBRANT showed high performance in predicting drug mechanisms of action, discovering novel compounds and assessing drug combinations, demonstrating great promise for phenotypic drug discovery.
We introduce a biomimetic antigen-presenting system that uses hexapod heterostructures for specific T cell recognition at the single-molecule and single-cell levels. The system enables high-resolution T cell activation, uses magnetic forces to increase immune responses, and offers flexible and precise identification of antigen-specific T cell receptors, aiding the study of T cell recognition and immune cell mechanics.
Interactions between RNA and RNA-binding proteins (RBPs) define the fate and function of every RNA molecule. We present TREX, or targeted RNase H-mediated extraction of crosslinked RBPs, an efficient and accurate method to unbiasedly reveal the protein interactors of specific regions of RNAs isolated from living cells.
We established a method to generate complex self-organizing bone marrow-like organoids (BMOs) via concomitant differentiation of human induced pluripotent stem cells. These BMOs consist of hematopoietic cells, stromal niche cells and de novo vascular networks. In addition, they contain multipotent hematopoietic stem and progenitor cells, as well as mesenchymal stem and progenitor cells; they model aspects of the three-dimensional bone marrow architecture and can be used to study developmental and aberrant hematopoiesis.
We developed Significant Latent Factor Interaction Discovery and Exploration (SLIDE), an interpretable machine learning approach that can infer hidden states (latent factors) underlying biological outcomes. These states capture the complex interplay between factors derived from multiscale, multiomic datasets across biological contexts and scales of resolution.
We developed Tapioca, an integrative ensemble machine learning-based framework, to accurately predict global protein–protein interaction network dynamics. Tapioca enabled the characterization of host regulation during reactivation from latency of an oncogenic virus. Introducing an interactome homology analysis method, we identified a proviral host factor with broad relevance for herpesviruses.
This Perspective presents a reliable and comprehensive source of information on pitfalls related to validation metrics in image analysis, with an emphasis on biomedical imaging.
Metrics Reloaded is a comprehensive framework for guiding researchers in the problem-aware selection of metrics for common tasks in biomedical image analysis.