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.
MISATO is a database for structure-based drug discovery that combines quantum mechanics data with molecular dynamics simulations on ~20,000 protein–ligand structures. The artificial intelligence models included provide an easy entry point for the machine learning and drug discovery communities.
A fast and versatile three-dimensional cell-based model, called SimuCell3D, is developed for high-resolution simulations of large and complex biological tissues. SimuCell3D natively integrates intra- and extracellular entities, including extracellular matrix, nuclei and polarized cell surfaces.
The authors introduce two cellular barcoding tools: CellBarcode, for extracting and filtering diverse DNA barcodes from bulk and single-cell sequencing data; and CellBarcodeSim, for simulating barcoding experiments, thus enabling the investigation of the impact of biological and technical factors on barcode detection.
GRAPE is a software resource for graph learning and embedding that is orders of magnitude faster than existing state-of-the-art libraries, making large-graph analysis feasible in a wide range of real-world applications.
An approach, CorALS, is proposed to enable the construction and analysis of large-scale correlation networks for high-dimensional biological data as an open-source framework in Python.
A computational method is proposed to generate the full-scale dataset of the tridimensional position and connectivity of neurons in the CA1 region of the human hippocampus starting from high-resolution microscopy images and experimental data.
Data visualization is widely used in science, but interpreting such visualizations is prone to error. Here a dynamic visualization is introduced for capturing more information and improving the reliability of visual interpretations.
A computational workflow centered on probabilistic machine learning is developed to reconstruct the energy dispersion from photoemission band-mapping data. The workflow uncovers previously inaccessible momentum-space structural information at scale.
The Absolut! framework can generate synthetic three-dimensional antibody–antigen structures to assist machine learning and dataset construction for antibody design. Most importantly, the relative machine learning performance learnt on Absolut! datasets is shown to transfer to experimental datasets.
The authors present an open-source framework that enables fast and accurate time–frequency analysis of signals and demonstrate it on real-world applications, such as signals from the brain–computer interface.
The D4 format for genomics datasets employs an adaptive encoding strategy based on the relatively low variance of sequence coverage. This encoding improves the speed at which these datasets can be queried for biological inquiry, while also achieving better or comparable file sizes than existing formats.
The R package barcodetrackR facilitates the analysis and visualization of clonal tracking data, and it includes a graphical user interface to allow researchers without programming experience to utilize various quantitative tools.
DNA profiles of suspects that are searched in criminal databases, such as CODIS, are often retained and can result in racial profiling. This work builds a privacy-preserving CODIS query system to support DNA profile searches while preserving individual privacy.
Scellnetor is a single-cell network enrichment method that can unravel connected molecular interaction networks to explain the progression and differentiation of developmental trajectories on a systems biology level.
