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.
Computational biology and bioinformatics is an interdisciplinary field that develops and applies computational methods to analyse large collections of biological data, such as genetic sequences, cell populations or protein samples, to make new predictions or discover new biology. The computational methods used include analytical methods, mathematical modelling and simulation.
Pebblescout navigates vast, rapidly growing nucleotide content in resources by providing indexing and search capabilities. We used Pebblescout to index a metagenomic subset of Sequence Read Archive and seven other resources into databases spanning over 3.7 petabases and searchable interactively at a pilot website using queries as short as 42 bases.
MISATO, a dataset for structure-based drug discovery combines quantum mechanics property data and molecular dynamics simulations on ~20,000 protein–ligand structures, substantially extends the amount of data available to the community and holds potential for advancing work in drug discovery.
By using volunteers to map roads in forests across Borneo, Sumatra and New Guinea, an innovative study shows that existing maps of the Asia-Pacific region are rife with errors. It also reveals that unmapped roads are extremely common — up to seven times more abundant than mapped ones. Such ‘ghost roads’ are promoting illegal logging, mining, wildlife poaching and deforestation in some of the world’s biologically richest ecosystems.
Estimates of palaeodiversity are biased by the incompleteness of the fossil record. Here, the authors develop DeepDive, a deep learning approach that infers richness while accounting for record heterogeneity, and test it with two empirical datasets.
A deep learning model is used to classify central nervous system tumors based on their DNA methylation profile directly from histopathology, and showed high accuracy in a large set of external validation cohorts, potentially informing downstream treatment.
DNA methylation (DNAm) clocks can track mitotic age, but their potential use for cancer risk prediction remains less explored. Here, the authors develop a DNAm counter of total mitotic age (stemTOC) that shows an increase of mitotic age in normal tissues and precancerous lesions.
Generative artificial intelligence (AI), exemplified by large language models such as ChatGPT, shows promise in mental health practice, aiding research, training and therapy. However, bias, inaccuracy and trust issues necessitate careful integration with human expertise.
As quantum technology advances, it holds immense potential to accelerate oncology discovery through enhanced molecular modeling, genomic analysis, medical imaging, and quantum sensing.
Pebblescout navigates vast, rapidly growing nucleotide content in resources by providing indexing and search capabilities. We used Pebblescout to index a metagenomic subset of Sequence Read Archive and seven other resources into databases spanning over 3.7 petabases and searchable interactively at a pilot website using queries as short as 42 bases.
In this Tools of the Trade article, Vipul Singhal and Nigel Chou describe BANKSY, a machine learning tool that harnesses gene expression gradients from the neighbourhood of a cell for cell typing and domain segmentation.