Computer modelling articles from across Nature Portfolio

Signalosomes amplify cellular responses, but how they avoid uncontrolled activation is unclear. The authors use quantitative super-resolution imaging and mathematical modeling to reveal optimal RIP3:RIP1 ratios that ensure precise cell death signaling.

Recent advances in AI have transformed RNA research by enabling powerful sequence-based predictions. Here, the authors benchmark eleven genomic language models across four RNA-related tasks, showing that biological context and model design, not just scale, drive performance and inform model selection.

Hormone systems control diverse physiological functions but consistent rules to model these circuits remain incompletely understood. Here the authors use mathematical modelling to report that 43 hormone circuits can be divided into five classes based on regulatory motifs and that the circuit structure relates to function.

Artificial intelligence approaches that link patient data with chemical-induced kidney injury patterns are revolutionizing nephrotoxicity risk assessment. Substantial progress has been made in the development of integrated approaches that leverage big data, molecular profiles and toxicological understanding to identify at-risk patients, provide insights into molecular mechanisms and advance predictive nephrology.

With biomedical sciences quickly outgrowing many other application areas in terms of data generation, there is a unique opportunity for life sciences to become one of the greatest beneficiaries of research in machine learning and AI, and also inspire foundational developments in it.

In this Tools of the Trade article, Amir Giladi describes the development and use of PIC-seq, which enables the direct enrichment and analysis of conjugates of physically interacting cells in the tumour microenvironment.