
Genome biology, Год журнала: 2025, Номер 26(1)
Опубликована: Фев. 20, 2025
Liquid-liquid phase separation (LLPS) enables the formation of membraneless organelles, essential for cellular organization and implicated in diseases. We introduce catGRANULE 2.0 ROBOT, an algorithm integrating physicochemical properties AlphaFold-derived structural features to predict LLPS at single-amino-acid resolution. The method achieves high performance reliably evaluates mutation effects on propensity, providing detailed predictions how specific mutations enhance or inhibit separation. Supported by experimental validations, including microscopy data, it predicts across diverse organisms compartments, offering valuable insights into mechanisms mutational impacts. tool is freely available https://tools.tartaglialab.com/catgranule2 https://doi.org/10.5281/zenodo.14205831 .
Язык: Английский