Figures
Towards the next generation of localisation prediction algorithms
A key facet of both natural and artificial intelligence lies in their predictive potential. The last decade offered a mere glimpse of AI's revolutionary potential in predicting protein structures. AI's impact on predictability and understanding in biology is destined to expand towards phenomena such as intracellular protein sorting. We outline a roadmap for next-generation algorithms emphasizing the integration of evolutionary and experimental diversity in training data and model parameters inspired by evolutionary cell biology. With the prevalence of advanced machine learning increasing, our analyses exemplify how diversity can bridge AI and biology, fostering novel insights and breakthroughs. Gould et al
Image Credit: Parth K. Raval
Citation: (2024) PLoS Computational Biology Issue Image | Vol. 20(11) December 2024. PLoS Comput Biol 20(11): ev20.i11. https://doi.org/10.1371/image.pcbi.v20.i11
Published: December 4, 2024
Copyright: © 2024 . This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
A key facet of both natural and artificial intelligence lies in their predictive potential. The last decade offered a mere glimpse of AI's revolutionary potential in predicting protein structures. AI's impact on predictability and understanding in biology is destined to expand towards phenomena such as intracellular protein sorting. We outline a roadmap for next-generation algorithms emphasizing the integration of evolutionary and experimental diversity in training data and model parameters inspired by evolutionary cell biology. With the prevalence of advanced machine learning increasing, our analyses exemplify how diversity can bridge AI and biology, fostering novel insights and breakthroughs. Gould et al
Image Credit: Parth K. Raval