Neural spectroscopy of AlphaFold2 reveals encoded protein conformational landscapes
Merged summary
TL;DR - Researchers introduce “neural spectroscopy,” showing that controlled perturbations of AlphaFold2’s weights expose coherent protein conformational landscapes. The findings suggest AlphaFold2 learned structural constraints beyond its explicit static-structure prediction objective.
- Scaled Gaussian Convolution of Evoformer weights produced physically structured conformational landscapes rather than random artifacts.
- For ubiquitin, native contacts broke in an order consistent with established folding experiments.
- Five models agreed that KaiB’s alternative fold was not recovered, while alpha-synuclein yielded distinct but coherent model-dependent landscapes.
- Matched-power noise produced debris rather than conformations, supporting the specificity of the method.
Sources (1)
Neural spectroscopy of AlphaFold2 reveals encoded protein conformational landscapes
TL;DR - Researchers introduce “neural spectroscopy,” showing that controlled perturbations of AlphaFold2’s weights expose coherent protein conformational landscapes. The findings suggest AlphaFold2 learned structural constraints beyond its explicit static-structure prediction objective.
- Scaled Gaussian Convolution of Evoformer weights produced physically structured conformational landscapes rather than random artifacts.
- For ubiquitin, native contacts broke in an order consistent with established folding experiments.
- Five models agreed that KaiB’s alternative fold was not recovered, while alpha-synuclein yielded distinct but coherent model-dependent landscapes.
- Matched-power noise produced debris rather than conformations, supporting the specificity of the method.