# AlphaFold's Bayesian Roots in Probability Kinematics

arXiv: https://arxiv.org/abs/2505.19763 · HTML: https://mlsanity.com/paper/2505.19763/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 57 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 9 of 9)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [A New Approach to Probabilistic Programming Inference](https://mlsanity.com/paper/1507.00996/) (2015)
- [Recent advances in directional statistics](https://mlsanity.com/paper/2005.06889/) (2020)
- [Uncertain Evidence in Probabilistic Models and Stochastic Simulators](https://mlsanity.com/paper/2210.12236/) (2022)
- [Bayesian Neural Networks with Soft Evidence](https://mlsanity.com/paper/2010.09570/) (2020)
- [Internal-Coordinate Density Modelling of Protein Structure: Covariance Matters](https://mlsanity.com/paper/2302.13711/) (2023)
- [Fisher's Legacy of Directional Statistics, and Beyond to Statistics on Manifolds](https://mlsanity.com/paper/2405.17919/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards More General Control of Diffusion Models Using Jeffrey Guidance](https://mlsanity.com/paper/2606.13240/) (2026)

## Abstract (arXiv)

The seminal breakthrough of AlphaFold in protein structure prediction relied on a learned potential energy function parameterized by deep models, in contrast to its successors AlphaFold2 and AlphaFold3, which lack an explicit probabilistic interpretation. While AlphaFold's potential was originally justified by heuristic analogy to physical potentials of mean force, we show that it can instead be understood as a principled instance of probability kinematics (PK), also known as Jeffrey conditioning, a generalization of Bayesian updating. This reinterpretation reveals that AlphaFold is a generalized Bayesian model that explicitly defines a posterior distribution over structures, providing a deeper explanation of its success and a foundation for future model design. To demonstrate this framework with precision, we introduce a tractable synthetic model in which an angular random walk prior is updated with distance-based evidence via PK, directly mirroring AlphaFold's mechanism. This setting allows us to explore the probabilistic foundations of AlphaFold in a clear and interpretable way. Our work connects a landmark in protein structure prediction to a broader class of compositional deep generative models and points to new opportunities for principled probabilistic approaches.