# Estimation of Distribution Algorithm for Protein Structure Prediction

## TL;DR

This paper introduces a specialized Estimation of Distribution Algorithm (EDA) for ab initio protein structure prediction that effectively models dihedral angle relationships, requiring minimal prior knowledge and balancing prediction quality with computational efficiency.

## Contribution

The authors developed a novel EDA with univariate and bivariate probabilistic models tailored for protein structure prediction, improving ab initio methods with less dependency on prior knowledge.

## Key findings

- The EDA accurately predicts protein structures without prior knowledge.
- Bivariate models capture dihedral angle relationships effectively.
- Compared to simple methods, the EDA offers a better balance of accuracy and computational time.

## Abstract

Proteins are essential for maintaining life. For example, knowing the structure of a protein, cell regulatory mechanisms of organisms can be modeled, supporting the development of disease treatments or the understanding of relationships between protein structures and food attributes. However, discovering the structure of a protein can be a difficult and expensive task, since it is hard to explore the large search to predict even a small protein. Template-based methods (coarse-grained, homology, threading etc) depend on Prior Knowledge (PK) of proteins determined using other methods as X-Ray Crystallography or Nuclear Magnetic Resonance. On the other hand, template-free methods (full-atom and ab initio) rely on atoms physical-chemical properties to predict protein structures. In comparison with other approaches, the Estimation of Distribution Algorithms (EDAs) can require significant less PK, suggesting that it could be adequate for proteins of low-level of PK. Finding an EDA able to handle both prediction quality and computational time is a difficult task, since they are strong inversely correlated. We developed an EDA specific for the ab initio Protein Structure Prediction (PSP) problem using full-atom representation. We developed one univariate and two bivariate probabilistic models in order to design a proper EDA for PSP. The bivariate models make relationships between dihedral angles $\phi$ and $\psi$ within an amino acid. Furthermore, we compared the proposed EDA with other approaches from the literature. We noticed that even a relatively simple algorithm such as Random Walk can find the correct solution, but it would require a large amount of prior knowledge (biased prediction). On the other hand, our EDA was able to correctly predict with no prior knowledge at all, characterizing such a prediction as pure ab initio.