Niching methods integrated with a differential evolution memetic algorithm for protein structure prediction

Protein structure prediction with energy minimization and deep learning approaches

“…Rosetta parameter increase_cycles is set to 10 (which multiplies the default values of fragment insertion cycles in the different Rosetta stages, details in Rohl et al. ( 2004 ) and Varela and Santos ( 2022 )), as recommended on the Rosetta site ( http://www.rosettacommons.org ).…”

“…Detailed information about these four stages can be found, for example in Rohl et al. ( 2004 ) and Varela and Santos ( 2022 ), while Fig. 2 illustrates schematically the search process of the Rosetta ab initio protocol with its four stages.…”

“…Consequently, one strategy is to obtain a set of optimized conformations (with minimal energy) with structural diversity. For this purpose, we introduced niching methods such as crowding, fitness sharing and speciation into the HybridDE version, thus forcing the search algorithm to obtain optimized conformations in different niches (with different structural conformations) (Varela and Santos 2022 ). This increases the chances of obtaining candidate structures close to the native structure.…”

“…This increases the chances of obtaining candidate structures close to the native structure. The crowding niching method was found to be the most useful niching technique in the application, given its simple parameter decision process, defining the CrowdingDE version, detailed in Varela and Santos ( 2020 , 2022 ).

Fig.

…”

“… 1953 ) to decide whether a structural fragment replaces a part of the current conformational structure of the target protein, with the goal of finding the structure with the minimum energy. Working with the fragment replacement technique as a local search operator, our evolutionary/memetic computational solutions ( HybridDE and CrowdingDE ) (Varela and Santos 2019 , 2020 , 2022 ) outperform Rosetta ab initio protocol when searching for structures with minimal energy and under the same number of conformational energy evaluations.…”