Energy Minimization vs. Deep Learning Approaches for Protein Structure Prediction

• Juan Luis Filgueiras ^[1] ; Daniel Varela ^[1] ; José Santos ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence: 9th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2022, Puerto de la Cruz, Tenerife, Spain, May 31 – June 3, 2022, Proceedings, Part II / José Manuel Ferrández Vicente (dir. congr.), José Ramón Álvarez Sánchez (dir. congr.), Félix de la Paz López (dir. congr.), Hojjat Adeli (aut.), 2022, ISBN 978-3-031-06527-9, págs. 109-118
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • This article discusses the advantages and problems of different approaches to ab initio protein structure prediction. Recent successful approaches based on deep learning are compared with those based on protein fragment replacements and energy minimization with different search strategies, including ours based on evolutionary algorithms. Selected proteins are considered to analyze the approaches, focusing on the problems of those based on deep learning.