About Discovering Collective Variables of Molecular Transitions via Genetic Algorithms and Neural Networks

Authors: Ferry Hooft, Alberto Pérez de Alba Ortíz, and Bernd Ensing

We have been developing a machine learning framework to automatically find, from simulation data, the set of collective variables that best describe the reaction coordinate of complex reactions and molecular transitions. We demonstrated our method, named FABULOUS, for example on describing a biologically relevant transition in DNA. The resulting reaction coordinate allowed us to obtain the reaction free energy profile and the reaction rate of the transition. The FABULOUS software, developed by Ferry Hooft and Alberto Pérez de Alba Ortíz, has been made freely available to the community on github. A paper on this work appeared in March [1] and the work was presented last week at the Lorentz Center Workshop on “Accelerating the Understanding of Rare Events” in Leiden.

Discovering Collective Variables of Molecular Transitions via Genetic Algorithms and Neural NetworksFerry Hooft, Alberto Pérez de Alba Ortíz, and Bernd Ensing, J. Chem. Theory Comput. 17, 4, 2294–2306 (2021) 

Get in Touch

Your Name:
How can we reach you?
What would you like to discuss?
What would you like to share? (Max. 2Mb, Format:jpg or pdf)