Using genetic algorithms to discover novel ground-state triplet conjugated polymers

Abarbanel, Omri; Hutchison, Geoffrey

doi:10.1039/d3cp00185g

Cited by 1 publication

(1 citation statement)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the near-infinite size of chemical space, computational tools provide the most efficient means to find novel molecular candidates with optimized properties tailored to specific applications. Multiple inverse design methods have been used to traverse chemical space, including generative machine learning 5,6 (ML), genetic algorithms 3,[7][8][9][10][11] and heuristic global optimization 12 . If one wishes to find the best molecular candidates for a given property for which we have no prior knowledge or little data, however, ML methods will not be suitable since they require training.…”

Section: Introductionmentioning

confidence: 99%

Determining best practices for using genetic algorithms in molecular discovery

Greenstein,

Elsey,

Hutchison

2023

The Journal of Chemical Physics

Self Cite

View full text Add to dashboard Cite

Genetic algorithms (GAs) are a powerful tool to search large chemical spaces for inverse molecular design. However, GAs have multiple hyperparameters that have not been thoroughly investigated for chemical space searches. In this tutorial, we examine the general effects of a number of hyperparameters, such as population size, elitism rate, selection method, mutation rate, and convergence criteria, on key GA performance metrics. We show that using a self-termination method with a minimum Spearman’s rank correlation coefficient of 0.8 between generations maintained for 50 consecutive generations along with a population size of 32, a 50% elitism rate, three-way tournament selection, and a 40% mutation rate provides the best balance of finding the overall champion, maintaining good coverage of elite targets, and improving relative speedup for general use in molecular design GAs.

show abstract