Fig. 3From: Bayesian optimization with evolutionary and structure-based regularization for directed protein evolutionML-assisted directed evolution techniques identify high fitness GB1 variants more frequently than simulated traditional DE approaches. Shown are the fraction of trials (y-axis) that reach less than or equal to a specified fitness (x-axis), where the selection criterion was either a simulated traditional DE approach, or standard or regularized EI, PI, and UCB was the acquisition function. (Left) Expected Improvement: The cumulative-weighted average fitness values are 7.25 for GPÂ +Â EIÂ +Â TPLM, 7.24 for GPÂ +Â EI, and 7.16 for GPÂ +Â EIÂ +Â FoldX. (Middle) Probability of improvement: The cumulative-weighted average fitness values are 7.62 for GPÂ +Â PIÂ +Â TPLM, 7.17 for GPÂ +Â PI, and 7.03 for GPÂ +Â PIÂ +Â FoldX. (Right) Upper confidence bound: The cumulative-weighted average fitness values are 7.76 for GPÂ +Â UCBÂ +Â TPLM, 7.10 for GPÂ +Â UCB, and 6.38 for GPÂ +Â UCBÂ +Â FoldX. (All): The traditional single step and recombination approaches select variants with cumulative-weighted average fitness values of 5.22 and 4.71, respectivelyBack to article page