A Scalable Genetic Programming Approach to Integrate miRNA-Target Predictions: Comparing Different Parallel Implementations of M3GP

Table 2

Parameters used by M3GP to obtain the results reported in Figure 2.

Parameter	Value
Runs	30
Population size	500 individuals
Generations	100
Initialization	6-depth full initialization with 1 initial dimension
Operator probabilities	Crossover , mutation
Function set	( protected as in [34])
Terminal set	Ephemeral random constants [0,1]
Bloat control	17-depth limit
Selection	Lexicographic tournament of size 5
Elitism	Keep best individual