journal menu
![[Figure 1]](di5002fig1mag.jpg)
|
|
Figure 1
Schematic diagram of the genetic algorithm steps. In this example there are four individuals, with nine sub-data sets to be segregated into three groups. The individuals are first initialized randomly; the nine sub-data sets are assigned randomly to group 1, 2 or 3. Within an individual, three scaling runs in XSCALE are then performed, one for each group. The merging statistics are then converted to fitness scores, and the individual receives the fitness for the highest group (it is also possible to use the average fitness). In this case, individual 4 is removed from the population because of lower fitness (fitness values are not shown) and replaced with a new individual. The DEAP built-in mutation and crossover genetic modifiers are then applied, followed by cycling back to the scoring step. The background colour indicates the source of the chromosome. For example, after the crossover step between individuals 1 and 2, two `new' individuals are created consisting of (i) the group assignments of sub-data sets 1–4 from individual 1 and the group assignments of sub-data sets 5–9 from individual 2 and (ii) the group assignments of sub-data sets 5–9 from individual 1 and the group assignments of sub-data sets 1–4 from individual 2. After crossover, mutations are randomly introduced as shown (yellow circles). |
![[Figure 1]](di5002fig1.jpg)
 | STRUCTURAL BIOLOGY |
ISSN: 2059-7983
access
