Selection Balancing Quality with Diversity

This study demonstrated how de novo design methods can be used to guide the discovery of high-quality lead compounds in the context of a fest follower project, starting with a known drug. 

There are numerous estimates of the size of available chemical space and while the exact figures do not agree, the consensus is that it is too large to effectively 

The definition of best, as stated above, is a multiobjective problem and the Pareto front provides one method to encapsulate the various optimal solutions. However, the sampling of this front to find a range of solutions is not always assured. Only localized areas of the front might be explored (e.g., by the use of small population sizes in each iteration, which reduces the breadth of solutions that can be followed in subsequent steps [49]) or solutions may be produced that only satisfy the easiest objective in the desirability criteria. The conceptually easiest solution is to include a (dis)similarity value as an input variable against which to optimize in the MPO but again, as noted earlier, there are difficulties in identifying which descriptors to use to define the correct notion of similarity. Other solutions cover ideas such as elitism or niching of compoimds from intermediate rounds of optimization to enhance the diversity of the final set of solutions. 

Recent methods draw on natural mimicry to find best solutions by using swarms of either pseudo-ants or -bees to test a large number of possible alternatives to find the ones that work well. Ant colony methods are useful in other fields such as delivery route optimization (the traveling salesman problem), but in essence the natural systems are individually trying many options in parallel and reporting back to the other members of the colony about the success or otherwise of their attempts. In the natural world, this is encoded by a pheromone trail and in the computational world it is the upweighting of selection parameters [62,63]. 

1 Paul, S., Mytelka, D Dunwiddie, D Persinger, C., Munos, B Lindborg, S., and Schacht, A. (2010) How to improve R D productivity the pharmaceutical industry s grand challenge. Nature Reviews Drug Discovery, 9, 203-214. 

---