This thesis aims to study bio-inspired algorithms and to design several bio-optimization algorithms, bio-clustering methods and feature selection using optimization methods. We proposed a new bio-inspired optimization algorithm named Wolf Search Algorithm (WSA). WSA is a new type of swarm intelligence techniques and it is able to find solution to optimization of the continuous functions. In the proposed approach, the search agent is capable of doing global exploration, local exploitation and jump out of local capabilities. Clustering using bio-optimization algorithms is a hybrid method, which is not just only an algorithm. It is a generic method, as we can choose any optimization algorithm and applies it into clustering to optimize clusters centroids. The objective function in our proposed method is the configuration of centroids. The optimization algorithm optimizes the objective function result to return the best centroids to the process of clustering. Then clusters are constructed around these best centroids. Feature selection using optimization algorithms also is a generic method that integrates with optimization algorithms for optimizing the candidate feature sets in order to choose the optimal subset of feature from the whole set. The experimental results show that our proposed algorithms and methods are very competitive when compared to other approaches.