Large scale experiments in the field of scientific computing, particularly in bioinformatics, typically require both processing of huge amounts of data and significant computing power. High performance computing (HPC) architectures, in particular cloud computing environments, may help meet these requirements by enabling fast, large-scale, and costeffective parallel job execution. However, for that to happen, we need efficient scheduling algorithms to distribute tasks to available resources in a uniform way. In this paper we propose an agent-based framework that allows modeling, implementing, deploying, and configuring parallel execution of bioinformatics experiments in the cloud. To demonstrate the feasibility of our approach, we implemented an instance of the proposed framework on the AWS platform. Experimental results show performance gains, scalability, and indicate that the proposed framework may be an efficient alternative for running parallel bioinformatics applications in the cloud. Copyright 2012 ACM.