With the proliferation of Web Services, scientific applications are more and more designed as temporal composition of services, commonly referred to as, workflows. To address this paradigm shift, different workflow management systems have been proposed. If their efficiency has been established over centralized reliable systems, it is questionable over highly decentralized failure-prone platforms. Scientific applications started to be deployed over emerging clouds, leading to new issues, like elasticity, i.e., the possibility to dynamically refine at runtime the amount of resources dedicated to an application. This raised a new demand for programming models, able to express autonomic self-coordination of services in a dynamic, elastic platform. Chemistry-inspired computing recently regained momentum in this context, naturally expressing parallelism, distribution, and autonomic behaviors. While its high expressiveness and adequacy for this context has been established, the chemical model severely suffers from a lack of proof of concepts. In this paper, we concretely show how to leverage such models in this context. We focus on the design, the implementation and the experimental validation of a chemistry-inspired scientific workflow management system.