Multi-agent systems in epidemiology: a first step for computational biology in the study of vector-borne disease transmission

Abstract

Background: Computational biology is often associated with genetic or genomic studies only. However, thanks to the increase of computational resources, computational models are appreciated as useful tools in many other scientific fields. Such modeling systems are particularly relevant for the study of complex systems, like the epidemiology of emerging infectious diseases. So far, mathematical models remain the main tool for the epidemiological and ecological analysis of infectious diseases, with SIR models could be seen as an implicit standard in epidemiology. Unfortunately, these models are based on differential equations and, therefore, can become very rapidly unmanageable due to the too many parameters which need to be taken into consideration. For instance, in the case of zoonotic and vector-borne diseases in wildlife many different potential host species could be involved in the life-cycle of disease transmission, and SIR models might not be the most suitable tool to truly capture the overall disease circulation within that environment. This limitation underlines the necessity to develop a standard spatial model that can cope with the transmission of disease in realistic ecosystems.

Results: Computational biology may prove to be flexible enough to take into account the natural complexity observed in both natural and man-made ecosystems. In this paper, we propose a new computational model to study the transmission of infectious diseases in a spatially explicit context. We developed a multi-agent system model for vector-borne disease transmission in a realistic spatial environment.

Conclusion: Here we describe in detail the general behavior of this model that we hope will become a standard reference for the study of vector-borne disease transmission in wildlife. To conclude, we show how this simple model could be easily adapted and modified to be used as a common framework for further research developments in this field.

Figure 1

Static UML modeling of our model. The "Model Swarm" class, which contains the representation of the virtual world where the pathogen agent circulates, contains links to all "Host" objects. The "Host" object can contain, or not, one "Parasite" object if Host is infected, infectious or has been infected. All attributes and functions are detailed in the main text.

Figure 2

Distributed behavior of our model. Each function acting on the virtual world or on scheduling is in the "Model Swarm" class. These are virtual functions and each behavior is implemented in one of the inheriting classes. "Model Swarm Alone" contains the same functions as the "Model Swarm" class and is applied in a stand-alone use. "Model Swarm Client" and "Model Swarm Sever" are called in the case of parallelization. On the server side, a thread is created for each client and communication is done via an established communication protocol (See Additional file 1, section 4). On the client side, each client can focus on a given number of "Host" objects and a thread is created to communicate with the Server component.