The determination of this article is to mature a new protein module detection approach that tries to address the shortcoming of graph-based protein functional module detection algorithms and leverage their biological significance. In our study, we designed a migration strategy that enables proteins to migrate between clusters to finally get grouped with biologically similar proteins. We have strained to progress an enhancement method to help better filter, or precisely reorganize, the outcomes of pre-existing graph-based functional module detection algorithms to be more biologically significant. The Markov Cluster (MCL) detection algorithm technique was adopted as it fits well with the migration principle of the Interactomics based protein network. Also, it is ideal to describe the inherent uncertainty of biological linkages. Besides, spectral clustering was used to get better precision in measuring the distances in the network and to cope with the high-data dimensionality. A study was performed on these techniques to understand their advantages and limitations to define some metrics that take into consideration the biological and topological characteristics of proteins, to adopt the MCL algorithm means and spectral clustering techniques to protein networks context. The statistical tests were positive and with this work, we tried to increase the effects of a widely used graph-based algorithm respectively.

Keywords : Algorithm, Cluster, Interaction, Module, Measurement, Network, Protein, Technique.