DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data

In the big data era, the relationship between entries becomes more and more complex. Effective graph (or network) representation learning and mining algorithms pave the way for many applications, such as recommendation, fraud detection, social search, and bioinformation retrieval. Nowadays, many graph (or network) algorithms have already paid attention to dynamic or temporal networks, which are more suitable than static ones for fitting the complex real-world scenarios with evolving patterns of graph topology and node features. To contribute to the network representation learning and network mining research community, we provide a bunch of label-adequate, dynamics-meaningful, and attribute-sufficient dynamic networks from the health domain. To be specific, in our repository DPPIN, we totally have 12 dynamic network datasets at different scales, and each dataset is a dynamic protein-protein interaction network describing protein-level interactions of yeast cells. These domain-specific node features, graph evolution patterns, and node and graph labels could serve as the benchmarks and constraints to help the training and learning manners of graph algorithms. All resources of this work are deployed and publicly available at https://github.com/DongqiFu/DPPIN.