SummarySystems-scale analysis of multiple layers of molecular and cellular data has significant potential for providing novel insights into malaria pathology and immunity. We present here a unique longitudinal multi-omics dataset encompassing Macaca mulatta blood and bone marrow responses to infection by Plasmodium cynomolgi, a non-human primate (NHP) parasite species used to model P. vivax malaria acute and relapsing infections in humans. We analyzed relationships across multiple biological layers using a mutual information-based machine learning approach to integrate heterogeneous longitudinal datasets and constructed an atlas of multi-omics relatedness networks (MORNs). Using this technique, we were able to detect signatures that defined both acute and relapsing infections. Importantly, relapse infections could be distinguished from both acutely-infected and uninfected NHP, suggesting that the host-parasite interactions during relapses are unique compared to acute Plasmodium infections. To our knowledge, this is the first report of large-scale, longitudinal multi-omics analysis of malaria in any system. This dataset, along with the method used to analyze it, provides a unique resource for the malaria research community and demonstrates the power of longitudinal infection study designs, NHP model systems and integrative multi-omics analyses.