Atomic force microscopy-single-molecule force spectroscopy (AFM-SMFS) is a powerful methodology to probe intermolecular and intramolecular interactions in biological systems because of its operability in physiological conditions, facile and rapid sample preparation, versatile molecular manipulation, and combined functionality with high-resolution imaging. Since a huge number of AFM-SMFS force-distance curves are collected to avoid human bias and errors and to save time, numerous algorithms have been developed to analyze the AFM-SMFS curves. Nevertheless, there is still a need to develop new algorithms for the analysis of AFM-SMFS data since the current algorithms cannot specify an unbinding force to a corresponding/each binding site due to the lack of networking functionality to model the relationship between the unbinding forces. To address this challenge, herein, we develop an unsupervised method, i.e., a network-based automatic clustering algorithm (NASA), to decode the details of specific molecules, e.g., the unbinding force of each binding site, given the input of AFM-SMFS curves. Using the interaction of heparan sulfate (HS)-antithrombin (AT) on different endothelial cell surfaces as a model system, we demonstrate that NASA is able to automatically detect the peak and calculate the unbinding force. More importantly, NASA successfully identifies three unbinding force clusters, which could belong to three different binding sites, for both Ext1f/f and Ndst1f/f cell lines. NASA has great potential to be applied either readily or slightly modified to other AFM-based SMFS measurements that result in "saw-tooth"-shaped force-distance curves showing jumps related to the force unbinding, such as antibody-antigen interaction and DNA-protein interaction.