Molecular recognition ligands are of great significance in many fields, but our ability to develop new recognition molecules remains to be expanded. Here, we developed a Sequential Multi-dimensional Analysis algoRiThm for aptamer discovery (SMART-Aptamer) from high-throughput sequencing (HTS) data of SELEX libraries based on multi-level structure analysis and unsupervised machine learning to discover nucleic acid recognition ligands with high accuracy and efficiency. We vali-dated SMART-Aptamer with three sets of HTS data from screening pools against hESCs, EpCAM and CSV. High affinity ap-tamers for all three targets were successfully obtained, and the results revealed that SMART-Aptamer is able to pick out high affinity aptamers with low false positive and negative rates. With the advantages of accuracy, efficiency, and robustness, SMART-Aptamer represents a paradigm-shift strategy for the discovery of binding ligands for a variety of biomedical applica-tions.