The discovery of synergistic strategies effectively improves the corrosion inhibition capability of amino acids. However, the wide variety of amino acid formulations and the time-consuming nature of corrosion tests make combinatorial discovery challenging to achieve. Herein, a library of 70 amino acids was created and tested in a high-throughput manner. Benefiting from a vast amount of labeled data of amino acid formulations, an interpretable machine learning approach was used to reveal the contribution of molecular features to inhibition performance of amino acids and the synergisms in the optimal formulation. The synergism was verified by electrochemical tests and quantum chemical calculations.