Malonylation modification of proteins is closely related to many diseases, such as diabetes and cancer. This modification needs to be closely examined and accurately identified in order to glean more understanding of the molecular mechanisms driving disease. Whereas traditional routes through which the medical field seeks to investigate this modification suffer from need for significant cycle time and funding, the integration of AI into these experiments allows for a more efficient and potentially more accurate route for research. This paper presents Catsoft_Kmalsite, a malonylation site prediction model, which uses information from AlphaFold2 to analyze 3D protein folding sequence and structure. Catsoft_Kmalsite outperformed other state-of-the-art studies in all evaluated metrics. Across six metrics, including AUC, ACC, Sen, Pre, F1, and MCC, the model achieved average performances of 94.03%, 87.91%, 89.15%, 86.91%, 88.00%, and 0.7585, respectively, in fivefold cross-validation and specific performance of 95.18%, 89.55%, 90.87%, 88.79%, 89.82%, and 0.7912 on the independent test set. Additionally, the researchers have developed a website and a code and data set wherein users can employ Catsoft_Kmalsite.