Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins. In this study, we approach a deep learning technique via convolutional neural network on position specific scoring matrix to identify ATP-binding sites in membrane proteins, which is the most important drug targets. We also addressed the imbalanced dataset issue, which can be seen in most binding site prediction problems. With an MCC of 0.89 and an AUC of 99%, our proposed technique can serve as a powerful tool for biologists to identify ATP-binding sites in membrane proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics. Display omitted •Many life-essential biology mechanisms can be understood by identifying accurately ATP-binding sites in membrane proteins.•Existing predictors can be used to predict ATP-binding membrane proteins but lack of specificity reduces their potential.•The specific and greatly imbalanced dataset issue of ATP-binding sites in membrane proteins was also address.