Aminoglycoside Acetyltransferase Dataset

Data collection is the most crucial task that forms the foundation of a robust and worthwhile computational model. The dataset used to develop the proposed model has been meticulously gathered from UniProt. UniProt is a generalized database of protein sequences and their functional information. In the wake of applying a query in Uniport database, only reviewed sequences are collected for both Acetyltransferase (positive) and non-acetyltransferase (negative). Subsequently, the positive samples were meticulously extracted, resulting in a compilation of 6266 reviewed sequences. Simultaneously, a dataset comprising 4998 reviewed samples classified as negative sequences was collected. Altogether, 11264 samples encompassing both negative and positive sequences were amassed.