First, a fixed-dimensional feature vector is generated for each protein sequence using the frequency of the hydropathy blocks occurring in the sequence. 首先，利用蛋白質序列中親水模塊的出現頻率，每條蛋白質序列被轉換為一個特徵向量。
It outperforms much better than the other two in that it calculates and maximizes the feature vector distance between multi-modal clusters in a hyper-sphere space. 該方法能計算並最大化高維空間中的多模式聚集特徵向量距離，由於具有滿足三角不等式和非奇性的特性，相對於其他兩種方法，它提高了檢測性能。
