The focus of this master thesis is to analyze the effectiveness of self-learning and active-learning on biological virtual screening. Virtual screening is used in the pharmaceutical industry to increase the effectiveness of biological screening. Self- learning is a technique where parts of the classified test data are reused for training the classifier again. Active learning gives the classifier the possibility to select certain parts of the test data to use them as additional training data. The experiments in the thesis show that both methods can be used to improve the precision of the virtual screening process, but active-learning is more effective due to the additional information that is provided.