RECENT ADVANCES ON DRUG DISCOVERY FOR ANTI-INFLAMMATORY ACTIVITY DETECTION: SUPERVISED AND UNSUPERVISED ALGORITHM

Determining molecular activity from large and high-complexity drug molecules is a challenging task. Many methods have been tried to solve this difficult problem. However, there is not a comprehensive evaluation that covers the performance test of various molecular descriptors based on supervised and unsupervised methods. In practical application, unlabeled dataset is easier to get than labeled data, however, which cannot be a factor that has great influence on test results. Usually, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are two common traditional supervised algorithms. Sparse AutoEncode (SAE) and Deep Belief Nets (DBN) are two typical unsupervised algorithms. In this paper, the two types of methods were adopted and extensive classification and evaluation strategies were performed to test and verify the IL-1B anti-inflammatory activity. The results reveal no matter what kind of descriptors, the unsupervised algorithm has more precise predictions than the supervised algorithm though the target output is the same. This research contributes to finding the best match algorithm to determine the reliability of drug activity discovery. It not only reduces the cost of research and improves the efficiency of anti-inflammatory drug discovery, but also has a great significance on promoting anti-inflammatory drug design.