In this paper, a three-layer three-output-node back-propagation neural network was applied to analyze the QSAR and QSTR of 23 5,8-disubstituted fluoroquinolones simultaneously. Four descriptors, q N1, q O4, σ m5, and MR 8, were selected from a set of quantum chemical indices and physicochemical parameters using PLS method. The results obtained from neural networks showed that the 4 descriptors were correlated significantly with both the antibacterial activity and cytotoxicity and a multiple QSAR model was built. It provided useful information to develop new selectively potent fluoroquinolones with high activity and low toxicity. Meanwhile, the study demonstrated that the multi-output-node neural network was a powerful tool to analyze multiple QSAR and superior to PLS method.