RESUMO
The purpose of instance selection is to reduce the data size while preserving as much useful information stored in the data as possible and detecting and removing the erroneous and redundant information. In this work, we analyze instance selection in regression tasks and apply the NSGA-II multi-objective evolutionary algorithm to direct the search for the optimal subset of the training dataset and the k-NN algorithm for evaluating the solutions during the selection process. A key advantage of the method is obtaining a pool of solutions situated on the Pareto front, where each of them is the best for certain RMSE-compression balance. We discuss different parameters of the process and their influence on the results and put special efforts to reducing the computational complexity of our approach. The experimental evaluation proves that the proposed method achieves good performance in terms of minimization of prediction error and minimization of dataset size.
RESUMO
The NADPH oxidase enzyme complex, NOX2, is responsible for reactive oxygen species production in neutrophils and has been recognized as a key mediator of inflammation. Here, we have performed rational design and in silico screen to identify a small molecule inhibitor, Phox-I1, targeting the interactive site of p67(phox) with Rac GTPase, which is a necessary step of the signaling leading to NOX2 activation. Phox-I1 binds to p67(phox) with a submicromolar affinity and abrogates Rac1 binding and is effective in inhibiting NOX2-mediated superoxide production dose-dependently in human and murine neutrophils without detectable toxicity. Medicinal chemistry characterizations have yielded promising analogs and initial information of the structure-activity relationship of Phox-I1. Our studies suggest the potential utility of Phox-I class inhibitors in NOX2 oxidase inhibition and present an application of rational targeting of a small GTPase-effector interface.