Su Yansen is a professor and Ph.D. supervisor at Anhui University, a recipient of the National Excellent Young Scientists Fund. Her research focuses on intelligent computing and bioinformatics. She serves as the Deputy Secretary-General of the Bio-computing and Bio-information Processing Professional Committee of the China Electronics Society, and as a member of the Bioinformatics Professional Committee of the China Computer Federation. She is also a member of the Youth Editorial Board of INSC, a journal in the second quartile of SCI, and chaired the Program Committeee of the Third International Conference on Biomedical Data Mining and Computational Biology. In the past five years, she has published over 50 SCI-indexed papers in mainstream journals related to intelligent computing and bioinformatics, and has been granted 5 national patents. She has hosted one national key research and development program project and 2 National Natural Science Foundation of China (NSFC) grants.
Multi-objective optimization methods and applications on bioinformatics
Multi-objective optimization problems (MOPs) widely exist in biological areas, which contain two or more objectives to be optimized simultaneously. In the absence of a single solution making all the objectives optimal, there exist multiple Pareto optimal solutions for an MOP, which make diverse trade-offs between the conflicting objectives. Since multiple optimal solutions rather than a single one need to be provided, solving MOPs is much more difficult than solving single-objective optimization problems. Besides, there are many biological MOPs containing constraints. More seriously, with the curse of dimensionality for several biological optimization problems, it is extremely difficult for conventional MOEAs to find multiple optimal solutions for large-scale MOPs. To address these problems, we propose a algorithm to balance the objective optimization and constraint satisfaction during the evolutionary process. We also propose a comprehensive performance indicator for studying the performance of state-of-the-art MOEAs on large-scale sparse biological MOPs. In addition, we have applied these methods to deal with biological problems, such as the molecular signature identification, the disease module identification, and the molecules optimization.
