|
Introduction MACOED is a multi-objective ant colony optimization algorithm for detecting the genetic interactions. In the MACOED, we combine both the standard logistical regression and the Bayesian network methods, which are from the opposing schools of statistics. The combination of these two evaluation objectives is proved to be complementary to each other resulting in a performance of higher power and lower false positives. To solve the space and time complexity for large dimension problems, a memory-based multi-objective ant colony optimization algorithm is designed in MACOED, which is able to retentive the non-dominated solutions found in the past iterations.
Fig.1. The flow chart of MACOED. Source code and executable file MACOED: C++ version: MACOED_C++.zip Matlab version: MACOED_Matlab.zip Exhaustive multi-objective method: C++ version: Exhau_mop_C++.zip Matlab version: Exhau_mop_Matlab.zip Benchmark datasets DME model: DME model datasets.zip DNME model: DNME model datasets.zip High-resolution figures Fig.3: Single-objective v.s. Multi-objective on DME models Fig.4: Single-objective v.s. Multi-objective on DNME models Fig.5: Performance comparison Contact Pengjie Jing: jingse@sjtu.edu.cn Hongbin Shen: hbshen@sjtu.edu.cn Reference Peng-Jie Jing, Hong-Bin Shen, MACOED: A multi-objective ant colony optimization algorithm for SNP epistasis detection in genome-wide association studies, Bioinformatics, 2014 (in press). |
