Clinical Diagnosis Using Proteomics and Complementary Learning

Proteomics is a promising microbiology technology that will play a critical role in future oncology and drug discovery. The protein expression pattern is useful in clinical diagnosis. However, the protein expression pattern is high-dimensional and hence, renders manual analysis difficult. Thus, computational intelligence method is often applied with proteomic analysis. Unfortunately, the commonly used methods such as statistics and neural network are not interpretable and traceable. Thus, complementary learning fuzzy neural network (CLFNN) is proposed to complement proteomics. Complementary learning is a cognitive mechanism found in the brain where human practices pattern recognition. Positive and negative knowledge are segregated, and decision is made by exploiting the lateral inhibition of positive and negative knowledge. Hence, implementing complementary learning in fuzzy neural network may promise better performance. The experimental results show that the confluence of proteomics and CLFNN is a promising approach towards clinical diagnosis.