Protein Function Prediction Based on the Neural Response Algorithm


NRProF a novel automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. The main idea of this algorithm is to define a distance metric that corresponds to the similarity of the subsequences and reflects how the human brain can distinguish between different sequences. We predicted the most similar target protein for a given query protein using the two layered neural response algorithm and thereby assigned the GO term associated with the target sequence to the query sequence. Our method predicted and ranked the actual GO term in the first position out of five with an accuracy of 82%. Results of the 5-fold cross validation and the comparison with PFP server indicate the better performance by our method.

The core algorithm is implemented in R.


Please find the NRProF related files and source code from here .


We thank Prof. Steve Smale of City University of Hong Kong for valuable discussion and members of Wang lab at the University of Hong Kong for their critical comments.

Funding: The research was supported by General Research Fund (778609M to JW) and NSFC/RGC fund (N_HKU752/10 to JW) from the Research Grants Council of Hong Kong.


*Correspondence should be addressed to Junwen Wang (Email: ).


NRProF: Neural Response Based Protein Function Prediction Algorithm.
Hari Krishna Yalamanchili, Quan-Wu Xiao, and Junwen Wang . ISB.