An ensemble identifier developed by fusing the functional domain and sequential evolution information. QuatIdent is a 2-layer predictor. The 1st layer is for identifying a query protein as belonging to which one of the following 10 main quaternary structural attributes ((1) monomer, (2) dimer, (3) trimer, (4) tetramer, (5) pentamer, (6) hexamer, (7) heptamer, (8) octamer, (9) decamer, and (10) dodecamer). If the result thus obtained turns out to be anything but monomer, the process will be automatically continued to further identify it as belonging to a homo-oligomer or heterooligomer. The overall success rate by QuatIdent for the 1st layer identification was 71.1% and that for the 2nd layer ranged from 84 to 96%.
Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, Shanghai, China; Gordon Life Science Institute, San Diego, CA, USA
QuatIdent funding source(s)
This work was supported by the National Natural Science Foundation of China (Grant no. 60704047), the Science and Technology Commission of Shanghai Municipality (Grant no. 08ZR1410600, 08JC1410600), and sponsored by Shanghai Pujiang Program.