(ii) FUS2: 2 x AAS(AC) + 2 x PSSM(SAN) + 4 x PSSM(PP) + PSSM(LHF.G) + PSSM(BGR) + PSSM(TGR) + SMR(PP) + SMR(BGR) + 2 x DM(LPQ_G) = FUS1 + 2 x DM(LPQ_G).
The most interesting result among those reported in Tables 7 and 8 is that of our ensemble FUS1, which outperforms the other approaches in nearly all the datasets and accomplishes this performance gain without changing its weights.
The forth experiment is aimed at comparing our ensembles FUS1 and FUS2 with the performance reported in the literature by other state-of-the-art approaches.
Please note that our ensemble FUS1 works well across nearly all the tested datasets, without any parameter tuning to optimize performance for a given dataset.
Considering the dataset PF, which is one of the most widely used benchmarks, FUS1 compares very well with the other approaches where features are not extracted using 3D information (for a fair comparison).
Since the PF dataset aims at predicting the 3D structure of a protein, features extracted from 3D representations are highly useful as proven by the better performance obtained by FUS2 with respect to FUS1.
Given the results reported above, our proposed ensemble FUS1 should prove useful for practitioners and experts alike since it can form the base for building systems that are optimized for particular problems (e.g., SVM optimization and physicochemical properties selection).
Fus1 was identified by the International Lung Cancer Chromosome 3p21.3 Tumor Suppressor Gene Consortium, a team of researchers from M.
Fus1 and the other nine genes are located in a region of chromosome 3 called 3p (the short arm of chromosome 3).
Restoration of a gene such as fus1 might restore this gatekeeper function.