Using default value of the parameters, EpiSearch method predicted two top scoring patches centered on residues M214 (Score: 0.813) and R100 (Score: 0.805).
Both of GTG1 and GTG2 (including all four predicted splicing alternatives) were not included in this list since either or both TM-prediction methods predicted eight or nine TM-regions in GTG1 and GTG2 (one splice form of GTG2 has only five TM-regions).
Interestingly, the P method performs similarly to the L method by predicting six new candidates (although only two are common with those predicted by L), while A, S and C methods predict two, two and three additional members, respectively.
However, no single TM-prediction method predicts exactly seven TM-regions from all known 7TMRs.
For example, in the case of Trastuzumab peptides, the method correctly predicts six residues using a 10Å patch size and three residues using a patch size of 8Å compared to nine residues using a patch size of 12Å.
Similarly, in the case of mAb Bo2C11, the method correctly predicts five residues using a patch size of 10Å compared to seven residues using a patch size of 12Å.
Our method predicts correctly two out of the four hot spots - M150A and F205A, and all of the three non-hot spots.
Tested on the Mars-500 database, the proposed method predicts the six basic emotions with over 75% accuracy.
In addition, the Miso(2,6) method predicts only one other candidate module, with the noteworthy property that 4 out of the 5 genes are known to be involved in DNA repair.
Moreover, the Bayesian method predicted just two of the three facies where Neuro-Bayesian method predicted all the three facies successfully.
