TANGLE (Torsion ANGLE) predictor works by integrating multiple local sequence profiles in combination with global sequence features within a two-level SVR learning framework. Input features include evolutionary profiles in the form of position-specific scoring matrices (PSSMs), predicted secondary structure, solvent accessibility and native disorder information. Moreover, other global sequence information such as sequence length and sequence weight were also used as input to TANGLE.
- Web Browser
:: MORE INFORMATION
PLoS One. 2012;7(2):e30361. doi: 10.1371/journal.pone.0030361.
TANGLE: two-level support vector regression approach for protein backbone torsion angle prediction from primary sequences.
Song J, Tan H, Wang M, Webb GI, Akutsu T.