The aim of BetaTPred2 server is to predict beta turns in proteins by neural network from the given amino acid sequence. It uses two feed-forward neural networks where the learning algorithm is standard backpropagation. The first sequence-to-structure network is learned on the PSI-BLAST generated scoring matrices or multiple alignment profiles. The second structure-to-structure network uses the predicted turns/nonturns output from first network along with secondary structure predicted by PSIPRED.
The input is a single letter-code amino acid sequence either in fasta or free format. The residues in the query sequence predicted as turns are marked as 't' and non-turn residues are marked as 'n'. The PSIPRED predicted secondary structure is displayed along with the predicted turn/non-turn results.