PredictFold - H3P2
Developed by K. Ganesan and S. Parthasarathy*
Dept. of Bioinformatics, Bharathidasan University, Tiruchirappalli 620 024, India
* For correspondence

The PredictFold H3P2 is a fold recognition server based on a five-dimensional substitution matrix with three dimensions for the homologous structure (H3) and two dimensions for the probe sequence (P2). This method uses residue classes and secondary structure information to predict the structural similarity of the remote homologs which are sequentially distant[1]. Our implementation uses a library of SCOP fold profiles from which a structurally similar profile is predicted for a twilight zone sequence.