Protein-DNA complex formation is an integral component of transcriptional and translational pathways. Exact identification of mutual recognition sites on the protein and DNA becomes absolutely imperative both for a stable and specific complex formation. In the absence of a known structure of a protein-DNA complex mutual recognition sites cannot be determined and hence methods to predict them are required.
SDCPred is an attempt to predict such mutual recognition sites and hence help in the better understanding of these intricate and vital processes.
SDCPred predicts specific DNA-binding sites between the residue environments of proteins and a mononucleotide or dinucleotide step in DNA. The input is an amino acid sequence in the FASTA format and the output is a set of scores for each amino acid residue, implying the probability of that residue binding to a particular mononucleotide or a dinucleotide step in DNA.
The predictions are based on the parameters trained on a non-redundant dataset of 159 protein chains using a five-residue window encoded by PSSM rows of that protein. Apart from contact prediction scores for all four mononucleotides and 10 dinucleotide steps, the web server also returns multiple alignments used for generating the PSSM based predictionThis web server predicts the mononucleotide and dinucleotide base step contacts in protein using evolutionary information in the form of PSSM using Neural Networks. The input is an amino acid sequence in the fasta format.