Name of the protein sequence:
This is an optional field. User may or may not enter the name of the sequence.

Input sequence:
Sequence can be submitted by two ways. User can paste the sequence directly into the inbox field provided or upload the file by using the "BROWSE" option.Sequences must be entered in the one-letter code. All the non standard characters will be ignored from the sequence.

Sequence format:
TBpred can accept only FASTA format protein sequence. It uses ReadSeq routine to parse the input. The user should check the format of the input sequence before submitting the prediction. The results of the prediction will be wrong if the format choosen is wrong.

Prediction Approach:
Three different types of prediction strategies have been developed for predicting the proteins to 4 different subcellular localizations.

• Amino acid composition:
  There are altogether 20 types of amino acids in a protein.The fraction of those amino acids have been calculated for a protein sequence and thus SVM model is generated for 4 different subcellular localizations based upon 20 dimensional input vector.
• Dipeptide composition:
  Protein's local order amino acid composition (dipeptide composition) is also exploited to train SVM.For each protein sequence SVM detects input vector of 400 dimensions.
• Position Specific Scoring Matrix(PSSM):
  A PSSM, or Position-Specific Scoring Matrix is a type of scoring matrix in which amino acid substitution scores are assigned separately for each position in a protein sequence.From this PSSM a SVM pattern is generated in which each protein sequence is represented by 400 values.The SVM is trained with input vectors of 400 dimensions for each protein.

Output:
The output shows the input data as submitted by the user along with the prediction results. It gives the name ( if provided), length of the sequence and prediction approach as used by the users. In addition to this different scores generated for all the four types of locations are also given.