Sat Jul 04, 2020 11:59 am


Neural Network with PDB Validation

NNvPDB Help Page

Input Sequence
    The input Sequence Should be in Fasta format.NNvPDB consider non-amino acid letters as unknown.


>sp|P68431|H31_HUMAN Histone H3.1 OS=Homo sapiens GN=HIST1H3A

Query Page
    The input page accepts single protein sequence in fasta format.

Figure 1.Query Page of NNvPDB.

Result Page
    The result page has 3 sections.

Section 1: It contains the description about the input section. The name of the sequence and its length.

Section 2: It contains the secondary structures assigned to the query sequence. H represents Helix, S represents Sheet, C represents Coil and Asterisk (*) represents the unpredicted states.

Section 3: This section contains Validation report in text file format (Figure 3).In this file, user can find the comparison between the predicted secondary states and secondary structures of the similar PDB structures. Asterisk (*) represents match and dot (.) represent mismatch.

      Based on the comparison, validation table will be given in the result page. This table provides the following information: PDB ID, E-value, query coverage, percentage identity, subject start, subject end, query start, query end, length of the query sequence, number of residues predicted in all 3 states, number of residues correctly predicted in all 3 states and Q3 accuracy percentage.

Figure 2.Result Page of NNvPDB showing the secondary structure states and Validation report of the predicted results.

Validation Report in Text File

Figure 3. Comparative view of Predicted states with similar PDB Structures

Mrs. Seethalakshmi Sakthivel
Research Scholar,
Department of Genetic Engineering,
SRM Institute of Science and Technology

Dr. S.K.M Habeeb,
Associate Professor
Department of Genetic Engineering,
SRM Institute of Science and Technology