PSIPRED

PSIPRED
Original author(s)
  • David T. Jones
  • Daniel Buchan
  • Tim Nugent
  • Federico Minneci
  • Kevin Bryson
Initial release 1999
Development status Online
Available in English
Type Bioinformatics (secondary structure prediction)
Alexa rank Decrease 10,588 (October 2014)[1]
Website bioinf.cs.ucl.ac.uk/psipred/
As of 7 May 2014

PSIPRED (Psi-blast based secondary structure prediction) is a technique used to investigate protein structure. PSIPRED employs neural network, machine learning methods in its algorithm.[2][3][4] It is a server-side program, featuring a website serving as a front-end interface, which can predict a protein's secondary structure (beta sheets, alpha helices and coils) from the primary sequence.

Secondary structure

Secondary structure is the general three-dimensional form of local segments of biopolymers such as proteins and nucleic acids (DNA/RNA). It does not, however, describe specific atomic positions in three-dimensional space, which are considered to be the tertiary structure. Secondary structure can be formally defined by the hydrogen bonds of the biopolymer, as observed in an atomic-resolution structure. In proteins, the secondary structure is defined by the patterns of hydrogen bond between backbone amino and carboxyl groups. Conversely, for nucleic acids, the secondary structure consists of the hydrogen bonding between the nitrogenous bases. The hydrogen bonding patterns may be significantly distorted, which makes an automatic determination of secondary structure difficult. Efforts to use computers in predicting the secondary structures of proteins based only on their given primary structure sequences have been ongoing since the 1970s.[5]

Secondary structure prediction involves a set of techniques in bioinformatics that aim to predict the local secondary structures of proteins and RNA sequences based only on knowledge of their primary structure — amino acid or nucleotide sequence, respectively. For proteins, a prediction consists of assigning regions of the amino acid sequence as highly probable alpha helices, beta strands (often noted as "extended" conformations), or turns. The success of a prediction is determined by comparing it to the results of the DSSP algorithm applied to the crystal structure of the protein; for nucleic acids, it may be determined from the hydrogen bonding pattern. Specialized algorithms have been developed for the detection of specific well-defined patterns such as trans-membrane helices and coiled coils in proteins, or canonical micro-RNA structures in RNA.

Basic information

The idea of this method is to use the information of the evolutionarily related proteins to predict the secondary structure of a new amino acid sequence. PSIBLAST is used to find related sequences and to build a position-specific scoring matrix. This matrix is processed by a neural network,[3][6] which was constructed and trained to predict the secondary structure of the input sequence;[7] in short, it is a machine learning method.[8]

Prediction algorithm (method)

The prediction method or algorithm is split into three stages: Generation of a sequence profile, Prediction of initial secondary structure, and Filtering of the predicted structure.[9] PSIPRED works to normalize the sequence profile generated by PSIBLAST.[3] Then, by using neural networking, initial secondary structure is predicted. For each amino acid in the sequence the neural network is fed with a window of 15 acids. There is additional information attached, indicating if the window spans the N or C terminus of the chain. This results in a final input layer of 315 input units, divided into 15 groups of 21 units. The network has a single hidden layer of 75 units and 3 output nodes (one for each secondary structure element: helix, sheet, coil).[6]

A second neural network is used for filtering the predicted structure of the first network. This network is also fed with a window of 15 positions. The indicator on the possible position of the window at a chain terminus is also forwarded. This results in 60 input units, divided into 15 groups of four. The network has a single hidden layer of 60 units and results in three output nodes (one for each secondary structure element: helix, sheet, coil).[9]

The three final output nodes deliver a score for each secondary structure element for the central position of the window. Using the secondary structure with the highest score, PSIPRED generates the protein prediction.[9] The Q3 value is the fraction of residues predicted correctly in the secondary structure states, namely helix, strand and coil.[9]

See also

References

  1. ↑ "ucl.ac.uk Site Overview". Alexa Internet. Retrieved 8 October 2014.
  2. ↑ Gajendra P. S. Raghava; Harpreet Kaur. "Prediction of beta turn types". Retrieved 5 May 2014.
  3. 1 2 3 Yi-Ping Phoebe Chen (18 January 2005). Bioinformatics Technologies. Springer. p. 107. ISBN 978-3-540-20873-0.
  4. ↑ Cuff, James A.; Barton, Geoffrey A. (15 August 2000). "Application of multiple sequence alignment profiles to improve protein secondary structure prediction.". Proteins (John Wiley & Sons) 40 (3): 502–11. doi:10.1002/1097-0134(20000815)40:3<502::aid-prot170>3.0.co;2-q. PMID 10861942.
  5. ↑ Heringa, Jaap (2000). "Computational Methods for Protein Secondary Structure Prediction Using Multiple Sequence Alignments". Current Protein & Peptide Science (Bentham Science Publishers.) 1 (3): 273–301(29). doi:10.2174/1389203003381324.
  6. 1 2 S. C. Rastogi; Namitra Mendiratta; Parag Rastogi (22 May 2013). Bioinformatics: Methods and Applications: (Genomics, Proteomics and Drug Discovery). PHI Learning Pvt. Ltd. pp. 302–. ISBN 978-81-203-4785-4.
  7. ↑ "PSIPRED | Bioinformatic Technology". 10 April 2014. Retrieved 7 May 2014.
  8. ↑ "PSIPRED overview". Retrieved 7 May 2014.
  9. 1 2 3 4 Jones, David T. (17 September 1999). "Protein Secondary Structure Prediction Based on Position-specific Scoring Matrices" (PDF). Journal of Molecular Biology (Elsevier) 292: 195–202. doi:10.1006/jmbi.1999.3091. PMID 10493868. Retrieved 7 May 2014.
This article is issued from Wikipedia - version of the Friday, October 23, 2015. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.