banner-button_0 banner-button_Layer-7 banner_button_03 banner-button_Layer-4 banner-button_05 banner-button_Layer-5 banner-button_07
banner-button_08 banner-button_09 banner-button_10
Bioinformatics Unit banner
   tabfoot tabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bgtabfoot-bg

YASPIN secondary structure prediction help


Back to YASPIN

YASPIN is a HNN (Hidden Neural Network) secondary structure prediction program that uses the PSI-BLAST algorithm to produce a PSSM for the input sequence, which it then uses to perform its prediction.

Reference: Lin K., Simossis V.A., Taylor W.R. and Heringa J. (2005) A Simple and Fast Secondary Structure Prediction Algorithm using Hidden Neural Networks. Bioinformatics. 21(2):152-9. (Epub 2004 Sep 17). Abstract

YASPIN performs predictions using the so-called hidden neural network model, which is the combination of a neural network and a hidden Markov model of protein local structures. Unlike most of the concurrent secondary structure prediction methods, YASPIN uses a single-layered neural network to predict 7-state local structure information and then filters that information using a hidden Markov model prior to transforming it into 3-state secondary structure. As a result, the actual secondary structure prediction if faster and has more information to work with.

YASPIN has been trained on 2896 structures from the PDB40 database. The final version has been tested on 727 different structures that were randomly selected prior to the training process. YASPIN's performance was compared to that of PSIPRED (Jones, 1999) and PHD (Rost and Sander, 1993) (on the same test set) with reference to the DSSP and STRIDE reference datasets. Foe more details please refer to the published article (at the moment in preparation).

Yaspin runs blastpgp version 2.2.6 [Apr-09-2003]. Database versions can be downloaded below.

YASPIN Options:

  1. SEQUENCE FORMATS: Yaspin accepts single sequences in the formats dictated by the PSI-BLAST documentation. You can either paste in a sequence in the space provided OR upload a file with your sequence.
  2. UPLOADING PSSMs: This is an optional field. In the event that you have an existing PSSM for your sequence, you can upload it using the space provided. Using the PSSM will redirect the program to analyse your PSSM instead of running PSI-BLAST to generate a new one. This saves a lot of time.
  3. JOB TITLE: This is also optional. In the case of no entry, the job name will be "Untitled".
  4. DATABASES: At the moment we have made NR (non-redundant) and SCOP40 databases available for the PSI-BLAST runs. More Databases will be made available soon. Databases used can be downloaded from the links below:
  5. NEURAL NETS: YASPIN NNs have been separately trained against the DSSP and STRIDE databases. You have the option to select one of the two.
  6. EMAIL: This is a field that you may choose to un-tick if you DO NOT wish to get your results by email. Please note that the results are kept on the server for 15 days max and are erased after that. In order to have a local record of your results you will need to enter the email address you want the results sent to.

(c) IBIVU 2018. If you are experiencing problems with the site, please contact the webmaster.