Jpred
Jpred v.4 is the latest version of the JPred Protein Secondary Structure Prediction Server which provides predictions based on the Jnet algorithm, one of the most accurate methods for secondary structure prediction, that has existed since initial work by James Cuff starting in 1998 over many different versions.
Jpred predicts the secondary structure of proteins (e.g. Alpha_helix, Coiled_coil and Beta_sheet) by algorithmic first principles, and neural networks from a protein sequence letter code. The techniques used in Jpred v1 are now deployed today in sophisticated software such as AlphaFold.
The Jpred service was initially created, and has continued to be supported in the UK for over 28 years because in 1998, predicting protein secondary structure relied on 100's of strange, obscure and individual unix commands. In 1998, the early World_Wide_Web finally allowed the design of Jpred to perform interactive consensus predictions (now called mixtures of experts) to be easy to access for any researcher in any biological laboratory.
In addition to protein secondary structure, JPred also makes predictions of solvent accessibility and coiled-coil regions. The JPred service runs up to 134 000 jobs per month and has carried out over 2 million predictions in total for users in 179 countries.