This server offers a neural network that classifies strand-loop-strand motifs into local hairpins and non local diverging turns utilizing the amino acid sequence as input. The neural network is trained with a representative subset of the Protein Data Bank and achieves a prediction accuracy of 75.9+/-4.4%. Hairpins are predicted with an accuracy of 77.3+/-6.1%, diverging turns with an accuracy of 74.0+/-6.0%.

Files are limited to 4MB in size; if you are a Meiler-Lab member, please login to upload files up to 16MB