Application of Improved Three-Dimensional Kernel Approach to Prediction of Protein Structural Class

<table>The mapping <svg height="11.3125" id="M14" style="vertical-align:-0.0pt" version="1.1" viewbox="0 0 12.9375 11.3125" width="12.9375" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,11.25)"><path d="M488 658v-28q-47 -3 -58.5 -12t-11.5 -39q49 -2 97 -15t93.5 -39.5t73.5 -75t28 -112.5q0 -53 -19.5 -96.5t-50 -71t-70 -47t-77.5 -27.5t-75 -9q0 -36 11.5 -45.5t58.5 -12.5v-28h-223v28q47 3 58.5 12.5t11.5 45.5q-47 1 -94.5 14t-93 39.5t-74.5 76t-29 114.5
q0 51 19 93.5t49 70t69.5 47t77.5 28t76 10.5q0 30 -11 39t-54 12v28h218zM335 118v429q-34 -2 -67 -13.5t-63.5 -35t-49.5 -65.5t-19 -96q0 -56 18.5 -99t49 -67.5t63.5 -37.5t68 -15zM418 547v-429q35 2 67.5 14t63.5 35.5t50 66.5t19 99t-19 99t-50 66.5t-64 35t-67 13.5
z" id="x3A6"></path></g>
</svg> embeds the data points in a feature space.</table>

BioMed Research International

fig2

Figure 2

Figure 2: Application of Improved Three-Dimensional Kernel Approach to Prediction of Protein Structural Class 