Introduction

Query

References

About

References

Our method is based on learning the hierarchical clustering offered by ProtoNet.

The ProtoNet clustering was augmented with solved structures out of PDB, and studied to observe its predictive value.

The metric space of proteins-comparative study of clustering algorithms. (gzipped poscrscript, pdf).
Sasson O, Linial N, Linial M.
Proceedings of ISMB 2002, Bioinformatics. 2002 Jul; 18 Suppl 1:S14-21.

Estimating the probability for a protein to have a new fold: A statistical computational model (pdf or gzipped postscript);
Portugaly E, Linial M
PNAS (2000) 97(10), pp. 5161-5166

Selecting targets for structural determination by navigating in a graph of protein families (pdf);
Portugaly E, Kifer I, Linial M
Bioinformatics (2002) 18(7), pp. 899-907