Davies, J., Glasgow, J. & Kuo, T. (2007). Protein structure prediction with visuospatial analogy. In T. Barkowsky, M. Klnauff, G. Ligozat, & D. R. Montello (Eds.) Lecture Notes in Artificial Intelligence 4387 Spatial Cognition V: Reasoning, Action, Interaction (LNAI 4387) 127--139.

• using case-based reasoning to predict protein shape

BibTex Entry:

 @InCollection{DaviesGlasgowKuo2007,
  author =      {Davies, Jim and
                          Glasgow, Janice and
                           Kuo, Tony},
   title =       {Protien structure prediction with visuospatial analogy},
   booktitle =   {Lecture Notes in Artificial Intelligence 4387 Spatial Cognition V: Resasoning, Action, Interaction (LNAI 4387)},
   pages =       {127--139},
   publisher =   {Springer},
   year =        {2007},
   editor =      {T. Barkowsky and M. Klnauff and G. Ligozat and D. R. Montello},
   volume =      {4387}
 }

Choose download format: [ PDF (previous version)]

From the Visual Analogy research theme.

Abstract

We show that visio-spatial representations and reasoning techniques
can be used as a similarity metric for analogical protein structure
prediction. Our system retrieves pairs of $\alpha$-helices based on
contact map similarity, then transfers and adapts the structure
information to an unknown helix pair, showing that similar protein
contact maps predict similar 3D protein structure. The success of this
method provides support for the notion that changing representations
can enable similarity metrics in analogy.