@Article{Mann_LatPack_HFSP_08,
  author =	 {Martin Mann and Daniel Maticzka and Rhodri Saunders and Rolf Backofen},
  title =	 {Classifying protein-like sequences in arbitrary lattice protein models using {LatPack}},
  journal =	 {HFSP Journal},
  issn = 	 {1955-2068},
  year =	 {2008},
  volume =   {2},
  number =   {6},
  pages =    {396-404},
  doi = 	 {10.2976/1.3027681},
  note =	 {Special issue on protein folding: experimental and theoretical approaches},
  user =	 {mmann},
  abstract =	{Knowledge of a protein's 3-dimensional native
                structure is vital in determining its chemical properties
                and functionality. However, experimental
                methods to determine structure are very costly and
                time-consuming. Computational approaches, such
                as folding simulations and structure prediction algorithms,
                are quicker and cheaper but lack consistent
                accuracy. This currently restricts extensive computational
                studies to abstract protein models. It
                is thus essential that simplifications induced by the
                models do not negate scientific value. Key to this is
                the use of thoroughly defined protein-like sequences.
                In such cases abstract models can allow for the investigation
                of important biological questions.
                Here we present a procedure to generate and classify
                protein-like sequence data sets. Our LatPack
                tools, and the approach in general, are applicable
                to arbitrary lattice protein models. Identification
                is based on thermodynamic and kinetic features.
                Further LatPack can incorporate the sequential
                assembly of proteins by addressing co-translational
                folding.
                We demonstrate the approach in the widely used,
                unrestricted 3D-cubic HP-model. The resulting sequence
                set is the first large data set for this model
                exhibiting the protein-like properties required. Our
                data and tools are freely available and can be used
                to investigate protein-related problems. Furthermore
                our data sets can serve as the first benchmark
                sequence sets for folding algorithms that have traditionally
                only been tested on random sequences.}
}