PseAAC

PseAAC converts protein sequences into numeric vectors that encode amino acid composition together with sequence-order information for input to pattern-recognition algorithms in computational proteomics.

Key Features:

• Sequence-order encoding: Retains sequence-order information within the pseudo amino acid composition representation.
• Multiple PseAAC variants: Provides various kinds of pseudo amino acid compositions to accommodate different representation choices.
• Numeric vector output: Produces numeric vectors suitable for input to pattern-recognition algorithms.
• Extension of amino acid composition: Extends conventional amino acid composition models by incorporating sequence-order information for a more nuanced protein representation.

Scientific Applications:

• Protein function annotation: Enhances prediction and annotation of protein function by supplying richer sequence representations.
• Structure prediction: Aids protein structure prediction by enriching sequence-derived feature sets.
• Interaction studies: Supports interaction studies by improving feature representation for interaction-related predictions.
• Computational proteomics: Applicable across branches of computational proteomics to improve predictive quality for various protein attributes.

Methodology:

Convert a protein sequence into a digital vector that encodes amino acid composition and sequence-order information (pseudo amino acid composition) for use by pattern-recognition algorithms.