PseKNC

PseKNC represents DNA and RNA sequences as discrete feature vectors that retain global and long-range sequence order information by integrating oligonucleotide composition with physicochemical properties for computational genomics and genome sequence analysis.

Key Features:

• Sequence Order Information Retention: Maintains global and long-range sequence order information within the pseudo oligonucleotide composition representation.
• Physicochemical Property Integration: Incorporates physicochemical properties of oligonucleotides into the sequence representation to enrich feature information.
• Flexibility and Customization: Allows generation of different PseKNC modes by selecting parameters and specific physicochemical properties.

Scientific Applications:

• Gene prediction: Provides sequence features that can be used to improve gene prediction models.
• Regulatory motif identification: Captures sequence-order and physicochemical signals useful for identifying regulatory motifs.
• Comparative genomics: Supplies enriched sequence representations for comparative analysis across genomes.

Methodology:

Formulation of a sequence representation model that combines discrete oligonucleotide composition with additional sequence-order information derived from physicochemical properties, with the option to generate various PseKNC modes by selecting different parameters and physicochemical properties.