Characterization and sequence prediction of structural variations in alpha-helix

摘要

Background: The structure conservation in various alpha-helix subclasses reveals the sequence and context dependent factors causing distortions in the alpha-helix. The sequence-structure relationship in these subclasses can be used to predict structural variations in alpha-helix purely based on its sequence. We train support vector machine(SVM) with dot product kernel function to discriminate between regular alpha-helix and non-regular alpha-helices purely based on the sequences, which are represented with various overall and position specific propensities of amino acids. Results: We characterize the structural distortions in five alpha-helix subclasses. The sequence structure correlation in the subclasses reveals that the increased propensity of proline, histidine, serine, aspartic acid and aromatic amino acids are responsible for the distortions in regular alpha-helix. The N-terminus of regular alpha-helix prefers neutral and acidic polar amino acids, while the C-terminus prefers basic polar amino acid. Proline is preferred in the first turn of regular alpha-helix , while it is preferred to produce kinked and curved subclasses. The SVM discriminates between regular alpha-helix and the rest with precision of 80.97% and recall of 88.05%. Conclusio