Sequence analysis Context similarity scoring improves protein sequence alignments in the midnight zone

Motivation: High-quality protein sequence alignments are essential for a number of downstream applications such as template-based protein structure prediction. In addition to the similarity score between sequence profile columns, many current profile–profile alignment tools use extra terms that compare 1D-structural properties such as secondary structure and solvent accessibility, which are predicted from short profile windows around each sequence position. Such scores add non-re-dundant information by evaluating the conservation of local patterns of hydrophobicity and other amino acid properties and thus exploiting correlations between profile columns. Results: Here, instead of predicting and comparing known 1D properties, we follow an agnostic ap-proach. We learn in an unsupervised fashion a set of maximally conserved patterns represented by 13-residue sequence profiles, without the need to know the cause of the conservation of these pat-terns. We use a maximum likelihood approach to train a set of 32 such profiles that can best repre-sent patterns conserved within pairs of remotely homologs, structurally aligned training profiles. We include the new context score into our HMM-HMM alignment tool hhsearch and improve espe-cially the quality of difficult alignments significantly. Conclusion: The context similarity score improves the quality of homology models and other meth-ods that depend on accurate pairwise alignments. Contact