ProALIGN Directly learning alignments for protein structure prediction via exploiting context-specifice alignment motifs

we report a novel deep learning approach ProALIGN that can predict much more ac-curate sequence-template alignment. Like protein sequences consisting of sequence motifs, protein alignments are also composed of frequently-occurring alignment motifs with charac-teristic patterns. Alignment motifs are context-specific as their characteristic patterns are tightly related to sequence contexts of the aligned regions. Inspired by this observation, we represent a protein alignment as a binary matrix (in which 1 denotes an aligned residue pair) and then use a deep convolutional neural network to predict the optimal alignment from the query protein and its template. The trained neural network implicitly but effectively encodes an alignment scoring function, which reduces inaccuracies in the handcrafted scoring func-tions widely used by the current threading approaches. For a query protein and a template, we apply the neural network to directly infer likelihoods of all possible residue pairs in their entirety, which could effectively consider the correlations among multiple residues. We further construct the alignment with maximum likelihood, and finally build structure model accord-ing to the alignment.