@Article{Waldispuhl_ODonnell_Will-Simul_Align_and-JCB2014, author = {Waldispuhl, Jerome and O'Donnell, Charles W. and Will, Sebastian and Devadas, Srinivas and Backofen, Rolf and Berger, Bonnie}, title = {Simultaneous {Alignment} and {Folding} of {Protein} {Sequences}}, journal = JCB, year = {2014}, volume = {21}, number = {7}, pages = {477-491}, user = {backofen}, pmid = {24766258}, doi = {10.1089/cmb.2013.0163}, issn = {1066-5277}, issn = {1557-8666}, abstract = {Abstract Accurate comparative analysis tools for low-homology proteins remains a difficult challenge in computational biology, especially sequence alignment and consensus folding problems. We present partiFold-Align, the first algorithm for simultaneous alignment and consensus folding of unaligned protein sequences; the algorithm's complexity is polynomial in time and space. Algorithmically, partiFold-Align exploits sparsity in the set of super-secondary structure pairings and alignment candidates to achieve an effectively cubic running time for simultaneous pairwise alignment and folding. We demonstrate the efficacy of these techniques on transmembrane beta-barrel proteins, an important yet difficult class of proteins with few known three-dimensional structures. Testing against structurally derived sequence alignments, partiFold-Align significantly outperforms state-of-the-art pairwise and multiple sequence alignment tools in the most difficult low-sequence homology case. It also improves secondary structure prediction where current approaches fail. Importantly, partiFold-Align requires no prior training. These general techniques are widely applicable to many more protein families (partiFold-Align is available at http://partifold.csail.mit.edu/ ).} }