An improved hidden Markov model for transmembrane topology prediction

R.Y. Kahsay, Li Liao, G. Gao
<i title="IEEE Comput. Soc"> <a target="_blank" rel="noopener" href="" style="color: black;">16th IEEE International Conference on Tools with Artificial Intelligence</a> </i> &nbsp;
In this work, we proposed a hidden Markov model for transmembrane protein sequences. The architecture of the model, based on an existing model TMHMM by Sonnhammer et al, contains 7 types of states including helix core, helix caps, loops on both the cytoplasmic side and non-cytoplasmic side, and a globular domain state embedded in the middle of loops. The model differs from TMHMM by how to treat the loops on the both sides, and by use of Dirichlet priors. Using Maximum Likelihood, the model was
more &raquo; ... rained and cross-validated on a set of 160 sequences with known topology. The prediction accuracy for membrane domain location and topology are %89 and %84 respectively, both surpassing significantly these of the best existing model TMHMM (%83 and %77).
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="">doi:10.1109/ictai.2004.30</a> <a target="_blank" rel="external noopener" href="">dblp:conf/ictai/KahsayLG04</a> <a target="_blank" rel="external noopener" href="">fatcat:aw5rmwumo5a6vg34wx26sdpcre</a> </span>
<a target="_blank" rel="noopener" href="" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href=""> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> </button> </a>