HHsenser: exhaustive transitive profile search using HMM-HMM comparison

Abstract

HHsenser is the first server to offer exhaustive intermediate profile searches, which it combines with pairwise comparison of hidden Markov models. Starting from a single protein sequence or a multiple alignment, it can iteratively explore whole superfamilies, producing few or no false positives. The output is a multiple alignment of all detected homologs. HHsenser's sensitivity should make it a useful tool for evolutionary studies. It may also aid applications that rely on diverse multiple sequence alignments as input, such as homology-based structure and function prediction, or the determination of functional residues by conservation scoring and functional subtyping.HHsenser can be accessed at http://hhsenser.tuebingen.mpg.de/. It has also been integrated into our structure and function prediction server HHpred (http://hhpred.tuebingen.mpg.de/) to improve predictions for near-singleton sequences.

Figure 1

Simplified flow chart (left) and schematic diagram of HHsenser (right). The red X in the diagram is the query sequence, the other, smaller X's represent seed sequences from which new alignments are built (shaded disks). The large circles indicate the space from which new seeds are selected (arrows). The large search radius (E < 1) together with sensitive HMM–HMM comparison allows to jump wide gaps between related families (green arrow).

Figure 2

Sample output of HHsenser showing a part of the stringent alignment of lytic transglycosilases obtained with protein P5 from bacteriophage phi-6 as starting sequence. The overlaid window shows a JalView applet (30). Tabs allow to switch to the stringent alignment, the permissive alignment, the sequences rejected in the course of the transitive search and the various intermediate aligments accepted as homologs. Files can be downloaded via links, either with or without inserts relative to the query sequence.