Topology prediction for helical transmembrane proteins at 86% accuracy–Topology prediction at 86% accuracy

By Burkhard Rost, Piero Fariselli, Rita Casadio. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Support vector machine approach for protein subcellular localization prediction (2001, unknown): “No transmembrane proteins were included as they could be quite reliably predicted by some known methods (Rost et al. , 1996; Hirokawa et al. , 1998; Lio and Vannucci, 2000).”
Prediction of contact maps with neural networks and correlated mutations. (2001, methodology): “It has been previously shown that neural networks are efficient tools in solving several kinds of problems, including predictions of secondary structures (Rost and Sander, 1995; Jones, 1999), transmembrane helices (Rost et al., 1996) and folding initiation sites (Compiani et al., 1998).”
The PredictProtein server (2003, background): “NORSp Floppy regions J. Liu and B. Rost (19,20) Protein structure PHDsec Secondary structure B. Rost (11,49,50) PHDacc Solvent accessibility B. Rost (11,51) PHDhtm Membrane helices B. Rost (11,52, 53 ) PROFsec Secondary structure B. Rost (12) PROFacc Solvent accessibility B. Rost Unpublished GLOBE G”
Best α‐helical transmembrane protein topology predictions are achieved using hidden Markov models and evolutionary information (2004, methodology): “1 (Rost et al. 1996) is the single sequence version of PHD, PHD_htm2.”
Artificial neural networks for computer-based molecular design. (1998, methodology): “An improvement of the method developed by Rost and co-workers (Rost et al., 1995) included the combination of several dierent ®lter systems as well the inclusion of expert knowledge (Rost et al., 1996).”
Comparing function and structure between entire proteomes (2001, methodology): “We filtered the resulting alignments (Rost 1999) and used them as input forPHDhtm(Rost et al. 1996), using the default threshold of 0.8.”
PHAT: a transmembrane-specific substitution matrix (2000, methodology): “Block families were submitted to PHDhtm, a prediction program that achieves 86% transmembrane prediction accuracy per residue ( Rost et al., 1996 ).”