Transmembrane helices predicted at 95% accuracy

How researchers see this paper

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

Artificial neural networks for computer-based molecular design. (1998, methodology): “At least two transembrane helices were indicated for 59 proteins corresponding to about 25% of all proteins on yeast chromosome VIII, and about 20% showed multiple transmembrane segments (Rost et al., 1995).”
Predicting transmembrane protein topology with a hidden Markov model: application to complete genomes. (2001, methodology): “Several methods use a sliding window which is predicted as being part of a membrane helix or not, either by a weight matrix (Edelman, 1993) or by a neural network (Rost et al., 1995; Casadio et al., 1996).”
Improved Disorder Prediction by Combination of Orthogonal Approaches (2009, methodology): “PROFhtm [74] is a method that predicts transmembrane helices (green rectangles).”
Unexpected features of the dark proteome (2015, methodology): “Proc Natl Acad Sci USA 106(27): 11079–11084.”