Methods of predicting protein conformation from amino acid sequence are reviewed. Several widely used algorithms to predict local secondary structure are first discussed. Four general approaches to predict the tertiary structure are then described: (1) energy calculations from an open chain; (2) recognition of sequence homology with a known structure; (3) uses of a sequence template that dictates a particular fold; (4) docking alpha-helices and beta-strands. Throughout this review, the likely success of these methods is considered.