Purchase Commercial License

DeepTMHMM predicts alpha and beta transmembrane proteins using deep neural networks. Transmembrane proteins are relevant for drug development since they make up more than 50% of all human drug targets.

DeepTMHMM is currently the most complete and best-performing method for the prediction of the topology of both alpha-helical and beta-barrel transmembrane proteins. The model encodes the primary amino acid sequence by a pre-trained language model and decodes the topology by a state space model to produce topology and type predictions at unprecedented accuracy. DeepTMHMM makes it possible to scan full proteomes in order to detect both classes of transmembrane proteins, and we anticipate our method to be very valuable for the research community.