DeepTMHMM2 enables accurate prediction of transmembrane protein topology and subcellular location
Transmembrane -helical and {beta}-barrel proteins are a ubiquitous component of proteomes. Topology prediction infers how proteins are embedded in lipid bilayers, identifying membrane-spanning segments and their orientation. While recent methods achieve high performance for membrane-spanning segments, they cannot predict re-entrant regions and interfacial helices - membrane-associated segments…
Transmembrane and beta-barrel proteins are widespread elements within proteomes. Predicting the topology of these proteins reveals how they are embedded within lipid bilayers, pinpointing membrane-spanning sections and their direction. While previous techniques have excelled at identifying membrane-spanning sections, they fall short when it comes to predicting re-entrant areas and interfacial helices - membrane-associated segments that only partially penetrate the bilayer - and determining the type of biological membrane a protein is found in.
Introducing DeepTMHMM2, the initial predictor capable of incorporating re-entrant regions and interfacial helices into its topological predictions, and jointly forecasting localization across 17 distinct biological membranes. Results from benchmarks demonstrate that DeepTMHMM2 excels at learning these extra elements while maintaining high accuracy in predicting the standard -helical and beta-barrel topology.
When applied to Swiss-Prot, the analysis uncovers that non-crossing segments are a common trait in the transmembrane proteome, with interfacial helices appearing in almost a quarter of all -helical transmembrane proteins.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
