TMbed: transmembrane proteins predicted through language model embeddings

Abstract

Background: Despite the immense importance of transmembrane proteins (TMP) for molecular biology and medicine, experimental 3D structures for TMPs remain about 4-5 times underrepresented compared to non-TMPs. Today's top methods such as AlphaFold2 accurately predict 3D structures for many TMPs, but annotating transmembrane regions remains a limiting step for proteome-wide predictions.

Results: Here, we present TMbed, a novel method inputting embeddings from protein Language Models (pLMs, here ProtT5), to predict for each residue one of four classes: transmembrane helix (TMH), transmembrane strand (TMB), signal peptide, or other. TMbed completes predictions for entire proteomes within hours on a single consumer-grade desktop machine at performance levels similar or better than methods, which are using evolutionary information from multiple sequence alignments (MSAs) of protein families. On the per-protein level, TMbed correctly identified 94 ± 8% of the beta barrel TMPs (53 of 57) and 98 ± 1% of the alpha helical TMPs (557 of 571) in a non-redundant data set, at false positive rates well below 1% (erred on 30 of 5654 non-membrane proteins). On the per-segment level, TMbed correctly placed, on average, 9 of 10 transmembrane segments within five residues of the experimental observation. Our method can handle sequences of up to 4200 residues on standard graphics cards used in desktop PCs (e.g., NVIDIA GeForce RTX 3060).

Conclusions: Based on embeddings from pLMs and two novel filters (Gaussian and Viterbi), TMbed predicts alpha helical and beta barrel TMPs at least as accurately as any other method but at lower false positive rates. Given the few false positives and its outstanding speed, TMbed might be ideal to sieve through millions of 3D structures soon to be predicted, e.g., by AlphaFold2.

Keywords: Protein language models; Protein structure prediction; Transmembrane protein prediction.

Fig. 1

Potential transmembrane proteins in the globular data set. AlphaFold2 [11, 68] structure of extracellular serine protease (P09489) and Lipase 1 (P40601). Transmembrane segments (dark purple) predicted by TMbed correlate well with membrane boundaries (dotted lines: red = outside, blue = inside) predicted by the PPM [45] web server. Images created using Mol* Viewer [71]. Though our data set lists them as globular proteins, the predicted structures indicate transmembrane domains, which align with segments predicted by our method. The predicted domains overlap with autotransporter domains detected by the UniProtKB [46] automatic annotation system. Transmembrane segment predictions were made with the final TMbed ensemble model

Fig. 2

New membrane proteins. PDB structures for probable flagellin 1 (Q9YAN8; 7TXI [73]), protein-serine O-palmitoleoyltransferase porcupine (Q9H237; 7URD [74]), choline transporter-like protein 1 (Q8WWI5; 7WWB [75]), S-layer protein SlpA (Q9RRB6; 7ZGY [76]), and membrane protein (P0DTC5; 8CTK [77]). Transmembrane segments (dark purple) predicted by TMbed; membrane boundaries (dotted lines: red = outside, blue = inside) predicted by the PPM [45] web server. Images created using Mol* Viewer [71]