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 can accurately predict structures for many, but the annotations of the transmembrane regions remains a limiting step for proteome-wide predictions. Results: Here, we present a novel method, dubbed TMbed. Inputting embeddings from protein Language Models (in particular ProtT5), TMbed completes predictions of alpha helical and beta barrel TMPs 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 (extracted from family alignments). On the per-protein level, TMbed correctly identified 61 of the 65 beta-barrel TMPs (94±7%) and 579 of the 593 alpha-helical TMPs (98±1%) in a non-redundant data set, at false positive rates well below 1% (erred on 31 of 5859 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. Although limited by GPU memory, our method can handle sequence of up to 4200 residues on standard graphics cards used in common desktop PCs (e.g., NVIDIA GeForce RTX 3060). Conclusions: TMbed accurately predicts alpha helical and beta barrel TMPs. Utilizing protein Language Models and GPU acceleration it can predict the human in less than an hour. Availability: Our code, method, and data sets are freely available in the GitHub repository, https://github.com/BernhoferM/TMbed

LambdaPP: Fast and accessible protein-specific phenotype predictions

“… Panel A: residue level features: secondary structure, transmembrane topology, disordered residues, small molecule, nucleic or metal binding residues, residue conservation and average variation (23; 39; 42; 13; 29); Panel B: sequence-level features: predicted subcellular localization (64), and an excerpt of predicted GO-annotations (38); Panel C: effect of SAVs (wild-type sequence on x-axis, mutations on y-axis; darker color=higher effect) (42); and Panel D : predicted 3D structure (45). Interactive version at https://embed.predictprotein.org/#/Q9NZC2.…”

“…Per-protein features predicted solely with ProtT5 embeddings as input currently include subcellular location (64), and Gene Ontology terms (GO) (38). Per-residue predictions solely with ProtT5 embeddings as input include: conservation (42); helical transmembrane regions, transmembrane beta barrels, along with signal peptides (13); binding for various ligands (39); intrinsically disordered regions (29); secondary structure (23). LambdaPP also predicts the effect of introducing single amino acid variants (SAV) in the input sequence upon molecular function, which uses the predicted conservation with a BLOSUM62-score (26) of the SAV as input (42).…”

“…TMbed predicts for each residue one of four classes: alpha helical transmembrane (TM) region, transmembrane beta strand, signal peptide, or other (13). For proteins with TM regions, it also predicts the inside/outside orientation within the membrane, i.e., on which side of the membrane the N-terminus begins.…”

“…predicting CATH (62) classes (25), LambdaPP will be updated to extend the breadth of pLM-based predictions offered. All feature prediction methods integrated into the LambdaPP webserver are currently based on ProtT5 embeddings (23) as methods trained on ProtT5 have, so far in our hands, outperformed those trained on ESM-1b (54) and others (4; 9; 24; 23) for numerous different applications (37-39; 42; 64; 13; 25; 72). This consistency also increases speed as the generation of embeddings has become a limiting step.…”

“…Starting with an amino acid sequence, LambdaPP orchestrates the prediction of (1) protein structure using ColabFold (45); (2) per-protein features: Gene Ontology (GO) annotations using goPredSim (38), subcellular location using LA (64); (3) per-residue features: binding residues using bindEmbed21DL (39), conservation using ProtT5cons (42), disorder using SETH (29), secondary structure using ProtT5-sec (23), helical and barrel transmembrane (TM) regions using TMbed (13); and (4) variant effect scores using VESPAl (42). …”