Home
 /
Papers
 /
Biophysics
 /
Deep learning-based joint sequence–structure de novo membrane protein design
Preprint
Open access
Top 1% · Validated by QED

Deep learning-based joint sequence–structure de novo membrane protein design

Lucas S.P. Rudden, Remo Bättig, Vinnie Andrews +8 more
August 2025
 ·
bioRxiv
 ·
DOI 
10.1101/2025.08.15.670493
99
%
QED Score
QED Impressions

By building the first all-atom joint sequence–structure diffusion model for membrane proteins, this work shatters the longstanding barrier to de novo TM design, delivering programmable receptors, disease-relevant inhibitors, and conformational switches verified by X-ray crystallography.

Run full QED analysis
Read paper
Save

QED claims analysis

Summary

TMDiffusion, a joint all-heavy-atom sequence-structure diffusion model specifically trained on transmembrane protein interactions, achieves >70% experimental success in designing diverse functional membrane proteins including high-affinity oligomers, competitive inhibitors targeting disease mutations, and conformational switches that enable programmable control of single-pass receptor signaling, with atomic-level structural accuracy validated by X-ray crystallography.

See full analysis
Main Claim 1 –

TMDiffusion: First joint all-heavy-atom TM sequence–structure diffusion model

Supporting evidence

  • TMDF recapitulates natural TM helix sequence–structure and interactions
  • Contact maps are required for TMDF sequence–structure learning
Main Claim 2 –

TMDF designs diverse TM architectures with >70% experimental success

Supporting evidence

  • TMDF designs match crystal structures with sub-angstrom accuracy
  • TMDF designs left-handed TM scaffolds that outperform wild-type
  • Designed TM proteins form intended oligomerization states
Main Claim 3 –

TMDF designs FGFR3 A391E TM inhibitors with 47% success

Main Claim 4 –

TMDF programs single-pass receptor signaling via designed TM conformational switching

Supporting evidence

  • Steered MD validates designed interfaces via energy barrier correlations

Abstract

Deep learning has revolutionized soluble protein design, yet de novo transmembrane (TM) protein engineering remains hindered by scarce structural data, complex membrane-specific interactions and conformational dynamics. We developed TMDiffusion (TMDF), a joint all-heavy-atom sequence–structure diffusion model trained to capture the full interaction diversity of natural TM proteins, including weak and polar contact networks. TMDF designs diverse TM architectures—associating domains, inhibitors, and conformational switches—in a single step, achieving >70% experimental success. A crystal structure of designed proteins matches predictions with atomic accuracy. Leveraging TMDF, we built synthetic single-pass receptors whose de novo TM domains toggle between conformations, enabling precise control of signalling outputs consistent with predicted equilibria. These results show that membrane-adapted DL models can accurately encode and program TM association energetics and conformations. TMDF establishes a general framework for bottom-up design of TM proteins with programmable functions, advancing both mechanistic studies of membrane proteins and development of next-generation therapeutics.

Related papers

How the QED Score works

QED Score is an AI-based quality metric for life science research. It rates each paper on two dimensions: originality (is the finding new and important?) and validity (does the evidence support the claims?). Author names and affiliations are removed before scoring. Each manuscript is broken down into its claims and the experiments behind them, and specialized AI agents then examine those claims for statistical rigor, consistency across figures, and contradictions with the existing literature. A verification layer re-checks every issue they flag. Scores are percentile ranks against all papers in the corpus. In a blinded study of papers where QED Score and journal rank disagreed, domain experts sided with QED Score in 75% of cases.
Read the methodology

Free access for academic researchers

Create your free QED account to validate your research, strengthen grant proposals, and uncover scientific insights.
We've sent you an access link.
Please check your inbox.

Didn't get your email? Check your spam folder or reach out to info@qedscience.com

Oops! Something went wrong while submitting the form.
Looking for QED for pharma, biotech or life science organizations?