⚙
AI-generated deep summary
by claude@2026-07, 2026-07-06
· read from full text
ⓘ
The paper introduces FrustrAI-Seq, an ultra-fast, purely sequence-based method to predict local energetic frustration in proteins using embeddings from protein language models, aiming to replace costly structure-based frustration calculations. Using proteome-scale benchmarking, the authors report that it can profile the entire human proteome in about 17 minutes on a single Nvidia H100 GPU while maintaining biologically relevant performance on the α-globin and β-lactamase protein families. A stated limitation is that the approach is trained and evaluated in ways that still depend on model-based sequence representations rather than explicit structural or evolutionary information, which it deliberately avoids to broaden applicability. This paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.
Abstract
Proteins fold into their native three-dimensional (3D) structures by navigating complex energy landscapes shaped by the biophysical and biochemical properties of their sequence. Once folded, some sequence positions (dubbed residues) remain locally frustrated, reflecting functional constraints incompatible with optimal packing. This local energetic frustration provides important insights into protein function and dynamics, but its analysis typically relies on structure-based energy calculations and remains energetically costly at scale. Here, we introduce an ultra-fast sequence-based prediction of local energetic frustration directly from protein sequences using embeddings from protein language models (pLMs). Our method, coined FrustrAI-Seq , enables proteome-wide frustration profiling in minutes (∼ 17 minutes for the entire human proteome on a single Nvidia H100 GPU) while retaining biologically relevant performance as shown for the α -globin and β -lactamase family. By eliminating the need for explicit structural or evolutionary information, this approach expands frustration analysis to protein regions and classes that were previously inaccessible, including intrinsically disordered regions and high-throughput de novo designed protein datasets. To support reproducibility and large-scale applications, we provide the largest freely available resource of precomputed local frustration scores to date (∼10 6 proteins), along with model weights and complete training and inference code at: github.com/leuschjanphilipp/FrustrAI-Seq .
Full text
1,732 characters
· extracted from
oa-doi-fallback
· click to expand
Abstract
Proteins fold into their native three-dimensional (3D) structures by navigating complex energy landscapes shaped by the biophysical and biochemical properties of their sequence. Once folded, some sequence positions (dubbed residues) remain locally frustrated, reflecting functional constraints incompatible with optimal packing. This local energetic frustration provides important insights into protein function and dynamics, but its analysis typically relies on structure-based energy calculations and remains energetically costly at scale. Here, we introduce an ultra-fast sequence-based prediction of local energetic frustration directly from protein sequences using embeddings from protein language models (pLMs). Our method, coined FrustrAI-Seq, enables proteome-wide frustration profiling in minutes (∼ 17 minutes for the entire human proteome on a single Nvidia H100 GPU) while retaining biologically relevant performance as shown for the α-globin and β-lactamase family. By eliminating the need for explicit structural or evolutionary information, this approach expands frustration analysis to protein regions and classes that were previously inaccessible, including intrinsically disordered regions and high-throughput de novo designed protein datasets. To support reproducibility and large-scale applications, we provide the largest freely available resource of precomputed local frustration scores to date (∼106 proteins), along with model weights and complete training and inference code at: github.com/leuschjanphilipp/FrustrAI-Seq.
- Local Energetic Frustration
- Frustration
- Protein Language Model
- Frus-tratometer
- FrustraEvo
Competing Interest Statement
The authors have declared no competing interest.
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.