tFold: epitope-specific de novo antibody design
Peer-reviewed| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2025/2026 |
| Venue / status | Peer-reviewed journal; Nature Communications (Q1); issue 2026 |
| DOI | 10.1038/s41467-025-67361-9 |
| URL | https://doi.org/10.1038/s41467-025-67361-9 |
| Preprint URL | NR |
| Tools | tFold System |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | Epitope-specific de novo mAb CDR generation with integrated complex modeling and virtual screening |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | Sequence generator + tFold-Ab/tFold-Ag structure/complex models + structure-aware filters |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | CDR sequences, candidate antibody structures and antibody–antigen complexes |
| Conditioning | Fixed framework family, epitope, CDR length combinations |
| Sampling | NR |
Training
| Поле | Значение |
|---|---|
| Objectives / losses | NR |
| Dataset | NR |
| Preprocessing | NR |
Inference
NR
Baselines и retrospective benchmarks
| Поле | Значение |
|---|---|
| Baselines | NR |
| Retrospective | NR |
Prospective experimental validation
| Поле | Значение |
|---|---|
| Prospective | Best reported Kd: 3.22 nM Flu A, 81.6 nM PD-1, 0.045 nM PD-L1, 2.0 nM SC2RBD; after phage display screening |
| Tested designs | Four therapeutic targets; ten Fc-fusion antibodies characterized in reported campaign |
| Success criterion | Best reported Kd: 3.22 nM Flu A, 81.6 nM PD-1, 0.045 nM PD-L1, 2.0 nM SC2RBD; after phage display screening |
| Main results | Best reported Kd: 3.22 nM Flu A, 81.6 nM PD-1, 0.045 nM PD-L1, 2.0 nM SC2RBD; after phage display screening |
Limitations
Generation, ranking and display selection are intertwined; reported affinities cannot be attributed to generator alone; framework/design space constrained.
Что статья показывает
- Best reported Kd: 3.22 nM Flu A, 81.6 nM PD-1, 0.045 nM PD-L1, 2.0 nM SC2RBD; after phage display screening
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| tFold: epitope-specific de novo antibody design | Interpretation | DOI/URL from landscape matrix |
| Publication status: Peer-reviewed journal; Nature Communications (Q1); issue 2026 | Author-reported | landscape matrix, publication status column |
Review queue
- Bibliographic title must be verified against the PDF.
Source-grounded разбор статьи
Исследовательский вопрос
[MATRIX]Epitope-specific de novo mAb CDR generation with integrated complex modeling and virtual screening
Утверждения и поддержка evidence
[MATRIX]Claimed novelty: NR
[INTERPRETATION]Статья не «доказывает» общее преимущество метода вне своего экспериментального дизайна.
Что представленный evidence не поддерживает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Ограничения, признанные авторами
[MATRIX]Generation, ranking and display selection are intertwined; reported affinities cannot be attributed to generator alone; framework/design space constrained.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.