De novo design of protein structure and function with RFdiffusion
Peer-reviewed| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2023 |
| Venue / status | Peer-reviewed journal; Nature (Q1) |
| DOI | 10.1038/s41586-023-06415-8 |
| URL | https://doi.org/10.1038/s41586-023-06415-8 |
| Preprint URL | NR |
| Tools | RFdiffusion |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | De novo backbone generation; motif scaffolding; oligomers; target-conditioned binders |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | SE(3) diffusion fine-tuned from RoseTTAFold |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | Protein backbone / complex geometry; sequence is downstream |
| Conditioning | Contigs, motifs, hotspots, target, symmetry, partial diffusion |
| 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 | Strong general protein evidence; not antibody-specific |
| Tested designs | Hundreds of designs across motif, binder and assembly campaigns; task-specific counts in paper |
| Success criterion | Strong general protein evidence; not antibody-specific |
| Main results | Strong general protein evidence; not antibody-specific |
Limitations
Backbone-only; sequence and validation are separate; input hotspot choice strongly affects outcome; vanilla model fails on antibody loop geometry.
Что статья показывает
- Strong general protein evidence; not antibody-specific
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| De novo design of protein structure and function with RFdiffusion | Author-reported | DOI/URL from landscape matrix |
| Publication status: Peer-reviewed journal; Nature (Q1) | Author-reported | landscape matrix, publication status column |
Source-grounded разбор статьи
Исследовательский вопрос
[MATRIX]De novo backbone generation; motif scaffolding; oligomers; target-conditioned binders
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]Backbone-only; sequence and validation are separate; input hotspot choice strongly affects outcome; vanilla model fails on antibody loop geometry.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.