Illuminating protein space with a programmable generative model
Peer-reviewed| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2023 |
| Venue / status | Peer-reviewed journal; Nature (Q1) |
| DOI | 10.1038/s41586-023-06728-8 |
| URL | https://doi.org/10.1038/s41586-023-06728-8 |
| Preprint URL | NR |
| Tools | Chroma |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | Programmable de novo protein and complex generation |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | Backbone diffusion + equivariant graph networks + conditional random field sequence design |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | Backbone/all-atom structure and sequence |
| Conditioning | Substructure, symmetry, shape, class/annotation and custom differentiable conditioners |
| 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 | General protein evidence |
| Tested designs | Early biophysical and crystallographic validation; exact count: NR |
| Success criterion | General protein evidence |
| Main results | General protein evidence |
Limitations
Weights access is gated; conditioner scores are not measured function; no antibody-specific proof.
Что статья показывает
- General protein evidence
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| Illuminating protein space with a programmable generative model | 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]Programmable de novo protein and complex generation
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]Weights access is gated; conditioner scores are not measured function; no antibody-specific proof.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.