Large language models generate functional protein sequences across diverse families
Peer-reviewed| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2023 |
| Venue / status | Peer-reviewed journal; Nature Biotechnology (Q1) |
| DOI | 10.1038/s41587-022-01618-2 |
| URL | https://doi.org/10.1038/s41587-022-01618-2 |
| Preprint URL | NR |
| Tools | ProGen / ProGen2 |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | General protein sequence generation |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | Autoregressive Transformer; control tags / family conditioning |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | Amino-acid sequence |
| Conditioning | Tags, prefix; no native 3D constraints |
| 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 | Prospective enzymatic function reported; not antibody evidence |
| Tested designs | Functional artificial sequences across several lysozyme families; exact aggregate count: NR here |
| Success criterion | Prospective enzymatic function reported; not antibody evidence |
| Main results | Prospective enzymatic function reported; not antibody evidence |
Limitations
Sequence plausibility is not structural or functional proof; conditioning vocabulary is coarse; family transfer requires care.
Что статья показывает
- Prospective enzymatic function reported; not antibody evidence
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| Large language models generate functional protein sequences across diverse families | Author-reported | DOI/URL from landscape matrix |
| Publication status: Peer-reviewed journal; Nature Biotechnology (Q1) | Author-reported | landscape matrix, publication status column |
Source-grounded разбор статьи
Исследовательский вопрос
[MATRIX]General protein sequence 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]Sequence plausibility is not structural or functional proof; conditioning vocabulary is coarse; family transfer requires care.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.