Humanization of antibodies and nanobodies by diffusion models
Preprint| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2024/2025 |
| Venue / status | bioRxiv preprint (Frontier/Watchlist) |
| DOI | 10.1101/2024.10.22.619416 |
| URL | https://doi.org/10.1101/2024.10.22.619416 |
| Preprint URL | https://doi.org/10.1101/2024.10.22.619416 |
| Tools | HuDiff |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | De novo framework generation / humanization of antibodies and nanobodies from CDRs |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | Adaptive autoregressive diffusion; separate antibody and nanobody models |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | Humanized variable-domain sequence around supplied CDRs |
| Conditioning | CDRs fixed; human/nanobody priors |
| 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 antibody variant 0.15 nM vs parent 0.12 nM by BLI; nanobody binding retained in reported study |
| Tested designs | One murine antibody and two alpaca nanobody parents prospectively humanized |
| Success criterion | Best antibody variant 0.15 nM vs parent 0.12 nM by BLI; nanobody binding retained in reported study |
| Main results | Best antibody variant 0.15 nM vs parent 0.12 nM by BLI; nanobody binding retained in reported study |
Limitations
Preprint; only three parent series prospectively tested; retained affinity does not establish reduced immunogenicity/manufacturability.
Что статья показывает
- Best antibody variant 0.15 nM vs parent 0.12 nM by BLI; nanobody binding retained in reported study
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| Humanization of antibodies and nanobodies by diffusion models | Interpretation | DOI/URL from landscape matrix |
| Publication status: bioRxiv preprint (Frontier/Watchlist) | Author-reported | landscape matrix, publication status column |
Review queue
- Bibliographic title must be verified against the PDF.
Source-grounded разбор статьи
Исследовательский вопрос
[MATRIX]De novo framework generation / humanization of antibodies and nanobodies from CDRs
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]Preprint; only three parent series prospectively tested; retained affinity does not establish reduced immunogenicity/manufacturability.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.