Humatch: fast and accurate antibody humanization
Peer-reviewed| Поле | Значение |
|---|---|
| Authors | NR |
| Year | 2024 |
| Venue / status | Peer-reviewed journal; mAbs; Q1 status NR |
| DOI | 10.1080/19420862.2024.2434121 |
| URL | https://doi.org/10.1080/19420862.2024.2434121 |
| Preprint URL | NR |
| Tools | Humatch |
Задача и claimed novelty
| Поле | Значение |
|---|---|
| Main biological task | Joint VH/VL framework humanization by mutation proposals |
| Claimed novelty | NR |
Архитектура
| Поле | Значение |
|---|---|
| Model architecture | Gene-specific CNN classifiers + iterative mutation selection and VH/VL pairing score |
| Input representation | NR |
| Encoder / decoder | NR |
| Generative state | Humanized heavy/light variable-domain sequences and mutation set |
| Conditioning | CDRs excluded by default; target human V-genes; paired-chain compatibility |
| Sampling | NR |
Training
| Поле | Значение |
|---|---|
| Objectives / losses | NR |
| Dataset | NR |
| Preprocessing | NR |
Inference
NR
Baselines и retrospective benchmarks
| Поле | Значение |
|---|---|
| Baselines | NR |
| Retrospective | Retrospective similarity to experimental humanizations; no measured affinity retention |
Prospective experimental validation
| Поле | Значение |
|---|---|
| Prospective | NR |
| Tested designs | No prospective wet-lab validation in primary paper |
| Success criterion | Retrospective similarity to experimental humanizations; no measured affinity retention |
| Main results | Retrospective similarity to experimental humanizations; no measured affinity retention |
Limitations
Humanness is not immunogenicity; CDR preservation does not guarantee binding retention; no prospective validation.
Что статья показывает
- Retrospective similarity to experimental humanizations; no measured affinity retention
Чего статья не показывает
- Predicted confidence, likelihood, pLDDT, docking or developability scores are not experimental affinity.
Размеченные утверждения
| Утверждение | Тип | Локатор |
|---|---|---|
| Humatch: fast and accurate antibody humanization | Author-reported | DOI/URL from landscape matrix |
| Publication status: Peer-reviewed journal; mAbs; Q1 status NR | Author-reported | landscape matrix, publication status column |
Source-grounded разбор статьи
Исследовательский вопрос
[MATRIX]Joint VH/VL framework humanization by mutation proposals
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]Humanness is not immunogenicity; CDR preservation does not guarantee binding retention; no prospective validation.
Дополнительные ограничения интерпретации
NRПока Methods/SI не прочитаны, нельзя утверждать split leakage, точные гиперпараметры и полноту ablation.