FlowDesign

Peer-reviewed Prospective flag Direct antibody flag

Summary card

Поле	Значение
Год / version	2025 / NR
Last verified	2026-08-13
Что генерирует	CDR sequence and structure
Форматы	Antibody Fv-like designs
De novo или optimization	CDR de novo/redesign
DOI	10.1016/j.cels.2025.101270
Paper	https://doi.org/10.1016/j.cels.2025.101270
GitHub / repo	NR
Service / docs	NR
Лицензия	NR
Доступность / commercial-use	Paper; code availability NR

Задача и generated object

Used in these tasks: Joint CDR sequence–structure design, Генерация CDR sequence

Part of these workflows: Antigen-conditioned CDR co-design

Поле	Значение
Required input	Antibody framework/complex context depending task
Conditioning	CDR design masks and structural priors
Fixed	NR
Editable	NR
Generated	CDR sequence and structure
Single mutations	Possible
Combinatorial mutations	Yes
Multi-objective	No explicit multi-objective optimizer

Architecture and operating principle

Author-reported (matrix)

Поле	Значение
Base architecture	NR
Model type	4 Joint antibody sequence–structure generator
Representation	NR
Generation unit	CDR sequence and structure
Conditioning	CDR design masks and structural priors
Output	CDR sequence and structure
Sampling	NR
Internal scorer	Computational structure/energy metrics
Structure generation	Joint geometry generation

Input representation

Поле	Значение
Node features	NR
Edge / pair features	NR

Encoder и decoder

Поле	Значение
Encoder	NR
Decoder	NR

Latent or generative state

Conditioning mechanism

CDR design masks and structural priors

Generation mechanism

Flow matching with improved structural priors

Sampling: NR

Training objectives

Losses: NR

Mathematical details: NR

Integrated evaluation

Computational structure/energy metrics

Architectural limitations

Narrow prospective target context.
lack of verified public code blocks independent pilot.
must separate predicted and measured gains.

Uses these architecture components: Flow matching, Joint sequence–structure generation

Generator versus evaluation

Component	Role	Architecture class	Integrated or external	Required or optional	Influences generation or post hoc	Runtime included or excluded
FlowDesign flow-matching model	primary_generator	Flow matching with improved structural priors	integrated	required	generation	included
Computational structure/energy metrics	integrated_scorer	NR	integrated	optional	post_hoc	unknown
Joint geometry generation	integrated_structure_predictor	NR	integrated	optional	post_hoc	included
Independent complex prediction and functional testing	mandatory_external_dependency	NR	external	required	post_hoc	excluded
Experimental binding/function assays	experimental_validation	NR	external	required	post_hoc	excluded

Training data и biases

Поле	Значение
Training data	NR
Preprocessing	NR
Negative examples	NR
Fine-tuning	NR
Label requirements	NR
Training hardware	NR
Training time	NR

Inference hardware и runtime

Поле	Значение
Candidate count	NR
Batch size	NR
Generation steps	NR
Recycles	NR
Size	NR
Reported runtime	NR
Runtime boundary	NR
CPU	NR
GPU	NR
VRAM	NR
RAM	NR
Disk	NR
Databases	NR

Experimental evidence

Поле	Значение
Evidence class	3–4 prospective binding/neutralization validation
Retrospective	NR
Prospective binding	Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction
Prospective function	Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction
Developability	NR
Tested design count	Ibalizumab-focused HIV design study; exact tested count: NR here
Success criterion	Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction
Independent validation	NR
Summary	Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction

Limitations and failure modes

Narrow prospective target context.
lack of verified public code blocks independent pilot.
must separate predicted and measured gains.

Deployment: Research-only until reproducibility confirmed

Reproducibility, license, commercial use

Поле	Значение
Repo	NR
License	NR
Commercial-use status	Paper; code availability NR

Alternative tools: NR

Complementary: NR

Related: NR

Not directly comparable with

AntiFold, Efficient evolution with ESM-1v, ESM-IF1, LigandMPNN, ProteinMPNN, Structural evolution (ESM-IF1 complex)

Сравнение допустимо только внутри совместимых категорий. Runtime и quality AntiFold vs RFantibody нельзя читать как одну шкалу: разные starting points и generated objects.

Depends on these external modules

Primary paper и полный список источников

Flow matching for antibody CDR sequence–structure co-design

Source matrix: landscape xlsx, last verified 2026-08-13.

Review queue

Bibliographic title must be verified against the PDF.
Official repository/service not verified.

Детальный source-grounded разбор

1. Что именно делает инструмент

[MATRIX]Вход: Antibody framework/complex context depending task

[MATRIX]Generated object: CDR sequence and structure

[MATRIX]Фиксируется: NR. Изменяется: NR.

[MATRIX]De novo или parent-based: CDR de novo/redesign.

2. Архитектура в одном абзаце

[MATRIX]Flow matching with improved structural priors

4. Математическая модель

NRТочные уравнения, losses и sampling solver будут внесены после чтения paper/code. Не подставляйте родовой UCB/transformer/diffusion, если он не подтверждён для этого инструмента.

Поля NR: conditional probability, update equations, sampling algorithm

5. Физическое устройство состояния

[MATRIX]Seed generated state / output: CDR sequence and structure. Structure generation: Joint geometry generation.

6. Физико-химическая интерпретация

[INTERPRETATION]Координаты, frames, PLM embeddings или residue tokens не являются расчётом ΔG, электростатики или растворителя, пока это не сделано внешней energy function. Likelihood / pLDDT / docking score ≠ экспериментальный binding.

7. Training

[MATRIX]Данные: NR. Fine-tuning: NR. Negative examples: NR.

8. Inference

[MATRIX]Sampling: NR. Generation steps: NR. Runtime boundary: NR.

10. Почему, по мнению авторов, метод эффективен

[MATRIX]Author-reported summary (матрица): Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction

NRCausal support не классифицирован, пока не прочитаны ablation и experimental sections.

12. Ablation analysis

NRAblation в этом выпуске не разобрана.

13. What the model does not represent

Явный растворитель и ионная сила — обычно отсутствуют в генераторе.
Протонирование, гликозилирование, кофакторы — обычно отсутствуют, если не оговорено.
Конформационная энтропия и долгая динамика — не моделируются одним forward pass.
Экспрессия, агрегация, иммуногенность — не равны likelihood генератора.
Истинная binding free energy — не равна internal score.

14. Evidence and limitations

[MATRIX]Evidence class (матрица): 3–4 prospective binding/neutralization validation. Prospective binding: Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction. Function: Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction. Developability: NR.

Narrow prospective target context.
lack of verified public code blocks independent pilot.
must separate predicted and measured gains.

15. Reproducibility

NRРепозиторий: NR. Лицензия: NR. Commit: NR, пока страница не имеет отдельного analysis YAML.

Модульная схема

Модуль	Класс модели	Вход	Выход	Обучается или frozen	Generator или evaluator
FlowDesign flow-matching model	Flow matching with improved structural priors	NR	NR	NR	primary_generator
Computational structure/energy metrics	NR	NR	NR	NR	integrated_scorer
Joint geometry generation	NR	NR	NR	NR	integrated_structure_predictor
Independent complex prediction and functional testing	NR	NR	NR	NR	mandatory_external_dependency
Experimental binding/function assays	NR	NR	NR	NR	experimental_validation

Generator versus evaluator

Компонент	Роль	Integrated или external	Required или optional	Влияет на generation или только ранжирует после
FlowDesign flow-matching model	primary_generator	integrated	required	generation
Computational structure/energy metrics	integrated_scorer	integrated	optional	post_hoc
Joint geometry generation	integrated_structure_predictor	integrated	optional	post_hoc
Independent complex prediction and functional testing	mandatory_external_dependency	external	required	post_hoc
Experimental binding/function assays	experimental_validation	external	required	post_hoc

Claim–evidence matrix

Утверждение	Предполагаемый механизм	Тип evidence	Датасет / эксперимент	Comparator	Метрика / результат	Источник	Оговорка
Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction	Flow matching with improved structural priors	5. prospective functional validation	Ibalizumab-focused HIV design study; exact tested count: NR here	NR	Reported improved binding affinity and neutralizing potency versus Ibalizumab; workload-specific details require paper extraction	[MATRIX] landscape matrix 2026-08-13	Не читать как полный разбор primary paper.