The GenSci148 program illustrates a shift from one-time mutation prediction to iterative protein engineering under real drug-development constraints

GenSci148 项目展示了从一次性突变预测向在真实药物研发约束下进行迭代式蛋白质工程的转变

SHANGHAI

上海

,

，

Aug. 20, 2026

2026年8月20日

/PRNewswire/ --

/美通社/ --

Shanghai Matwings Technology Co., Ltd. ('Matwings')

上海马翼科技有限公司（“马翼”）

today announced that

今日宣布

GenSci148 Injection

GenSci148 注射液

, an investigational ophthalmic biologic developed by

，一种由……开发的在研眼科生物制剂

Changchun GeneScience Pharmaceutical Co., Ltd. ('GenSci')

长春金赛药业股份有限公司（“GenSci”）

, has received clinical trial clearance in China for neovascular age-related macular degeneration (nAMD), diabetic macular edema (DME) and retinal vein occlusion (RVO).

，已在中国获得针对新生血管性年龄相关性黄斑变性（nAMD）、糖尿病性黄斑水肿（DME）和视网膜静脉阻塞（RVO）的临床试验批准。

Matwings supported the GenSci148 program through four iterative AI–wet lab cycles covering 222 protein variants. Rather than applying AI as a one-time mutation-prediction tool, the teams repeatedly used experimental results to redesign both molecules and optimization objectives. The program progressed from improving biological activity to balancing potency, stability, expression, formulation and other development-relevant properties—illustrating a shift from predicting mutations to engineering therapeutic proteins under real drug-development constraints..

Matwings 通过四轮迭代的人工智能与湿实验循环，支持了 GenSci148 项目，涵盖了 222 种蛋白质变体。团队并未将人工智能仅作为一次性的突变预测工具，而是反复利用实验结果重新设计分子并优化目标。该项目从最初提高生物活性，逐步发展到平衡效价、稳定性、表达量、制剂以及其他与开发相关的属性，体现了从单纯预测突变向在真实药物开发约束条件下工程化治疗性蛋白质的转变。

Four AI–Wet Lab Cycles, 222 Variants

四个AI-湿实验循环，222个变体

Matwings and GenSci implemented a closed-loop workflow combining

Matwings 和 GenSci 实施了结合闭环工作流程

AI-guided molecular design, wet-lab testing, experimental feedback and redesign

AI引导的分子设计、湿实验测试、实验反馈与重新设计

.

。

Across

横向

four iterative cycles

四个迭代周期

, the teams evaluated

，各团队评估了

222 protein variants

222种蛋白质变体

. The first two rounds assessed 92 and 30 variants, respectively, with an initial focus on biological activity. The next two rounds evaluated 50 variants each, expanding the optimization objectives to include high-concentration formulation viscosity and broader developability requirements.

前两轮分别评估了92种和30种变体，初步聚焦于生物活性。接下来的两轮各评估了50种变体，将优化目标扩展至包括高浓度制剂粘度以及更广泛的可开发性要求。

Experimental results from each round were incorporated into subsequent design cycles, allowing not only the molecular designs but also the optimization objectives to evolve as evidence accumulated.

每一轮的实验结果都被纳入后续的设计循环中，使得随着证据的积累，不仅分子设计得以演进，优化目标也随之调整。

The campaign therefore progressed from:

因此，活动进展如下：

activity optimization → broader developability optimization → multi-objective molecular engineering

活性优化 → 更广泛的可开发性优化 → 多目标分子工程

Across the optimization campaign, experimentally tested variants demonstrated improvements or favorable performance across six development-relevant properties:

在整个优化活动中，经过实验测试的变体在六个与开发相关的属性上均表现出改进或良好的性能：

Development Parameter

开发参数

Observed Result

观测结果

VEGF-A binding affinity

VEGF-A结合亲和力

Up to approximately

最高约

10-fold improvement

10倍提升

VEGF-A/C/D functional

VEGF-A/C/D 功能

blockade

封锁

Up to approximately

最高约

3-fold improvement

三倍提升

Nonclinical in vivo activity

非临床体内活性

Inhibitory activity observed

观察到抑制活性

84 days after dosing in the

给药后第84天

evaluated retinal model

评估的视网膜模型

Thermal stability

热稳定性

Tm increased by up to approximately 4.5°C

Tm 升高了约 4.5°C

Protein expression

蛋白质表达

Increased by up to approximately

增加至多约

27.6%

27.6%

High-concentration formulation

高浓度制剂

viscosity

粘度

Reduced by approximately

减少了大约

13 cP

13 厘泊

Together, these results reflect optimization across three increasingly demanding dimensions of therapeutic protein development: biological performance, molecular developability and formulation-relevant properties.

这些结果共同反映了在治疗性蛋白质开发的三个日益严苛的维度上的优化：生物性能、分子可开发性以及与制剂相关的特性。

In the nonclinical retinal model evaluated during the program, the optimized molecule maintained inhibitory activity 84 days after dosing. Under the specific experimental conditions tested, it also showed greater inhibition than aflibercept and faricimab.

在该项目评估的非临床视网膜模型中，优化后的分子在给药后84天仍保持抑制活性。在测试的特定实验条件下，其抑制作用也强于阿柏西普和法瑞西单抗。

These findings are preclinical and do not establish comparative clinical efficacy or safety.

这些发现属于临床前研究结果，并未确立比较性的临床疗效或安全性。

Beyond Mutation Prediction: Engineering Proteins Under Real Drug-Development Constraints

超越突变预测：在真实药物开发约束下进行蛋白质工程

Therapeutic protein engineering requires balancing biological activity with stability, expression, formulation and other development constraints. In the GenSci148 program, experimental results continuously informed subsequent AI-guided designs, enabling the optimization process to move beyond a single fixed objective..

治疗性蛋白质工程需要在生物活性与稳定性、表达、制剂以及其他开发约束之间取得平衡。在 GenSci148 项目中，实验结果持续为后续的人工智能引导设计提供依据，使优化过程能够超越单一固定目标。

Some experimentally validated mutations were located

一些经实验验证的突变位于

away from the conventional target-binding interface

远离传统的靶标结合界面

, illustrating how AI-guided exploration can identify productive regions of sequence space beyond interface-focused design.

，展示了人工智能引导的探索如何识别序列空间中超越界面聚焦设计的高效区域。

The program also illustrates a broader progression in protein AI validation:

该计划还展示了蛋白质人工智能验证方面更广泛的进展：

computational benchmarking → experimental validation → repeated integration within a real drug-development workflow

计算基准测试 → 实验验证 → 在真实药物研发流程中的反复整合

GenSci148 represents the third stage of this progression, with AI-guided design and experimental evidence repeatedly linked across successive engineering cycles.

GenSci148 代表了这一进程的第三阶段，其中人工智能引导的设计与实验证据在连续的工程周期中反复相互印证。

The Venus Protein AI Stack

维纳斯蛋白质人工智能栈

Matwings'

马特温斯

Venus

金星

protein AI stack has evolved from sequence-centered modeling toward systems integrating three-dimensional structure, evolutionary information and task-specific capabilities. Importantly, the AI-guided engineering work supporting GenSci148 was conducted using

蛋白质人工智能技术栈已从以序列为中心的建模，演变为整合三维结构、进化信息和任务特定能力的系统。重要的是，支持 GenSci148 的 AI 引导工程工作是在以下基础上开展的：

Venus 1.0

金星 1.0

, while Venus has since advanced to

，而金星此后已推进至

Venus 3.0, represented by VenusREM

由 VenusREM 代表的 Venus 3.0

, which integrates protein sequence, three-dimensional structure and evolutionary information for mutation-effect prediction.

，该方法整合蛋白质序列、三维结构和进化信息，用于突变效应预测。

Rather than relying on a single model, different components are applied to different protein R&D and engineering tasks within the broader closed-loop workflow.

在更广泛的闭环工作流程中，不同的组件被应用于不同的蛋白质研发和工程任务，而不是依赖于单一模型。

Generation

生成

Representative Model(s)

代表性模型

Information Integrated

信息集成

Primary Role

主要角色

Venus 1.0

金星 1.0

Venus 1.0

金星 1.0

Protein sequence

蛋白质序列

Sequence-

序列-

centered

居中

modeling

建模

Venus 2.0

金星 2.0

Venus-ProSST

金星-ProSST

Sequence + 3D structure

序列 + 三维结构

Structure-aware

结构感知

modeling

建模

Venus 3.0

金星 3.0

VenusREM

金星REM

Sequence + 3D structure +

序列 + 三维结构 +

evolutionary information

进化信息

Mutation-effect

突变效应

prediction

预测

Task-Specific

任务特定

Models

模型

Venus-FSFP, Venus-Maxwell, Venus-Mine, Venus-RXN, Venus-

金星-FSFP，金星-麦克斯韦，金星-Mine，金星-RXN，金星-

Fold

折叠

Task-dependent

任务依赖型

Protein R&D and

蛋白质研发及

engineering

工程

Certain models within the broader Venus portfolio are in development or planned stages.

维纳斯产品组合中的某些型号正处于开发或规划阶段。

Together, these models form a specialist AI stack that can be combined with experimental data and iterative design across different stages of protein engineering.

这些模型共同构成了一个专业化的AI技术栈，能够与实验数据及迭代设计相结合，应用于蛋白质工程的不同阶段。

From External Validation to Therapeutic Creation

从外部验证到治疗性创造

The GenSci148 collaboration provides external validation of Matwings' protein-engineering capabilities in a real therapeutic development program.

GenSci148 合作项目在真实的药物研发项目中，对外部验证了 Matwings 的蛋白质工程能力。

In March 2026, Matwings established

2026年3月，Matwings成立

Shanghai Biowings Therapeutics Co., Ltd. ('Biowings Therapeutics')

上海百奥维生制药有限公司（“百奥维生制药”）

to apply the same closed-loop engineering approach to internally originated therapeutic programs. Matwings develops the underlying AI and protein-engineering technology engine, while Biowings Therapeutics combines these capabilities with disease biology and drug-development expertise to create and advance therapeutic candidates..

将同样的闭环工程方法应用于内部发起的治疗项目。Matwings 开发底层的 AI 和蛋白质工程技术引擎，而 Biowings Therapeutics 则将这些能力与疾病生物学及药物开发专业知识相结合，以创建并推进候选治疗药物。

'The real test of AI for science is not whether a model performs well on a benchmark, but whether it can create measurable value through repeated design–experiment cycles in an actual R&D program,' said Prof. Liang Hong, Founder and Chief Scientist of Matwings.

“人工智能在科学领域的真正考验，不在于模型在基准测试中表现如何，而在于它能否在实际的研发项目中，通过反复的设计—实验循环创造可衡量的价值。”物质之翼创始人兼首席科学家梁宏教授表示。

'GenSci148 marks an important step from demonstrating individual model capabilities toward building a repeatable protein-engineering system.'

“GenSci148 标志着从展示单个模型能力向构建可重复的蛋白质工程系统迈出的重要一步。”

'Matwings contributed important molecular engineering and optimization capabilities to the GenSci148 program,' said Dr. Lei Jin, CEO of GenSci.

“Matwings为GenSci148项目贡献了重要的分子工程与优化能力。”GenSci首席执行官金磊博士表示。

'Rather than relying on one-time predictions, the teams repeatedly combined AI-guided design with experimental evidence to improve properties relevant to drug development.'

“各团队并未依赖一次性预测，而是反复将人工智能引导的设计与实验证据相结合，以改善与药物开发相关的特性。”

About Matwings

关于Matwings

Shanghai Matwings Technology Co., Ltd.

上海迈特温斯科技有限公司

is an AI-driven protein R&D company integrating specialist AI models, computational molecular design and experimental validation to support iterative protein engineering and drug development.

是一家由人工智能驱动的蛋白质研发公司，整合专业AI模型、计算分子设计与实验验证，以支持迭代式蛋白质工程和药物开发。

For more information, visit

更多信息，请访问

www.matwings.com

www.matwings.com

.

。

About Biowings Therapeutics

关于Biowings Therapeutics

Shanghai Biowings Therapeutics Co., Ltd.

上海生物翼制药有限公司

focuses on AI-enabled therapeutic asset creation and clinical translation.

专注于人工智能赋能的治疗性资产开发与临床转化。

Scientific and Development Notice:

科学与开发通知：

GenSci148 is an investigational product. Its safety and efficacy have not been established. Preclinical findings are specific to the experimental systems and conditions evaluated and may not predict clinical outcomes.

GenSci148 是一种研究性产品。其安全性和有效性尚未确立。临床前研究结果特定于所评估的实验系统和条件，可能无法预测临床结局。

Contact:

联系方式：

Website:

网站：

www.matwings.com

www.matwings.com

E-mail:

电子邮件：

[email protected]

[email protected]

SOURCE Shanghai Matwings Technology Co., Ltd.; Shanghai Biowings Therapeutics Co., Ltd.

来源：上海迈威生物科技有限公司；上海百奥维治疗有限公司

21

二十一

%

百分比

more press release views with

更多新闻稿浏览量与

Request a Demo

申请演示