{"id":67653,"date":"2026-08-20T18:00:00","date_gmt":"2026-08-20T11:00:00","guid":{"rendered":"https:\/\/thaipropertynews.com\/feeds\/?p=67653"},"modified":"2026-08-20T18:00:00","modified_gmt":"2026-08-20T11:00:00","slug":"matwings-demonstrates-closed-loop-protein-ai-through-four-ai-wet-lab-cycles-and-222-protein-variants","status":"publish","type":"post","link":"https:\/\/thaipropertynews.com\/feeds\/?p=67653","title":{"rendered":"Matwings Demonstrates Closed-Loop Protein AI Through Four AI-Wet Lab Cycles and 222 Protein Variants"},"content":{"rendered":"

The GenSci148 program illustrates a shift from one-time mutation prediction to iterative protein engineering under real drug-development constraints<\/b><\/p>\n

SHANGHAI<\/span>, Aug. 20, 2026<\/span> \/PRNewswire\/ — Shanghai Matwings Technology Co., Ltd. (“Matwings”)<\/b> today announced that GenSci148 Injection<\/b>, an investigational ophthalmic biologic developed by Changchun GeneScience Pharmaceutical Co., Ltd. (“GenSci”)<\/b>, has received clinical trial clearance in China for neovascular age-related macular degeneration (nAMD), diabetic macular edema (DME) and retinal vein occlusion (RVO).<\/p>\n

Matwings supported the GenSci148 program through four iterative AI\u2013wet 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\u2014illustrating a shift from predicting mutations to engineering therapeutic proteins under real drug-development constraints.<\/p>\n

Four AI\u2013Wet Lab Cycles, 222 Variants<\/b><\/p>\n

Matwings and GenSci implemented a closed-loop workflow combining AI-guided molecular design, wet-lab testing, experimental feedback and redesign<\/b>.<\/p>\n

Across four iterative cycles<\/b>, the teams evaluated 222 protein variants<\/b>. 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.<\/p>\n

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.<\/p>\n

The campaign therefore progressed from:<\/p>\n

activity optimization \u2192 broader developability optimization \u2192 multi-objective molecular engineering<\/b><\/p>\n

Across the optimization campaign, experimentally tested variants demonstrated improvements or favorable performance across six development-relevant properties:<\/p>\n

\n\n\n\n\n\n\n\n\n\n
\n

Development Parameter<\/b><\/span><\/p>\n<\/td>\n

\n

Observed Result<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

VEGF-A binding affinity<\/b><\/span><\/p>\n<\/td>\n

\n

Up to approximately 10-fold improvement<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

VEGF-A\/C\/D functional
blockade<\/b><\/span><\/p>\n<\/td>\n

\n

Up to approximately 3-fold improvement<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Nonclinical in vivo activity<\/b><\/span><\/p>\n<\/td>\n

\n

Inhibitory activity observed 84 days after dosing in the
evaluated retinal model<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Thermal stability<\/b><\/span><\/p>\n<\/td>\n

\n

Tm increased by up to approximately 4.5\u00b0C<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Protein expression<\/b><\/span><\/p>\n<\/td>\n

\n

Increased by up to approximately 27.6%<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

High-concentration formulation
viscosity<\/b><\/span><\/p>\n<\/td>\n

\n

Reduced by approximately 13 cP<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table><\/div>\n

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

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.<\/p>\n

These findings are preclinical and do not establish comparative clinical efficacy or safety.<\/p>\n

Beyond Mutation Prediction: Engineering Proteins Under Real Drug-Development Constraints<\/b><\/p>\n

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.<\/p>\n

Some experimentally validated mutations were located away from the conventional target-binding interface<\/b>, illustrating how AI-guided exploration can identify productive regions of sequence space beyond interface-focused design.<\/p>\n

The program also illustrates a broader progression in protein AI validation:<\/p>\n

computational benchmarking \u2192 experimental validation \u2192 repeated integration within a real drug-development workflow<\/b><\/p>\n

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

The Venus Protein AI Stack<\/b><\/p>\n

Matwings’ Venus<\/b> 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 Venus 1.0<\/b>, while Venus has since advanced to Venus 3.0, represented by VenusREM<\/b>, which integrates protein sequence, three-dimensional structure and evolutionary information for mutation-effect prediction.<\/p>\n

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.<\/p>\n

\n\n\n\n\n\n\n\n
\n

Generation<\/b><\/span><\/p>\n<\/td>\n

\n

Representative Model(s)<\/b><\/span><\/p>\n<\/td>\n

\n

Information Integrated<\/b><\/span><\/p>\n<\/td>\n

\n

Primary Role<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 1.0<\/b><\/span><\/p>\n<\/td>\n

\n

Venus 1.0<\/span><\/p>\n<\/td>\n

\n

Protein sequence<\/span><\/p>\n<\/td>\n

\n

Sequence-
centered
modeling<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 2.0<\/b><\/span><\/p>\n<\/td>\n

\n

Venus-ProSST<\/span><\/p>\n<\/td>\n

\n

Sequence + 3D structure<\/span><\/p>\n<\/td>\n

\n

Structure-aware
modeling<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 3.0<\/b><\/span><\/p>\n<\/td>\n

\n

VenusREM<\/span><\/p>\n<\/td>\n

\n

Sequence + 3D structure +
evolutionary information<\/span><\/p>\n<\/td>\n

\n

Mutation-effect
prediction<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Task-Specific
Models<\/b><\/span><\/p>\n<\/td>\n

\n

Venus-FSFP, Venus-Maxwell, Venus-Mine, Venus-RXN, Venus-
Fold<\/span><\/p>\n<\/td>\n

\n

Task-dependent<\/span><\/p>\n<\/td>\n

\n

Protein R&D and
engineering<\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table><\/div>\n

Certain models within the broader Venus portfolio are in development or planned stages.<\/i><\/p>\n

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

From External Validation to Therapeutic Creation<\/b><\/p>\n

The GenSci148 collaboration provides external validation of Matwings’ protein-engineering capabilities in a real therapeutic development program.<\/p>\n

In March 2026, Matwings established Shanghai Biowings Therapeutics Co., Ltd. (“Biowings Therapeutics”)<\/b> 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.<\/p>\n

“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\u2013experiment cycles in an actual R&D program,” said Prof. Liang Hong, Founder and Chief Scientist of Matwings.<\/b> “GenSci148 marks an important step from demonstrating individual model capabilities toward building a repeatable protein-engineering system.”<\/p>\n

“Matwings contributed important molecular engineering and optimization capabilities to the GenSci148 program,” said Dr. Lei Jin, CEO of GenSci.<\/b> “Rather than relying on one-time predictions, the teams repeatedly combined AI-guided design with experimental evidence to improve properties relevant to drug development.”<\/p>\n

About Matwings<\/b><\/p>\n

Shanghai Matwings Technology Co., Ltd.<\/b> 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.<\/p>\n

For more information, visit www.matwings.com<\/b><\/a>.<\/p>\n

About Biowings Therapeutics<\/b><\/p>\n

Shanghai Biowings Therapeutics Co., Ltd.<\/b> focuses on AI-enabled therapeutic asset creation and clinical translation.<\/p>\n

Scientific and Development Notice:<\/b> 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.<\/p>\n

Contact:<\/b><\/p>\n

Website: www.matwings.com<\/a>
E-mail: public@biowingsthera.com<\/a><\/span><\/p>","protected":false},"excerpt":{"rendered":"

<\/p>\n

The GenSci148 program illustrates a shift from one-time mutation prediction to iterative protein engineering under real drug-development constraints<\/b><\/p>\n

SHANGHAI<\/span>, Aug. 20, 2026<\/span> \/PRNewswire\/ — Shanghai Matwings Technology Co., Ltd. (“Matwings”)<\/b> today announced that GenSci148 Injection<\/b>, an investigational ophthalmic biologic developed by Changchun GeneScience Pharmaceutical Co., Ltd. (“GenSci”)<\/b>, has received clinical trial clearance in China for neovascular age-related macular degeneration (nAMD), diabetic macular edema (DME) and retinal vein occlusion (RVO).<\/p>\n

Matwings supported the GenSci148 program through four iterative AI\u2013wet 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\u2014illustrating a shift from predicting mutations to engineering therapeutic proteins under real drug-development constraints.<\/p>\n

Four AI\u2013Wet Lab Cycles, 222 Variants<\/b><\/p>\n

Matwings and GenSci implemented a closed-loop workflow combining AI-guided molecular design, wet-lab testing, experimental feedback and redesign<\/b>.<\/p>\n

Across four iterative cycles<\/b>, the teams evaluated 222 protein variants<\/b>. 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.<\/p>\n

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.<\/p>\n

The campaign therefore progressed from:<\/p>\n

activity optimization \u2192 broader developability optimization \u2192 multi-objective molecular engineering<\/b><\/p>\n

Across the optimization campaign, experimentally tested variants demonstrated improvements or favorable performance across six development-relevant properties:<\/p>\n

\n\n\n\n\n\n\n\n\n\n
\n

Development Parameter<\/b><\/span><\/p>\n<\/td>\n

\n

Observed Result<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

VEGF-A binding affinity<\/b><\/span><\/p>\n<\/td>\n

\n

Up to approximately 10-fold improvement<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

VEGF-A\/C\/D functional
blockade<\/b><\/span><\/p>\n<\/td>\n

\n

Up to approximately 3-fold improvement<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Nonclinical in vivo activity<\/b><\/span><\/p>\n<\/td>\n

\n

Inhibitory activity observed 84 days after dosing in the
evaluated retinal model<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Thermal stability<\/b><\/span><\/p>\n<\/td>\n

\n

Tm increased by up to approximately 4.5\u00b0C<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Protein expression<\/b><\/span><\/p>\n<\/td>\n

\n

Increased by up to approximately 27.6%<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

High-concentration formulation
viscosity<\/b><\/span><\/p>\n<\/td>\n

\n

Reduced by approximately 13 cP<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

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

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.<\/p>\n

These findings are preclinical and do not establish comparative clinical efficacy or safety.<\/p>\n

Beyond Mutation Prediction: Engineering Proteins Under Real Drug-Development Constraints<\/b><\/p>\n

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.<\/p>\n

Some experimentally validated mutations were located away from the conventional target-binding interface<\/b>, illustrating how AI-guided exploration can identify productive regions of sequence space beyond interface-focused design.<\/p>\n

The program also illustrates a broader progression in protein AI validation:<\/p>\n

computational benchmarking \u2192 experimental validation \u2192 repeated integration within a real drug-development workflow<\/b><\/p>\n

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

The Venus Protein AI Stack<\/b><\/p>\n

Matwings’ Venus<\/b> 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 Venus 1.0<\/b>, while Venus has since advanced to Venus 3.0, represented by VenusREM<\/b>, which integrates protein sequence, three-dimensional structure and evolutionary information for mutation-effect prediction.<\/p>\n

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.<\/p>\n

\n\n\n\n\n\n\n\n
\n

Generation<\/b><\/span><\/p>\n<\/td>\n

\n

Representative Model(s)<\/b><\/span><\/p>\n<\/td>\n

\n

Information Integrated<\/b><\/span><\/p>\n<\/td>\n

\n

Primary Role<\/b><\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 1.0<\/b><\/span><\/p>\n<\/td>\n

\n

Venus 1.0<\/span><\/p>\n<\/td>\n

\n

Protein sequence<\/span><\/p>\n<\/td>\n

\n

Sequence-
centered
modeling<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 2.0<\/b><\/span><\/p>\n<\/td>\n

\n

Venus-ProSST<\/span><\/p>\n<\/td>\n

\n

Sequence + 3D structure<\/span><\/p>\n<\/td>\n

\n

Structure-aware
modeling<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Venus 3.0<\/b><\/span><\/p>\n<\/td>\n

\n

VenusREM<\/span><\/p>\n<\/td>\n

\n

Sequence + 3D structure +
evolutionary information<\/span><\/p>\n<\/td>\n

\n

Mutation-effect
prediction<\/span><\/p>\n<\/td>\n<\/tr>\n

\n

Task-Specific
Models<\/b><\/span><\/p>\n<\/td>\n

\n

Venus-FSFP, Venus-Maxwell, Venus-Mine, Venus-RXN, Venus-
Fold<\/span><\/p>\n<\/td>\n

\n

Task-dependent<\/span><\/p>\n<\/td>\n

\n

Protein R&D and
engineering<\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Certain models within the broader Venus portfolio are in development or planned stages.<\/i><\/p>\n

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

From External Validation to Therapeutic Creation<\/b><\/p>\n

The GenSci148 collaboration provides external validation of Matwings’ protein-engineering capabilities in a real therapeutic development program.<\/p>\n

In March 2026, Matwings established Shanghai Biowings Therapeutics Co., Ltd. (“Biowings Therapeutics”)<\/b> 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.<\/p>\n

“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\u2013experiment cycles in an actual R&D program,” said Prof. Liang Hong, Founder and Chief Scientist of Matwings.<\/b> “GenSci148 marks an important step from demonstrating individual model capabilities toward building a repeatable protein-engineering system.”<\/p>\n

“Matwings contributed important molecular engineering and optimization capabilities to the GenSci148 program,” said Dr. Lei Jin, CEO of GenSci.<\/b> “Rather than relying on one-time predictions, the teams repeatedly combined AI-guided design with experimental evidence to improve properties relevant to drug development.”<\/p>\n

About Matwings<\/b><\/p>\n

Shanghai Matwings Technology Co., Ltd.<\/b> 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.<\/p>\n

For more information, visit www.matwings.com<\/b><\/a>.<\/p>\n

About Biowings Therapeutics<\/b><\/p>\n

Shanghai Biowings Therapeutics Co., Ltd.<\/b> focuses on AI-enabled therapeutic asset creation and clinical translation.<\/p>\n

Scientific and Development Notice:<\/b> 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.<\/p>\n

Contact:<\/b><\/p>\n

Website: www.matwings.com<\/a>
E-mail: public@biowingsthera.com<\/a><\/span><\/p>\n

<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":[],"rop_publish_now_history":[],"rop_publish_now_status":"pending","footnotes":""},"categories":[5,7],"tags":[],"class_list":["post-67653","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cision-pr-newswire","category-cision-pr-newswire-en"],"_links":{"self":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/67653","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=67653"}],"version-history":[{"count":0,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/67653\/revisions"}],"wp:attachment":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=67653"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=67653"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=67653"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}