LA JOLLA, Calif., March 20, 2024 /PRNewswire/ -- Model Medicines, a leading human health company specializing in generative AI-driven drug discovery, today announced groundbreaking headline results for the creation of a validated NCE, pan-antiviral library.

加利福尼亚州拉霍亚，2024年3月20日/PRNewswire/--Model Medicines是一家领先的人类健康公司，专门从事生成性人工智能驱动的药物发现，今天宣布了开创性的头条结果，用于创建经过验证的NCE泛抗病毒文库。

By leveraging proprietary AI technologies, Model Medicines achieved an impressive 66.7% hit rate at 10μM in discovering new chemical entities with antiviral activity as assessed in a gold-standard cell model of viral infection. Further, 46.7% of all evaluated compounds demonstrated sub-10μM IC50's - a key threshold to identify potent drug candidates with likely therapeutic potential.

通过利用专有的人工智能技术，模型药物在发现具有抗病毒活性的新化学实体方面取得了令人印象深刻的66.7%的命中率，如在病毒感染的金标准细胞模型中所评估的。此外，所有评估化合物中有46.7%表现出低于10μMIC50-这是鉴定具有可能治疗潜力的有效候选药物的关键阈值。

These results bring the total number of compounds discovered using Model Medicines' AI platform, GALILEO™ , to 192 across 26 targets. This also comes on the heels of the company's impressive 45.45% hit rate for its oncology program, announced in 2022..

这些结果使使用模型药物的AI平台GALILEO™在26个目标中发现的化合物总数达到192个。这也是继该公司于2022年宣布其肿瘤学计划令人印象深刻的45.45%命中率之后。。

Traditional drug discovery methods often yield hit rates of 1% - 4%, requiring the synthesis and testing of hundreds to thousands of compounds to identify a handful of potential leads. Modern AI-drug discovery hit rates ranging from 12% - 26%, for compounds evaluated at concentrations up to 100μM, have been reported by leading researchers and companies.

传统的药物发现方法通常产生1%-4%的命中率，需要合成和测试数百到数千种化合物才能识别出少数潜在的线索。领先的研究人员和公司已经报道，对于浓度高达100μM的化合物，现代人工智能药物发现的命中率从12%到26%不等。

Now, Model Medicines' AI-powered platform, GALILEO™  has dramatically improved the efficiency of the NCE hit discovery process with its 66.7% hit rate, representing a staggering 15-fold increase compared to traditional methods and a 3-fold increase over the best-in-class AI-driven drug discovery efforts, such as those reported by Schrödinger's Therapeutics Group (2023), Zhang et al.

现在，模型药物的人工智能平台GALILEO™以其66.7%的命中率显着提高了NCE命中发现过程的效率，与传统方法相比，惊人地增加了15倍，比同类最佳人工智能驱动的药物发现工作增加了3倍，例如Schrödinger治疗组（2023）Zhang等人报道的那些。

(2012), Rahman et al. (2021), and Jain et al. (2021). Moreover, Model Medicines' sub-10 μM hit rate of 46.7% is particularly impressive, as it not only demonstrates the platform's ability to identify a high proportion of active compounds, but also underscores its precision in identifying potent, high-potential compounds..

（2012），Rahman等人（2021）和Jain等人（2021）。此外，模型药物的低于10μM的命中率为46.7%，这一点特别令人印象深刻，因为它不仅证明了该平台能够识别高比例的活性化合物，而且还强调了其在识别有效的高潜力化合物方面的准确性。。

'Our results are not just groundbreaking for antiviral drug discovery; they represent a seismic shift in the entire landscape of pharmaceutical research and development.,' said Dr. Daniel Haders, CEO and Founder at Model Medicines. 'By efficiently navigating deep chemical space and accurately predicting the most promising compounds, we can significantly accelerate the development of novel, best-in-class therapeutics.'.

“我们的研究结果不仅是抗病毒药物发现的突破性成果；它们代表了整个药物研究和开发领域的巨大转变。”Model Medicines首席执行官兼创始人丹尼尔·哈德斯（DanielHaders）博士说通过有效地导航深层化学空间并准确预测最有希望的化合物，我们可以显着加速新型一流疗法的开发。”。

Model Medicines' study involved the virtual screening of over 52 trillion compounds using their proprietary GALILEO™  AI platform. The platform combines advanced machine learning algorithms, physics-based scoring, and absolute binding free energy calculations to identify compounds with the highest probability of success.

模型药物的研究涉及使用其专有的GALILEO™AI平台对超过52万亿种化合物进行虚拟筛选。该平台结合了先进的机器学习算法，基于物理的评分和绝对结合自由能计算，以识别成功概率最高的化合物。

From the initial screening, 15 compounds were selected for synthesis and experimental testing, resulting in 10 hits with activity at 10 μM, 7 of which exhibited a sub-10 μM IC50..

从初步筛选中，选择了15种化合物进行合成和实验测试，产生了10个命中，活性为10μM，其中7个表现出低于10μM的IC50。。

Importantly, Model Medicines' 2024 and 2022 studies only evaluated compound activity up to concentrations of 10 and 20 μM, respectively, while Schrödinger's Therapeutics Group (2023) and Rahman et al. (2021), for example, evaluated compound activity up to concentrations of 30 μM and 50μM, respectively.

重要的是，模型药物2024年和2022年的研究仅评估了浓度分别高达10和20μM的化合物活性，而薛定谔治疗组（2023）和Rahman等人（2021）分别评估了浓度高达30μM和50μM的化合物活性。

This suggests that Model Medicines' hit rates may be underreporting success/hit rates relative to leading studies in the field..

这表明，相对于该领域的领先研究，模型药物的命中率可能低估了成功率/命中率。。

Company/Research Group (Study Year)

公司/研究小组（学习年）

Hit Rate

命中率

Sub-10 μM IC50 Hit Rate

亚10μM IC50命中率

Therapeutic Area/Target

治疗区域/目标

Model Medicines (2024)

模型药物（2024）

66.7 %

66.7 %

46.7 %

46.7 %

Broad-spectrum antiviral NCEs

广谱抗病毒NCE

Model Medicines (2022)

模型药物（2022）

45.45 %

45.45 %

20.5 %

20.5 %

Oncology (AXL/BRD4) novel pharmacophores

肿瘤学（AXL/BRD4）新型药效团

Schrödinger's Therapeutics Group (2023)

薛定谔治疗集团（2023）

26 %

26 %

-

-（笑声）

Multiple

多重

Rahman et al. (2021)

Rahman等人（2021年）

12% - 26%

12% - 26%

-

-（笑声）

B. cenocepacia

B.cenocethy

Zhang et al. (2012)

张等人（2012）

14.2 %

14.2 %

14.2 %

14.2 %

Plasmodium falciparum

恶性疟原虫

Jain et al. (2021)

Jain等人（2021）

15.6 %

15.6 %

< 15.6%

< 15.6%

SARS-CoV-2

SARS冠状病毒2型

Traditional HTS Methods

传统高温超导方法

1% - 4%

1% - 4%

-

-（笑声）

Various

各种

Davey Smith, MD, MAS, FACP, FIDSA, Senior Clinical Advisor to Model Medicines and a renowned infectious disease specialist at UC San Diego Health, commented on the potential impact of Model Medicines' breakthrough: 'As we've seen with the devastating consequences of the COVID-19 pandemic, the world is in desperate need of a rapidly deployable, broad-spectrum antiviral that can effectively combat novel pathogens from the moment an outbreak occurs.

医学博士Davey Smith、MAS、FACP、FIDSA是模型药物的高级临床顾问，也是加州大学圣地亚哥分校健康中心的著名传染病专家，他评论了模型药物突破的潜在影响：“正如我们看到的新型冠状病毒肺炎大流行的毁灭性后果一样，世界迫切需要一种快速部署的广谱抗病毒药物，可以从爆发的那一刻起有效对抗新病原体。

Model Medicines' groundbreaking discovery of a new pan-antiviral chemical entity library, with an astounding 66.7% hit rate, represents a quantum leap forward in our ability to respond to viral threats on a global scale. This is not just a scientific achievement; it's a pivotal moment in our fight against infectious diseases.

Model Medicines开创性地发现了一个新的泛抗病毒化学实体库，命中率达到惊人的66.7%，代表着我们在全球范围内应对病毒威胁的能力取得了重大飞跃。这不仅仅是一项科学成就；这是我们抗击传染病的关键时刻。

Model Medicines' AI-driven approach is poised to revolutionize how we develop and deploy antiviral therapeutics, potentially saving millions of lives and transforming our capacity to confront future pandemics head-on. This is the kind of paradigm-shifting breakthrough we've been waiting for, and it couldn't have come at a more critical time for global health.'.

模型药物的人工智能驱动方法有望彻底改变我们开发和部署抗病毒治疗的方式，有可能挽救数百万人的生命，并改变我们对抗未来大流行的能力。这是我们一直在等待的一种范式转变突破，它不可能在全球健康的更关键时刻到来。”。

Model Medicines plans to advance the most promising compounds from this library into late-stage preclinical development and use the platform to initiate additional AI-driven drug discovery campaigns for other challenging therapeutic targets.

模型药物计划将该文库中最有希望的化合物推进到临床前开发的晚期，并使用该平台为其他具有挑战性的治疗靶点启动额外的AI驱动的药物发现活动。

RECENT PAPERS: Dissimilar, Drug-Like, Novel Chemical Entities (DDL-NCEs); Using Multimodal Generative AIBiochemistry's Hidden Matrix: Atomic ConstellationsVanity Metrics & Black Boxes ≠Therapeutics

最近的论文：不同的，类似药物的新型化学实体（DDL NCE）；使用多模态生成人工智能生物化学的隐藏矩阵：原子星座虚荣度量和黑匣子≠治疗

ABOUT MODEL MEDICINES:Model Medicines is a generative AI-driven human health company that uses AI to model all of chemistry and human biology to accelerate the creation of life-changing drugs. The company was founded in 2019 to deliver on the promise of AI drug discovery. With more than 192 compounds for 26 targets, they are delivering on the promise of AI drug discovery.

关于模型药物：模型药物是一家生成性人工智能驱动的人类健康公司，它使用人工智能对所有化学和人类生物学进行建模，以加速创造改变生命的药物。该公司成立于2019年，旨在实现人工智能药物发现的承诺。有超过192种化合物用于26个目标，它们正在实现AI药物发现的承诺。

The company has developed a robust pipeline of patent-pending therapeutics for oncology, infectious diseases, gastric disorders, neurological disorders, and weight disorders. The company is based in La Jolla, CA. To learn more, visit www.modelmedicines.com.

该公司开发了一系列正在申请专利的治疗肿瘤、传染病、胃病、神经系统疾病和体重障碍的强大药物。该公司位于加利福尼亚州拉霍亚。要了解更多信息，请访问www.modelmedicines.com。

SOURCE Model Medicines

来源模型药物