A Randomised, Double-blind, Placebo-controlled, Phase 1 First-in-human Study to Investigate the Safety, Tolerability, Pharmacokinetics, and Food Effect of Single- and Multiple-ascending Doses of BEN8744 in Healthy Subjects.

BEN8744 is an experimental new medicine for treating inflammatory bowel diseases such as Ulcerative Colitis.
The study will test single and repeated doses of BEN8744 or placebo by mouth. BEN8744 is a first in human study, so will start with a small dose and the dose will be increased as the study progresses. The goal is to find out its side effects and blood levels when taken by mouth and whether food affects the blood levels.
This is a 3-part study (Parts A, B and C) in up to 108 healthy people, aged 18-65.
Part A, will include up to 64 participants, single doses of BEN8744 or placebo. They'll take about 2 weeks to finish the study, stay on the ward for 4 nights and 5 days in a row and make 2 outpatient visits.
Part B, will include up to 12 participants, single doses of BEN8744 with and without food. They'll take up to 3 weeks to finish the study, stay on the ward for 4 nights and 5 days in a row on 2 occasions, and make 2 outpatient visits.
Part C will include up to 32 participants repeat doses of the BEN8744 or placebo for 14 days. They'll take about 4 weeks to complete the study, stay on the ward for 17 nights and 18 days in a row and make 2 outpatient visits.

开始日期2023-08-30

申办/合作机构

BenevolentAI Bio Ltd.

NCT04737304 / Completed临床1/2期

A First-in-Human, Double-Blind, Randomised, Vehicle Controlled Phase I/II Proof of Concept Study to Investigate the Safety, Tolerability, Pharmacokinetics and Efficacy of BEN2293 in Patients With Mild to Moderate Atopic Dermatitis

A randomised, adaptive design, double-blind, placebo-controlled, first-in-human, two-part study to investigate the safety, tolerability, PK and preliminary efficacy of multiple topical doses of BEN2293 in patients with mild to moderate AD.

开始日期2020-10-14

申办/合作机构

BenevolentAI Bio Ltd.

EUCTR2017-000877-35-IT / Not yet recruiting临床2期

Dose finding phase IIb study of Bavisant to evaluate its safety and efficacy in treatment of excessive daytime sleepiness (EDS) in parkinson's Disease (PD). - Treatment of excessive daytime sleepiness with Bavisant in Parkinson's Disease Patients (CASPAR)

开始日期2017-12-04

申办/合作机构

BenevolentAI Bio Ltd.

100 项与 BenevolentAI Ltd. 相关的临床结果

登录后查看更多信息

0 项与 BenevolentAI Ltd. 相关的专利（医药）

登录后查看更多信息

项与 BenevolentAI Ltd. 相关的文献（医药）

2022-03-24·The Journal of Clinical Endocrinology & Metabolism2区 · 医学

Identification of Rare Loss-of-Function Genetic Variation Regulating Body Fat Distribution

2区 · 医学

Article

作者: Cai, Lina ; Koprulu, Mine ; Day, Felix R ; Semple, Robert K ; Van de Streek, Marcel ; Kerrison, Nicola D ; McCarthy, Mark I ; Glastonbury, Craig A ; Patel, Satish ; Wareham, Nicholas J ; Savage, David B ; Wittemans, Laura B L ; Rocha, Nuno ; Zhao, Yajie ; O’Rahilly, Stephen ; Griffin, John D ; Lotta, Luca A ; Barroso, Inês ; Stewart, Isobel D ; Lucarelli, Debora M E ; Saudek, Vladimir ; Dong, Liang ; Small, Kerrin S ; Langenberg, Claudia ; Li, Chen ; Bowker, Nicholas ; Scott, Robert A ; Wheeler, Eleanor ; Luan, Jian’an ; Perry, John R B

AbstractContextBiological and translational insights from large-scale, array-based genetic studies of fat distribution, a key determinant of metabolic health, have been limited by the difficulty in linking predominantly noncoding variants to specific gene targets. Rare coding variant analyses provide greater confidence that a specific gene is involved, but do not necessarily indicate whether gain or loss of function (LoF) would be of most therapeutic benefit.ObjectiveThis work aimed to identify genes/proteins involved in determining fat distribution.MethodsWe combined the power of genome-wide analysis of array-based rare, nonsynonymous variants in 450 562 individuals in the UK Biobank with exome-sequence-based rare LoF gene burden testing in 184 246 individuals.ResultsThe data indicate that the LoF of 4 genes (PLIN1 [LoF variants, P = 5.86 × 10–7], INSR [LoF variants, P = 6.21 × 10–7], ACVR1C [LoF + moderate impact variants, P = 1.68 × 10–7; moderate impact variants, P = 4.57 × 10–7], and PDE3B [LoF variants, P = 1.41 × 10–6]) is associated with a beneficial effect on body mass index–adjusted waist-to-hip ratio and increased gluteofemoral fat mass, whereas LoF of PLIN4 (LoF variants, P = 5.86 × 10–7 adversely affects these parameters. Phenotypic follow-up suggests that LoF of PLIN1, PDE3B, and ACVR1C favorably affects metabolic phenotypes (eg, triglycerides [TGs] and high-density lipoprotein [HDL] cholesterol concentrations) and reduces the risk of cardiovascular disease, whereas PLIN4 LoF has adverse health consequences. INSR LoF is associated with lower TG and HDL levels but may increase the risk of type 2 diabetes.ConclusionThis study robustly implicates these genes in the regulation of fat distribution, providing new and in some cases somewhat counterintuitive insight into the potential consequences of targeting these molecules therapeutically.

FragGT: Fragment-based evolutionary molecule generation with gene types

作者: Meyers, Joshua ; Brown, Nathan

De novo molecular design is effective for optimizing compounds with desirable properties in drug discovery. In the realm of chemoinformatics, population-based evolutionary approaches have been known for over a decade including those that use retrosynthetically inspired fragment-based workflows to to balance the generation of synthesizable molecules with a sufficiently expressive molecular generator. We describe FragGT, a fragment-based de novo molecular design approach that uses an evolutionary algorithm to optimize molecules towards an objective function. We rely on the concept of gene types to hop between related molecular fragments where a fragment's gene type is defined by the nature of its connections to adjacent groups. We show that this simple approach achieves competitive performance on the GuacaMol benchmark suite with a low computational cost and the additional benefits of transparency and practicality.

项与 BenevolentAI Ltd. 相关的新闻（医药）

2024-10-19

·Endpoints

A Q&A with a Nobel Prize winner; Pfizer meets with Starboard; J&J reports Q3 earnings; and more

Welcome back to Endpoints Weekly, your review of the week’s top biopharma headlines. Want this in your inbox every Saturday morning? Current Endpoints readers can visit their reader profile to add Endpoints Weekly. New to Endpoints? Sign up here . Earnings season officially kicked off this week with Johnson & Johnson reporting its Q3 results. Endpoints will have our regular wall-to-wall coverage of the rest of the industry’s earnings, so keep checking your inboxes the next couple weeks for all the latest. — Max Gelman Endpoints hosted our first-ever AI Day in New York this week, with senior biopharma correspondent Andrew Dunn moderating. One of his discussions, with recently crowned Nobel Prize winner David Baker , is available as a Q&A on our website. The two chatted about the AI space, the future of protein design, and more. You can check it out here , and all of the recordings should be available online next week. Pfizer met with Starboard Value this week, after the activist investor took a $1 billion stake in the pharma giant. While the companies have not responded to requests for comment on how the meeting went, sources have described Starboard as a tenacious activist firm willing to engage in drawn-out, complex fights. Endpoints’ Max Bayer has the latest. Johnson & Johnson revealed a handful of pipeline cuts in its third-quarter earnings, including a Phase 2 study of seltorexant in patients with probable Alzheimer’s disease, a Phase 2 bipolar treatment, and a Phase 2 treatment for Parkinson’s. In oncology, J&J ended a Phase 3 study of Imbruvica for relapsed or refractory patients with mantle cell lymphoma in combination with venetoclax . Overall, the company beat investor expectations despite underperformance for its medtech unit. The FDA said in court documents last week that it would reconsider its decision to remove Eli Lilly’s blockbuster GLP-1 tirzepatide from its shortage list, potentially reopening the door for compounders to distribute their own versions of the drug. Following a request for clarity from the Alliance for Pharmacy Compounding, US regulators said on Thursday that they do not plan to take action against compounders while it reconsiders. But the APC has made clear that the announcement doesn’t protect pharmacies from state actions or challenges from Eli Lilly. At IDWeek 2024, both Merck and Pfizer reported results for their RSV antibody and vaccine, respectively. Merck said its experimental therapy reduced infants’ risk of certain lower respiratory infections by 60.4% compared to placebo in a Phase 2b/3 study, while Pfizer said its approved shot was 90% effective at preventing the most severe outcomes in the first-ever vaccination season. SPOTLIGHT Q&A: Sanofi’s R&D head reflects on his first year, a post-Dupixent future, and finding an identity House’s prominent China critic Jim McGovern leads opposition to Biosecure Act: ‘I would prefer to go back to the drawing board’ BenevolentAI CEO is out after less than a year on the job MORE IN R&D MORE IN DEALS MORE IN FINANCING MORE IN PHARMA MORE IN FDA+ MORE IN MANUFACTURING MORE IN HEALTH TECH

临床2期临床3期临床结果

2024-10-17

·Endpoints

BenevolentAI CEO is out after less than a year on the job

BenevolentAI’s CEO Joerg Moeller is stepping down effective immediately, the London biotech said Thursday, in the latest leadership shakeup atop the company. Since going public in early 2022 via a SPAC, BenevolentAI’s stock price has fallen over 90%. Its lead drug candidate fell short in a mid-stage eczema study last year, eventually leading to the program’s discontinuation. Moeller, formerly the global R&D head of Leo Pharma, was brought in to replace former CEO Joanna Shields in January. Now, less than 10 months into his tenure, BenevolentAI announced Moeller is headed out the door. The company didn’t give a reason for his exit, other than to say it was “immediate.” The company also didn’t name a replacement, though it did say that founder Ken Mulvany is now executive chairman. Mulvany rejoined BenevolentAI’s board in May, amid a broader boardroom battle . In a Thursday statement, Mulvany said the company has “only scratched the surface of our platform’s incredible potential.” Founded in 2013, BenevolentAI was one of the first biotech startups focused on artificial intelligence, alongside peers like Exscientia, Recursion Pharmaceuticals and Atomwise. Benevolent had pitched its AI approach as allowing it to slash preclinical costs and move faster. In its pitch to investors when it was going public via a SPAC, the biotech shared projections that its pipeline would grow from 12 programs in 2021 to more than 50 in 2026, eventually reaching 87 in 2030. It said its aim was to file one to two INDs per year for the next few years, increasing to a rate of two to three IND filings per year for 2027 to 2031. But those bold forecasts haven’t panned out. Today, BenevolentAI’s pipeline lists one program in the clinic and eight preclinical programs. It has slashed R&D and overall spending plans, including rounds of layoffs last May and this April . The company’s sole clinical-stage drug reported positive results from a healthy volunteer Phase 1 study earlier this year. And the company said last month it is in active out-licensing and partnership discussions around that molecule. BenevolentAI’s struggles are in line with several of its peers who have pitched R&D revolutions with their technology over the past decade. But the lead drug candidates from these AI-focused biotechs have fallen short in the clinic . Several of these original AI-focused biotechs have struggled to survive. Exscientia recently agreed to a merger deal with Recursion. Atomwise’s founding CEO Abe Heifets quietly left the company earlier this year with no announced successor, Endpoints News previously reported .

临床1期高管变更并购临床结果IPO

2024-10-10

·医药地理

2024诺贝尔化学奖花落AI！人工智能辅助药物设计引领蛋白设计新纪元

引言 10月9日，2024年诺贝尔化学奖授予大卫·贝克（David Baker）、戴米斯·哈萨比斯（Demis Hassabis）和约翰·江珀（John Jumper），以表彰他们在蛋白质设计和蛋白质结构预测领域作出的贡献。其中，一半奖项授予了 David Baker，他开发了计算机化方法，构建了全新的蛋白质种类；另一半授予了 Demis Hassabis 和 John Jumper，他们利用人工智能预测蛋白质的三维结构。在医药领域，新药的发现与开发历来是一个复杂、耗时且成本高昂的过程。近年来，随着人工智能（AI）技术的飞速发展，尤其是人工智能辅助药物设计（AIDD）的兴起，这一传统格局正被逐步打破。 01 什么是AIDD？ 1.1 AIDD的定义与背景 AIDD，即人工智能辅助药物设计，是指利用AI技术加速和优化药物发现与设计的全过程。它涵盖了从目标识别、化合物筛选、结构优化到临床试验设计的各个环节。自20世纪60年代计算机模拟分子行为（CADD）的初步尝试以来，AIDD经历了从机器学习到深度学习的技术飞跃，如今已成为医药研发不可或缺的一部分。图：深度学习辅助分子对接示意图 02 AIDD的发展 2.1 AI在蛋白设计规则上的突破近年来，AI在蛋白设计领域取得了显著进展。以DeepMind的AlphaFold为例，该算法在2022年7月成功预测了所有已分类蛋白质的3D结构，其预测精度远超其他算法。这一成就不仅极大地推动了结构生物学的发展，也为基于结构的药物设计提供了前所未有的便利。通过AI技术，研究人员能够更精准地理解蛋白质的结构特性，从而设计出更具针对性的药物分子。然而药物靶点发现只是药物研发的“第一步”，后续还需要基于靶点的结构去“筛选”可以与靶点结合的潜在药物，对药物进行修饰以便优化其活性、药代性、毒性等，这才可能进入临床实验。每个步骤都需要AlphaFold的应用出现，才能让药物设计的整个流程被有效的加速。图：AIDD常用机器学习方法此外，AIDD在靶向治疗（靶向疗法：旨在攻击癌细胞特有的分子标志物）研发中的应用也不容小觑。比如，英国的 BenevolentAI 公司就利用AI技术发现了一种新的抗癌药物——PARP（聚ADP核糖聚合酶）抑制剂。通过机器学习模型对大量的生物医学文献和数据库进行深度学习和分析，该公司成功找出PARP抑制剂在卵巢癌中的潜在疗效。这一成果标志着AI不仅能帮助研发新药，还能为已知药物找到新的治疗途径。如图为该公司针对肌萎缩侧索硬化症与特应性皮炎这两个热门疾病在研的药物信息。图：BenevolentAI公司在研药物信息数据来源：Pharma-ONE数据库公司分析版块，中国医药工业信息中心如图为针对PARP靶点作用药物的疾病分析。据数据统计可见，主要为癌症与肿瘤方面。图：PARP靶点作用药物的疾病类型分析数据来源：Pharma-ONE数据库靶点分析版块，中国医药工业信息中心 2.2 AIDD案例分析 ● Insilico Medicine的GENTRL技术 Insilico Medicine在2019年发布了首个使用AI系统生成张量强化学习（GENTRL）的活性体内候选药物。该技术在短短46天内设计出针对纤维化的先导化合物，展示了AIDD在加速药物发现方面的巨大潜力。 ●英科智能的AI发现新靶点 2021年12月，英科智能宣布实现AI发现新靶点的行业突破，其AI生成的新型分子已进入临床阶段。这一成果不仅证明了AIDD在靶点识别上的高效性，也为后续的药物开发奠定了坚实基础。 03 AIDD的潜在问题 3.1模型优化方面尽管现有的AI模型在药物筛选、靶点识别和药物设计等方面取得了一定的成功，但模型的准确性和泛化能力仍有待提高。这主要是因为药物研发的数据往往具有高度的复杂性和不确定性，导致模型在训练过程中容易出现过拟合或欠拟合的问题。为了解决这个问题，研究者们正在不断探索新的算法和模型架构，以提高模型的预测能力和鲁棒性。例如，通过引入深度学习技术，可以构建更加复杂的网络结构，以捕捉药物分子与目标靶点之间的复杂相互作用。然而，这也带来了更高的计算成本和资源需求，使得模型在实际应用中受到一定的限制。 3.2主动学习的开发方面 AIDD领域也面临着诸多挑战。主动学习是一种通过选择性地标注数据来优化模型训练过程的方法，它可以显著提高模型的性能和效率。然而，在药物研发领域，由于数据的稀缺性和标注成本的高昂，主动学习的应用受到了一定的限制。此外，如何设计有效的主动学习策略，以在有限的标注资源下最大化模型的性能，也是一个亟待解决的问题。为了解决这个问题，研究者们正在探索基于不确定性估计、多样性采样和交互式标注等方法的主动学习策略，以期在减少标注成本的同时提高模型的性能。 3.3其他方面除了上述两个方面的问题，AIDD在药物研发中还面临着数据安全、隐私保护、知识产权等方面的挑战。例如，在数据外包给第三方进行AIDD服务时，如何确保数据的安全性和隐私性，避免数据泄露和滥用，是一个重要的考虑因素。此外，随着AIDD技术的不断发展，如何保护和创新药物研发中的知识产权，也是一个亟待解决的问题。 04 大模型于AIDD运用的前景：GPT大模型在蛋白、基因领域的运用如今，GPT大模型凭借其强大的语言理解和生成能力，已经在自然语言处理、机器翻译等多个领域取得了显著成果。而这一技术正在向生命科学领域拓展，特别是在蛋白质和基因领域的应用，为AIDD带来了革命性的变化。在蛋白质领域，GPT大模型可以通过对大量蛋白质序列数据的学习，预测蛋白质的结构和功能。这对于理解蛋白质在生命过程中的作用至关重要，有助于推动药物研发和疾病治疗的发展。例如，通过预测蛋白质的结构，科学家可以更准确地识别药物靶点，设计出更具针对性的药物。同时，GPT大模型还可以预测蛋白质的功能区域和相互作用，为蛋白质工程提供有力支持，推动新药研发的创新。在基因领域，GPT大模型的应用同样令人瞩目。通过学习和理解基因组学、蛋白质组学和医学遗传学的海量术语，GPT大模型能够绘制基因、蛋白质和疾病之间的复杂关系，为遗传疾病的研究和治疗提供新的途径。例如，GP-GPT等专用大型语言模型已经展示了在遗传医学问答和基因-疾病关联鉴定方面的卓越性能，有助于加速阿尔茨海默氏症和其他遗传疾病等领域的研究。 05 结语 AIDD的发展离不开跨学科的合作。未来，生物学、化学、计算机科学等多个领域的专家将更紧密地合作，共同解决医药研发中的难题。这种合作模式将促进AIDD技术的不断创新和应用。 END 如需获取更多数据洞察信息或公众号内容合作，请联系医药地理小助手微信号：pharmadl001

临床研究

100 项与 BenevolentAI Ltd. 相关的药物交易

登录后查看更多信息

100 项与 BenevolentAI Ltd. 相关的转化医学

登录后查看更多信息

组织架构

使用我们的机构树数据加速您的研究。

或

查看完整样例数据

管线布局

2024年11月20日管线快照

管线布局中药物为当前组织机构及其子机构作为药物机构进行统计，早期临床1期并入临床1期，临床1/2期并入临床2期，临床2/3期并入临床3期

药物发现

临床前

临床1期

临床2期

其他

登录后查看更多信息

当前项目

药物(靶点)	适应症	全球最高研发状态

BEN-2293 ( NTRK x TrkA x TrkB x TrkC )	特应性皮炎更多	临床2期
BEN-8744 ( PDE10A )	炎症性肠病更多	临床1期
BEN-28010 ( Chk1 )	胶质母细胞瘤更多	临床前
BEN-34712 ( RARα x RARβ2 )	肌萎缩侧索硬化更多	临床前
Parkinson's disease therapy(BenevolentAI Ltd)	帕金森病更多	药物发现