Evaluation of an In silico pipeline for drug discovery – a sustainable alternative model to laboratory based – drug discovery without borders.

评估药物发现的计算机模拟管道 - 基于实验室的可持续替代模型 - 无国界药物发现。

• 批准号: 87520
• 金额: $ 12.71万
• 依托单位: INTELLIGENT OMICS LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=87520
• 关键词: Evaluation; silico; pipeline; drug; discovery

Drug discovery is an expensive, time consuming, and unsustainable process requiring large teams, significant use of animal models, and extensive physical laboratory resources. The process is also prone to failure because many of the methods used are unrepresentative of the disease state or organism being targetted. Despite the significant investment of biological, technical, and financial resources into the High Throughput Screening (THS) process, the drop off rate is high with few contenders even reaching trials in human subjects. This resource requirement has meant that drug discovery has been significantly impacted by the COVID-19 pandemic and subsequent lockdown of laboratory staff. We believe there is an alternative to this process using computer-based artificial intelligence-driven approaches here termed biologically driven In silico high throughput screening and drug discovery.With the MDC we are constructing a drug discovery pipeline based on existing artificial Intelligence in silico (computer-based) tools. These will be utilised in this project to identify alternative druggable targets for the KRas related pathway in lung cancer. This will be achieved through the application of the pipeline to high dimensional molecular data (transcriptomic) for lung cancer held in public repositories. We aim to identify a number of druggable contenders and associated small molecule-based compounds that can target these. We also will seek to validate the biological relevance of these through rapid automated cell line validation.The validation of this process will provide an alternative cost-effective sustainable approach to drug discovery which can be used with minimal resource constraints, reduced environmental impact, reduced costs, reduced use of animals, and human disease targetting. Thus we will circumvent many of the limitations of current HTS approaches. This will open up further opportunities for new cost-effective drug discovery allowing drugs to be developed in areas where there has traditionally been a lack of investment, such as rare or orphaned diseases.

药物发现是一个昂贵，耗时且不可持续的过程，需要大型团队，大量使用动物模型和广泛的物理实验室资源。这一过程也容易失败，因为所使用的许多方法不能代表所针对的疾病状态或生物体。尽管在高通量筛选（THS）过程中投入了大量的生物、技术和财政资源，但脱落率很高，甚至很少有竞争者进入人体试验。此资源需求意味着药物研发受到COVID-19大流行及随后实验室人员封锁的重大影响。我们相信有一个替代这个过程使用基于计算机的人工智能驱动的方法在这里被称为生物驱动的计算机高通量筛选和药物发现。与MDC我们正在构建一个药物发现管道基于现有的人工智能计算机（基于计算机）工具。这些将用于本项目，以确定肺癌中KRas相关途径的替代药物靶点。这将通过将管道应用于公共存储库中保存的肺癌高维分子数据（转录组学）来实现。我们的目标是确定一些可药用的竞争者和相关的小分子化合物，可以针对这些。我们还将寻求通过快速自动化细胞系验证来验证这些的生物学相关性。对这一过程的验证将为药物发现提供一种替代的具有成本效益的可持续方法，该方法可以以最小的资源限制、减少的环境影响、降低的成本、减少的动物使用和人类疾病靶向来使用。因此，我们将规避目前HTS方法的许多限制。这将为新的具有成本效益的药物发现开辟更多的机会，使药物能够在传统上缺乏投资的领域开发，例如罕见或孤儿疾病。