Intelligent Chemical Structure Browser for Drug Discovery and Optimization

项目总结 协作药物发现公司(CDD)建议开发一种新型智能数据浏览器，该浏览器将使 药物化学家开发新的药物化合物以更有效地浏览和组织实验 数据以一种直观的方式。拟议中的浏览器本质上将超链接化学空间，并允许化学家 在化学铅系列中的化合物之间轻松导航，遵循与从一个化合物 在他们的头脑中直观地映射的心理模型中的下一个复合。在和之间导航 扩展领先系列以发现进入动物研究和临床试验的最佳候选药物 包括药物发现流水线的关键阶段：后续大笔投资的成功取决于 做出正确的决定。这个阶段还特别强调创造性和直觉性思维。现有 帮助从事这项任务的科学家的软件将数据以表格的形式列出，这使得汇编变得困难 并比较快速探索如何进一步优化前景的想法所需的基本数据 候选人。我们提议的智能浏览器将支持更自然、更直观的工作流程。 这项技术的一项关键创新是我们开发的组织方法 基于子结构-上层结构关系的偏序分子结构 图表。我们的半格表示提供了一种机器可计算的格式，可以捕获 药物化学家凭直觉判断的相关化学实体之间的关系。 预期的主要影响包括(1)更快地将铅系列开发为候选药物，(2)应节省的成本 更有效地使用合成和分析资源，最重要的是(3)更好的科学决策 关于哪些化合物应该追求并进入临床流水线。在这个阶段做出更好的决定 药物发现过程应该增加被选中的候选药物成功的可能性 作为FDA批准的药物通过临床流水线出现，并改善 那些毒品。即使这些概率的小幅增加乘以所需的投资规模 通过临床试验服用药物可以转化为很大的价值。我们已经在以下方面验证了这种价值认知 与潜在的制药公司客户进行初步的市场调查。 好了！

PROJECT SUMMARY Collaborative Drug Discovery, Inc. (CDD) proposes to develop a novel intelligent data browser that will enable medicinal chemists developing new drug compounds to more efficiently browse and organize experimental data in an intuitive way. The proposed browser will essentially “hyperlink” chemical space and allow chemists to navigate easily among compounds in a chemical lead series following the same pathways that lead from one compound to the next in the mental models that they intuitively map in their heads. Navigating through and extending a lead series to discover the optimal drug candidate to advance into animal studies and clinical trials comprises a critical stage of the drug discovery pipeline: the success of large subsequent investments depends on making the right decision. This stage also especially emphasizes creative and intuitive thinking. Existing software that assists scientists engaged in this task tabulates data in formats that make it difficult to assemble and compare the essential data needed to rapidly explore ideas about how to further optimize promising candidates. Our proposed intelligent browser will support more natural and intuitive workflows. A key enabling innovation for this technology is a methodology that we have developed to organize molecular structures through a partial ordering based on the substructure-superstructure relation as a Hasse diagram. Our semilattice representation provides a machine computable format that can capture the relationships among related chemical entities that a medicinal chemist intuits. Expected key impacts include (1) faster development of lead series into drug candidates, (2) cost savings due to more efficient use of synthesis and assay resources, and most importantly (3) better scientific decisions about which compounds to pursue and advance into the clinical pipeline. Better decisions at this stage in the drug discovery process should increase the probability that drug candidates that are chosen will successfully emerge through the clinical pipeline as FDA approved drugs, and improve the effectiveness and safety profile of those drugs. Even a small increase in these probabilities multiplied by the size of the investments required to take drugs through clinical trials translates into a large value. We have validated this perception of value in preliminary market research with potential pharmaceutical company customers. !