摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-一项关于机器学习的新研究现在可以获得。根据来自马萨诸塞州剑桥的新闻，由News Rx记者报道，研究表明，“反应优化和表征依赖于反应产率的可靠测量，通常通过高效液相色谱(HPLC)测量。HPLC色谱图中的峰面积通过校准标准与分析物浓度相关，通常是已知浓度的纯样品S。”这项研究的资助者包括国防高级研究计划局（DAR PA）、DARPA加速分子发现、麻省理工学院制药发现和合成机器学习(MLPDS)联盟。我们的新闻记者从麻省理工学院的研究中获得了一句话：“制备校准Ru Ns所需的纯材料对于低产率反应可能是繁琐的，并且在小L反应尺度下具有技术挑战性。”本文提出了一种用HPLC定量测定反应产率的方法,该方法利用机器学习模型估算摩尔消光系数(摩尔消光系数),并结合紫外-可见吸收光谱和质谱分析,证明了该方法在医药和工艺化学中具有重要意义,包括酰胺偶联反应、钯催化交联偶联反应、亲核芳香取代反应、胺化反应等。这些反应都是使用自动化合成和分离平台进行的。无校准方法，如本文提出的方法，对于自动化平台能够自动发现、表征和优化反应是必要的。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning is now available. According to news originating from Cambridge, Massachusetts, by News Rx correspondents, research stated, "Reaction optimization and characterization depend on reliable measures of reaction yield, often measured by high-performanc e liquid chromatography (HPLC). Peak areas in HPLC chromatograms are correlated to analyte concentrations by way of calibration standards, typically pure sample s of known concentration." Funders for this research include Defense Advanced Research Projects Agency (DAR PA), DARPA Accelerated Molecular Discovery, MIT Machine Learning for Pharmaceuti cal Discovery and Synthesis (MLPDS) consortium. Our news journalists obtained a quote from the research from the Massachusetts I nstitute of Technology, "Preparing the pure material required for calibration ru ns can be tedious for low-yielding reactions and technically challenging at smal l reaction scales. Herein, we present a method to quantify the yield of reaction s by HPLC without needing to isolate the product(s) by combining a machine learn ing model for molar extinction coefficient estimation, and both UV-vis absorptio n and mass spectra. We demonstrate the method for a variety of reactions importa nt in medicinal and process chemistry, including amide couplings, palladium cata lyzed cross-couplings, nucleophilic aromatic substitutions, aminations, and hete rocycle syntheses. The reactions were all performed using an automated synthesis and isolation platform. Calibration-free methods such as the presented approach are necessary for such automated platforms to be able to discover, characterize , and optimize reactions automatically."
NETL
NSTL